AUTOMATIC SPEECH RECOGNITION

Advancing African-Accented English Speech Recognition: Epistemic Uncertainty-Driven Data Selection for Generalizable ASR Models (2025.acl-srw)

Challenge:	Automatic Speech Recognition (ASR) errors in voice-based dialog systems pose significant impediments to downstream tasks.
Approach:	They propose an automatic speech recognition (ASR) error-aware loss function to inject failed mentions and resolved entity names into the knowledge graph to enhance its awareness of unresolved mentions.
Outcome:	The proposed system enhances the knowledge graph's awareness of unresolved mentions by injecting pairs of failed mentions and resolved entities into the knowledge map.

Copied to clipboard

Bonaventure F. P. Dossou

metaCAT: A Metadata-based Task-oriented Chatbot Annotation Tool (2020.aacl-demo)

Challenge:	Accents play a pivotal role in shaping human communication, a new study finds . existing ASR systems often perform inadequately, even mispronouncing African names .
Approach:	They propose a method that uses epistemic uncertainty to automate annotation to reduce costs and human labor.
Outcome:	The proposed method reduces costs and human labor by reducing data annotation and epistemic uncertainty.

Copied to clipboard

Ximing Liu, Wei Xue, Qi Su, Weiran Nie, Wei Peng

Natural Language Interfaces

Challenge:	Creating high-quality annotated dialogue corpora necessitates a high level of human engagements.
Approach:	They propose to develop an annotation tool specifically for developing task-oriented dialogue data that provides comprehensive metadata annotation coverage to the domain, intent, and span information.
Outcome:	The tool provides comprehensive metadata annotation coverage to domain, intent, and span information.

Hyper-BTS Dataset: Scalability and Enhanced Analysis of Back TranScription (BTS) for ASR Post-Processing (2024.findings-eacl)

Copied to clipboard

Chanjun Park, Jaehyung Seo, Seolhwa Lee, Junyoung Son, Hyeonseok Moon, Sugyeong Eo, Chanhee Lee, Heuiseok Lim

Audio Query Handling System with Integrated Expert Models and Contextual Understanding (2025.emnlp-industry)

Challenge:	Automatic Speech Recognition (ASR) post-processing requires substantial amounts of data, requiring expensive phonetic transcription experts.
Approach:	They propose a "Hyper-BTS" dataset that is five times larger than prior studies . they propose criteria for categorizing error types within ASR post-processing .
Outcome:	The proposed method can generate ASR inputs from clean text using a text-to-speech system.

Copied to clipboard

Naveen Vakada, Arvind Krishna Sridhar, Yinyi Guo, Erik Visser

Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of Speech (2024.acl-short)

Challenge:	Existing chatbots are limited to specific audio tasks, but the domain of audio content related queries remains underexplored.
Approach:	They propose to use an intent classifier to route queries to audio-related experts using a diverse audio query dataset.
Outcome:	The proposed system outperforms state-of-the-art LLMs on custom audio tasks and MMAU sound set benchmarks.

Copied to clipboard

Adrien Pupier, Maximin Coavoux, Jérôme Goulian, Benjamin Lecouteux

No Label? No Problem: Unsupervised Continual Learning for Adaptive Medical ASR (2026.eacl-industry)

Challenge:	Direct dependency parsing of the speech signal is proposed as a way of incorporating prosodic information into the parser and bypassing the limitations of a pipeline approach.
Approach:	They propose to use graph-based parsing and sequence labeling based parses to integrate prosodic information into the parser and bypass limitations of pipeline approaches.
Outcome:	The proposed graph based approach outperforms a pipeline approach on a large treebank of spoken french, despite having 30% fewer parameters.

Copied to clipboard

Meizhu Liu, Tao Sheng

Audio De-identification - a New Entity Recognition Task (N19-2)

Challenge:	Medical audio often contains specialized terminology, such as medication names, which existing ASR systems struggle to transcribe accurately.
Approach:	They propose an unsupervised continual learning ASR framework that adapts to new data while preserving prior knowledge.
Outcome:	Experiments on real-world medical audio show that the proposed framework improves over state-of-the-art models.

Copied to clipboard

Ido Cohn, Itay Laish, Genady Beryozkin, Gang Li, Izhak Shafran, Idan Szpektor, Tzvika Hartman, Avinatan Hassidim, Yossi Matias

Building Accurate Low Latency ASR for Streaming Voice Search in E-commerce (2023.acl-industry)

Challenge:	Named Entity Recognition (NER) is an important step in de-identification (de-ID) of medical records, many of which are recorded conversations between a patient and a doctor.
Approach:	They propose to use Named Entity Recognition (NER) to detect audio spans with entity mentions in medical records and then use it to evaluate the results.
Outcome:	The proposed pipeline is based on a large labeled segment of the Switchboard and Fisher audio datasets and compares it with a benchmark.

Copied to clipboard

Abhinav Goyal, Nikesh Garera

Exploring the Effect of Dialect Mismatched Language Models in Telugu Automatic Speech Recognition (2022.naacl-srw)

Challenge:	Recent years have witnessed the popularity of end-to-end ASR models, which have demonstrated higher accuracy compared to traditional pipelines with separate acoustic, pronunciation, and language models.
Approach:	They build accurate LSTM, attention and CTC based streaming ASR models for large-scale Hinglish voice search.
Outcome:	The proposed model achieves a word error rate (WER) of 3.69% without EOS and 4.78% with EOS, with 1300 ms (46.64%) reduction in latency.

Copied to clipboard

Aditya Yadavalli, Ganesh Sai Mirishkar, Anil Vuppala

Shachar Mirkin, Michal Jacovi, Tamar Lavee, Hong-Kwang Kuo, Samuel Thomas, Leslie Sager, Lili Kotlerman, Elad Venezian, Noam Slonim

Challenge:	Existing studies have found that the ASR system is susceptible to dialect variations within a language, thereby adversely affecting the APR.
Approach:	They propose to build a dialect-specific AM while keeping the Language Model constant for all the dialects and to reduce the degradation by 9% and 15%.
Outcome:	The proposed model can be built for three different Telugu regional dialects while keeping the Language Model constant for all the dialects.

A Recorded Debating Dataset (L18-1)

Copied to clipboard

Synthetic Doctor-Patient Dialogue Generation for Robust Medical ASR: A Scalable Pipeline for Vocabulary Expansion and Privacy Preservation (2026.eacl-industry)

Challenge:	Existing research in computational argumentation and debating technologies focuses on argumentation mining, but other tasks are being addressed as well.
Approach:	They describe a dataset of debating speeches in English that is used for research . they use an automatic speech recognition system to produce a more "nLP-friendly" text .
Outcome:	The proposed dataset contains 60 speeches on various controversial topics, each in five formats corresponding to different stages in production.

Copied to clipboard

Kefei Liu, Meizhu Liu

Post-ASR Correction in Hindi: Comparing Language Models and Large Language Models in Low-Resource Scenarios (2026.eacl-short)

Challenge:	Existing ASR models struggle with high word error rates (WER) on clinical vocabulary, especially medication names.
Approach:	They propose to generate doctor-patient dialogues in both text and audio formats using a curated set of over 124,000 medical terms.
Outcome:	The proposed pipeline generated over 1 billion audios with ground truth transcriptions.

Copied to clipboard

Rishabh Kumar, Amrith Krishna, Ganesh Ramakrishnan, Preethi Jyothi

PriMock57: A Dataset Of Primary Care Mock Consultations (2022.acl-short)

Challenge:	Automatic Speech Recognition (ASR) systems for low-resource languages produce erroneous transcripts due to limited annotated data and linguistic complexity.
Approach:	They compare language models and large language models for post-ASR correction in Hindi . they observe a scaling trend under zero-shot ICL where mid-sized LLMs degrade performance before marginal recovery at extreme scales.
Outcome:	The proposed model outperforms larger models in both fine-tuning and in-context learning settings.

Copied to clipboard

Alex Papadopoulos Korfiatis, Francesco Moramarco, Radmila Sarac, Aleksandar Savkov

Thesis Proposal: Self-Adaptive and Epistemic Uncertainty-Guided ASR of Dense Intra-Sentential Code-Switched Speech for African Low-Resource Languages (2026.acl-srw)

Challenge:	Recent advances in Automatic Speech Recognition (ASR) have made it possible to reliably produce automatic transcripts of clinician-patient conversations.
Approach:	They present a public access, high quality dataset of 57 mocked primary care consultations . they aim to offer a benchmark for conversational medical ASR and consultation note generation from transcripts.
Outcome:	The proposed dataset can be used as a benchmark for conversational medical ASR and consultation note generation from transcripts.

Copied to clipboard

Umar Baba Umar, Sulaimon Adebayo Bashir, Abdulmalik Danlami Mohammed, Amina Gogo Tafida

Who Needs Decoders? Efficient Estimation of Sequence-Level Attributes with Proxies (2024.eacl-long)

Challenge:	Existing multilingual and pretrained ASR systems improve general recognition accuracy but are weak at switch regions and are sensitive to language imbalance during adaptation.
Approach:	They propose a self-adaptive and epistemic uncertainty-guided framework for African low-resource code-switched ASR using Hausa–English and Hausa-Yorùbá as case studies.
Outcome:	The proposed framework is based on Hausa–English and Hausa-Yorùbá as case studies.

Copied to clipboard

Yassir Fathullah, Puria Radmard, Adian Liusie, Mark Gales

ASR-EC Benchmark: Evaluating Large Language Models on Chinese ASR Error Correction (2025.emnlp-industry)

Challenge:	Autoregressive decoding is expensive for many sequence-to-sequence tasks, but for some downstream tasks, the actual decoding output is not needed, just attributes of the sequence.
Approach:	They propose non-autoregressive proxy models that can efficiently predict scalar-valued sequence-level attributes from the encodings, avoiding the expensive decoding stage.
Outcome:	The proposed models outperform ensembles in machine translation (MT) and automatic speech recognition (ASR) while being significantly faster.

Copied to clipboard

Victor Junqiu Wei, Weicheng Wang, Di Jiang, Yuanfeng Song, Lu Wang

A Dataset for Speech Emotion Recognition in Greek Theatrical Plays (2022.lrec-1)

Challenge:	Automatic Speech Recognition (ASR) systems have a substantial number of erroneous recognition due to environmental noise, ambiguity, etc.
Approach:	They use a benchmark dataset to analyze ASR errors in the Chinese language . they then apply large language models to correct ASR error correction .
Outcome:	The proposed method is based on a dataset of ASR errors in the Chinese language . it shows prompting is not effective for ASR error correction .

Copied to clipboard

Maria Moutti, Sofia Eleftheriou, Panagiotis Koromilas, Theodoros Giannakopoulos

Chinese Spoken Named Entity Recognition in Real-world Scenarios: Dataset and Approaches (2024.findings-acl)

Challenge:	Speech Emotion Recognition (SER) is a task that is difficult to perform by humans due to subjectiveness of the emotional content.
Approach:	They propose to use GreThE to collect data for speech emotion recognition in Greek plays.
Outcome:	The proposed dataset contains utterances from various actors and plays, along with respective valence and arousal annotations.

Copied to clipboard

Shilin Zhou, Zhenghua Li, Chen Gong, Lei Zhang, Yu Hong, Min Zhang

Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation (2025.findings-acl)

Challenge:	Current Chinese Spoken NER datasets are laboratory-controlled and are limited in topics.
Approach:	They propose to use Chinese Spoken NER datasets to extract entities from speech to help voice assistants better grasp the intent behind user's questions and instructions.
Outcome:	The proposed methods improve on self-training-asr and mapping then distilling, and even compared with GPT4.0, they achieve better results.

Copied to clipboard

Sreyan Ghosh, Mohammad Sadegh Rasooli, Michael Levit, Peidong Wang, Jian Xue, Dinesh Manocha, Jinyu Li

Information Retrieval

Challenge:	Generative Error Correction (GEC) is a powerful post-processing method to boost the performance of Automatic Speech Recognition systems.
Approach:	They propose a method to augment GEC models with retrieved entities to improve accuracy in out-of-domain and out-od scenarios.
Outcome:	The proposed method outperforms baseline models on multiple datasets and settings.

Automatic Speech Recognition System-Independent Word Error Rate Estimation (2024.lrec-main)

Copied to clipboard

Chanho Park, Mingjie Chen, Thomas Hain

RED-ACE: Robust Error Detection for ASR using Confidence Embeddings (2022.emnlp-main)

Challenge:	Word error rate (WER) is a metric used to evaluate the quality of transcriptions produced by Automatic Speech Recognition systems.
Approach:	They propose a hypothesis generation method for ASR system-dependent WER estimation . they use phonetically similar or linguistically more likely alternative words to generate hypotheses .
Outcome:	The proposed method outperforms baseline estimators on in-domain data and out-of-domain on Switchboard and CALLHOME.

Copied to clipboard

Zorik Gekhman, Dina Zverinski, Jonathan Mallinson, Genady Beryozkin

Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders (2021.acl-long)

Challenge:	ASR Error Detection (AED) models post-process the output of Automatic Speech Recognition systems, in order to detect transcription errors.
Approach:	They propose to use ASR model's word-level confidence scores to combine ASR models with transcribed text to improve AED performance.
Outcome:	The proposed models combine the confidence scores and transcribed text into a contextualized representation.

Copied to clipboard

Chen Xu, Bojie Hu, Yanyang Li, Yuhao Zhang, Shen Huang, Qi Ju, Tong Xiao, Jingbo Zhu

Direct Segmentation Models for Streaming Speech Translation (2020.emnlp-main)

Challenge:	End-to-end Speech Translation (E2E ST) encoders lack global context representation, whereas MT encoder lacks it.
Approach:	They propose a Stacked Acoustic-and-Textual Encoding method for speech translation . they propose an adaptor module to alleviate representation inconsistency .
Outcome:	The proposed method achieves state-of-the-art BLEU scores of 18.3 and 25.2 on two ST tasks.

Copied to clipboard

Javier Iranzo-Sánchez, Adrià Giménez Pastor, Joan Albert Silvestre-Cerdà, Pau Baquero-Arnal, Jorge Civera Saiz, Alfons Juan

BEA-Base: A Benchmark for ASR of Spontaneous Hungarian (2022.lrec-1)

Challenge:	Existing approaches to stream ST combine advances in ASR and MT to achieve high quality translations without compromising the speed of the system.
Approach:	They propose to concatenate an Automatic Speech Recognition system followed by a Machine Translation system.
Outcome:	The proposed models improve on the Europarl-ST dataset on the BLEU score.

Copied to clipboard

Peter Mihajlik, Andras Balog, Tekla Etelka Graczi, Anna Kohari, Balázs Tarján, Katalin Mady

Isometric Neural Machine Translation using Phoneme Count Ratio Reward-based Reinforcement Learning (2024.findings-naacl)

Challenge:	Hungarian is spoken by 15 million people, yet, easily accessible Automatic Speech Recognition (ASR) benchmark datasets are practically unavailable.
Approach:	They propose to use a subset of the BEA spoken Hungarian database to assess ASR, primarily for conversational AI applications.
Outcome:	The proposed framework achieves 45% reduction in recognition error rate compared to classical approach without external language model or additional supervised data.

Copied to clipboard

Shivam Mhaskar, Nirmesh Shah, Mohammadi Zaki, Ashishkumar Gudmalwar, Pankaj Wasnik, Rajiv Shah

KEBAP: Korean Error Explainable Benchmark Dataset for ASR and Post-processing (2023.emnlp-main)

Challenge:	Traditional Automatic Video Dubbing (AVD) pipelines use isometric-NMT algorithms to regulate the length of the output text.
Approach:	They propose an isometric-NMT system that regulates the length of the output text . they propose a phoneme Count Compliance score to measure length compliance .
Outcome:	The proposed approach improves phoneme count compliance scores by 36% compared to state-of-the-art models in English-Hindi language pairs.

Copied to clipboard

Seonmin Koo, Chanjun Park, Jinsung Kim, Jaehyung Seo, Sugyeong Eo, Hyeonseok Moon, Heuiseok Lim

WER we are and WER we think we are (2020.findings-emnlp)

Challenge:	Conventional evaluation metrics for automatic speech recognition systems produce a singular aggregate score, which is insufficient for understanding specific system vulnerabilities.
Approach:	They propose to introduce the Korean Error Explainable Benchmark Dataset for ASR and Post-processing (KEBAP) this method enables a more balanced assessment encompassing speech recognition accuracy and user readability.
Outcome:	The proposed method enables a more balanced assessment encompassing speech recognition accuracy and user readability.

Copied to clipboard

Piotr Szymański, Piotr Żelasko, Mikolaj Morzy, Adrian Szymczak, Marzena Żyła-Hoppe, Joanna Banaszczak, Lukasz Augustyniak, Jan Mizgajski, Yishay Carmiel

A Comprehensive Evaluation of Incremental Speech Recognition and Diarization for Conversational AI (2020.coling-main)

Challenge:	Recent reports of very low word error rates (WERs) achieved by modern automatic speech recognition systems are skepticism towards the accuracy of modern systems.
Approach:	They propose to use a dataset to test automatic speech recognition systems . they propose guidelines for creating real-life datasets with high quality annotations .
Outcome:	The proposed system achieves 81% of accuracy on human-chatbot interactions compared to the best reported results on human conversations and public benchmarks.

Copied to clipboard

Angus Addlesee, Yanchao Yu, Arash Eshghi

Contrastive and Consistency Learning for Neural Noisy-Channel Model in Spoken Language Understanding (2024.naacl-long)

Challenge:	Automatic Speech Recognition (ASR) systems are increasingly powerful and more numerous with several options existing as a service.
Approach:	They evaluate the most popular automatic speech recognition systems with metrics and experiments designed with these standards in mind.
Outcome:	The most popular ASR systems are Microsoft and IBM, and none are suitable for natural spontaneous conversations in real-time.

Copied to clipboard

Suyoung Kim, Jiyeon Hwang, Ho-Young Jung

DITTO: Data-efficient and Fair Targeted Subset Selection for ASR Accent Adaptation (2023.acl-long)

Challenge:	End-to-end learning models require large volume of speech data with intent labels . however, models are sensitive to inconsistencies between training and evaluation conditions .
Approach:	They propose a module-based approach to learn intent in a noisy-channel model . they correlate error patterns between clean and noisy ASR transcripts .
Outcome:	The proposed method outperforms existing methods and improves in noisy environments.

Copied to clipboard

Suraj Kothawade, Anmol Mekala, D.Chandra Sekhara Hetha Havya, Mayank Kothyari, Rishabh Iyer, Ganesh Ramakrishnan, Preethi Jyothi

WER-BERT: Automatic WER Estimation with BERT in a Balanced Ordinal Classification Paradigm (2021.eacl-main)

Challenge:	State-of-the-art automatic speech recognition systems exhibit disparate performance on varying speech accents.
Approach:	They propose to use submodular mutual information to find the most informative set of utterances matching a target accent within a fixed budget.
Outcome:	The proposed model is 3-5 times more label-efficient on the Indic-TTS and L2 datasets than other methods.

Copied to clipboard

Akshay Krishna Sheshadri, Anvesh Rao Vijjini, Sukhdeep Kharbanda

Information Extraction & Text Mining

Challenge:	Automatic Speech Recognition (ASR) systems are evaluated using Word Error Rate (WER) a higher WER means a lower percentage of errors between the ground truth and the transcription of the system.
Approach:	They propose a new balanced paradigm for automatic Word Error Rate estimation using a Librispeech dataset and a Google Cloud's Speech-to-Text API.
Outcome:	The proposed approach is more effective than regression in a classification setting, but suffers from heavy class imbalance.

A Benchmark of French ASR Systems Based on Error Severity (2025.coling-main)

Copied to clipboard

Antoine Tholly, Jane Wottawa, Mickael Rouvier, Richard Dufour

Vietnamese Automatic Speech Recognition: A Revisit (2026.findings-eacl)

Challenge:	Automatic Speech Recognition (ASR) transcription errors are often assessed using metrics that compare them with a reference transcription.
Approach:	They propose to categorize transcription errors into four levels of severity based on objective linguistic criteria, contextual patterns, and the use of content words as the unit of analysis.
Outcome:	The proposed evaluation categorizes errors into four levels of severity based on objective linguistic criteria, contextual patterns, and the use of content words as the unit of analysis.

Copied to clipboard

Thi Vu, Linh The Nguyen, Dat Quoc Nguyen

Generative Music Models’ Alignment with Professional and Amateur Users’ Expectations (2025.findings-acl)

Challenge:	Existing datasets with low quality and inconsistent annotations are insufficient for high-quality models.
Approach:	They propose a pipeline for aggregating and preprocessing high-quality ASR datasets from diverse, potentially noisy, open-source sources.
Outcome:	The proposed pipeline provides a foundation for training and evaluating state-of-the-art Vietnamese ASR systems.

Copied to clipboard

Zihao Wang, Jiaxing Yu, Haoxuan Liu, Zehui Zheng, Yuhang Jin, Shuyu Li, Shulei Ji, Kejun Zhang

Data Quality Issues in Multilingual Speech Datasets: The Need for Sociolinguistic Awareness and Proactive Language Planning (2025.acl-long)

Challenge:	Recent years have witnessed rapid advances in text-to-music generation using large language models.
Approach:	They propose a task to align AI-generated music with human expressions . they use a dataset of over 1.5 million songs to analyze their content .
Outcome:	The proposed framework outperforms baseline models and facilitates end-to-end generation of songs audio.

Copied to clipboard

Mingfei Lau, Qian Chen, Yeming Fang, Tingting Xu, Tongzhou Chen, Pavel Golik

Comprehensive Punctuation Restoration for English and Polish (2021.findings-emnlp)

Challenge:	Despite their growing importance, the quality of these datasets remains under-researched.
Approach:	They propose guidelines and recommendations to address quality issues in future dataset development . they find that macro-level issues are more prevalent in less institutionalized, often under-resourced languages .
Outcome:	The results highlight the need for proactive language planning and enhanced data quality control in the process of automatic speech recognition dataset creation.

Copied to clipboard

Michał Pogoda, Tomasz Walkowiak

Challenge:	Punctuation restoration is a fundamental requirement for the readability of text derived from Automatic Speech Recognition systems.
Approach:	They evaluate several methods in the comprehensive punctuation reconstruction task by comparing two languages with a model to determine the quality of the punctuated word.
Outcome:	The proposed model improves on two languages with relatively simple and complex morphologies.

Beyond Common Words: Enhancing ASR Cross-Lingual Proper Noun Recognition Using Large Language Models (2024.findings-emnlp)

Copied to clipboard

Rishabh Kumar, Sabyasachi Ghosh, Ganesh Ramakrishnan

DECM: Evaluating Bilingual ASR Performance on a Code-switching/mixing Benchmark (2024.lrec-main)

Challenge:	In this work, we address the challenge of cross-lingual proper noun recognition in automatic speech recognition systems where proper nodes in an utterance may originate from a language different from the language in which the ASR system is trained.
Approach:	They propose a dictionary-based method to correct ASR predictions in a large language model .
Outcome:	The proposed method significantly reduces word error rates across cross-lingual proper noun recognition tasks involving three secondary languages.

Copied to clipboard

Enes Yavuz Ugan, Ngoc-Quan Pham, Alexander Waibel

Advancing Test-Time Adaptation in Wild Acoustic Test Settings (2024.emnlp-main)

Challenge:	Code-switched (CSW) speech is a linguistic phenomenon that occurs when spoken utterances switch languages between sentences.
Approach:	They propose to use a dataset to evaluate German-English CSW speech . they show that the dataset includes splits with varying degrees of CSW .
Outcome:	The proposed dataset includes spontaneous speech from diverse domains, enabling realistic CSW evaluation in German-English.

Copied to clipboard

Hongfu Liu, Hengguan Huang, Ye Wang

Samrómur: Crowd-sourcing Data Collection for Icelandic Speech Recognition (2020.lrec-1)

Challenge:	Existing wild vision TTA methods fail to handle speech data due to the unique characteristics of high-entropy speech frames, which are unreliably filtered out even when containing crucial semantic content.
Approach:	They propose a method for acoustic foundation models to perform confidence-based adaptation in wild acustic test settings.
Outcome:	The proposed method outperforms baselines under Gaussian noise, environmental sounds, accent variations, and sung speech in the wild.

Copied to clipboard

David Erik Mollberg, Ólafur Helgi Jónsson, Sunneva Þorsteinsdóttir, Steinþór Steingrímsson, Eydís Huld Magnúsdóttir, Jon Gudnason

Non-Autoregressive Chinese ASR Error Correction with Phonological Training (2022.naacl-main)

Challenge:	Samrómur is a web application built upon Mozilla Foundation’s open-source voice collection platform Common Voice.
Approach:	They describe an ongoing project of speech data collection using the web application Samrómur which is built upon Common Voice, Mozilla Foundation’s web platform for open-source voice collection.
Outcome:	The proposed system will be the largest open speech corpus for Icelandic collected from the public domain.

Copied to clipboard

Zheng Fang, Ruiqing Zhang, Zhongjun He, Hua Wu, Yanan Cao

Discovering Canonical Indian English Accents: A Crowdsourcing-based Approach (L18-1)

Challenge:	Existing methods to correct ASR errors focus on fixed-length corrections, but rarely consider variable-length ones.
Approach:	They propose a non-autoregressive method to correct Chinese ASR errors . they use phonological tokens to extend the source sentence for variable-length correction .
Outcome:	The proposed method improves word error rate and speeds up inference by 6.2 times compared with the autoregressive model.

Copied to clipboard

Sunayana Sitaram, Varun Manjunath, Varun Bharadwaj, Monojit Choudhury, Kalika Bali, Michael Tjalve

Multilingual Models for ASR in Chibchan Languages (2024.naacl-long)

Challenge:	Automated Speech Recognition systems degrade in performance when recognizing accents that are different from the ones in training data.
Approach:	They propose to adapt Acoustic Models that are trained on one accent to a target accent by using a small amount of speech data in the target accent.
Outcome:	The proposed model can be used to identify accents in Indian English and other languages.

Copied to clipboard

Rolando Coto-Solano, Tai Wan Kim, Alexander Jones, Sharid Loáiciga

Leveraging Large Pre-trained Multilingual Models for High-Quality Speech-to-Text Translation on Industry Scenarios (2025.coling-main)

Challenge:	Existing algorithms for low resource-intensive languages are not available for these languages . a paper comparing the performance of different models and algorithms for these extremely low resource languages is presented.
Approach:	They propose to fine-tune four ASR algorithms to create monolingual models for Bribri and Cabécar . they then use the best performing algorithm to train joint and transfer learning models for both languages .
Outcome:	The proposed algorithms are effective in both Bribri and Cabécar, but especially in Bribri.

Copied to clipboard

Marko Avila, Josep Crego

Large Vocabulary Read Speech Corpora for Four Ethiopian Languages: Amharic, Tigrigna, Oromo and Wolaytta (2020.lrec-1)

Challenge:	Speech-to-Text Translation systems rely on a sequential pipeline that combines ASR and MT models.
Approach:	They propose a parameter-efficient framework that integrates one LPSM with a multilingual MT engine.
Outcome:	The proposed framework integrates one LPSM with a multilingual MT engine.

Copied to clipboard

Solomon Teferra Abate, Martha Yifiru Tachbelie, Michael Melese, Hafte Abera, Tewodros Abebe, Wondwossen Mulugeta, Yaregal Assabie, Million Meshesha, Solomon Afnafu, Binyam Ephrem Seyoum

Sequential Randomized Smoothing for Adversarially Robust Speech Recognition (2021.emnlp-main)

Challenge:	Automatic Speech Recognition (ASR) is one of the most important technologies to support spoken communication in modern life.
Approach:	They have developed four large speech corpora for four Ethiopian languages . they have word error rates of 37.65%, 31.03%, 38.02%, 33.89% for each language .
Outcome:	The proposed corpora achieve word error rates of 37.65%, 31.03%, 38.02%, 33.89% for Amharic, Tigrigna, Oromo and Wolaytta.

Copied to clipboard

Raphael Olivier, Bhiksha Raj

ArzEn: A Speech Corpus for Code-switched Egyptian Arabic-English (2020.lrec-1)

Challenge:	Existing, naive defenses against adversarial attacks are lagging . a new paper aims to break these defenses with adaptive noise ensembling .
Approach:	They propose a randomized smoothing paradigm that can be used to break adversarial attacks . they use speech enhancement methods and a novel use for ASR output ensembling methods .
Outcome:	The proposed model is robust to all attacks that use inaudible noise and can only be broken with very high distortion.

Copied to clipboard

Injy Hamed, Ngoc Thang Vu, Slim Abdennadher

Semantic Role Labeling from Chinese Speech via End-to-End Learning (2024.findings-acl)

Challenge:	a corpus of Arabic-English code-switching (CS) spontaneous speech is collected in an Egyptian university soundproof room . the language in Egypt is rather complex and poses many challenges to natural language processing (NLP)
Approach:	They present an Egyptian Arabic-English code-switching (CS) spontaneous speech corpus.
Outcome:	The proposed corpus is designed to be used in automatic speech recognition systems . it provides a useful resource for analyzing the CS phenomenon from linguistic, sociological, and psychological perspectives.

Copied to clipboard

Huiyao Chen, Xinxin Li, Meishan Zhang, Min Zhang

MCLF: A Multi-grained Contrastive Learning Framework for ASR-robust Spoken Language Understanding (2023.findings-emnlp)

Challenge:	Semantic role labeling (SRL) has traditionally focused on text input.
Approach:	They propose an end-to-end approach for SRL from speech integrating ASR and SRL in a joint-learning framework, focusing on the Chinese language.
Outcome:	The proposed model improves on the Chinese Proposition Bank 1.0 dataset and the existing model with improved performance.

Copied to clipboard

Zhiqi Huang, Dongsheng Chen, Zhihong Zhu, Xuxin Cheng

Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech (2021.emnlp-main)

Challenge:	Trending ASR-robust SLU systems have seen impressive improvements through global contrastive learning, but they can easily lead to severe semantic changes.
Approach:	They propose a two-stage multi-grained contrastive learning framework to improve ASR robustness . they first adapt pre-trained language models to downstream SLU datasets and then fine-tune it on the corresponding dataset.
Outcome:	The proposed framework improves on four datasets and four BERT-like backbone models.

Copied to clipboard

Katrin Tomanek, Vicky Zayats, Dirk Padfield, Kara Vaillancourt, Fadi Biadsy

A Survey of Multilingual Models for Automatic Speech Recognition (2022.lrec-1)

Challenge:	Automatic Speech Recognition systems perform poorly on atypical speech and heavily accented speech.
Approach:	They add a residual adapter to the encoder layer to improve model adaptation . they show that the residual adapters update only a tiny fraction of the model parameters .
Outcome:	The proposed model fine-tuning improves performance on atypical and accented speech . the system can update only a tiny fraction of the model parameters .

Copied to clipboard

Hemant Yadav, Sunayana Sitaram

UMRSpell: Unifying the Detection and Correction Parts of Pre-trained Models towards Chinese Missing, Redundant, and Spelling Correction (2023.acl-long)

Challenge:	Automatic Speech Recognition (ASR) systems have achieved human-like performance for a few languages, but the majority of the world’s languages do not have usable systems due to the lack of large speech datasets to train these models.
Approach:	They propose to use unlabeled speech data to build multilingual ASR models that can be used for improved performance on low-resource languages.
Outcome:	The proposed models can be used to improve performance on low-resource languages by using unlabeled speech data.

Copied to clipboard

Zheyu He, Yujin Zhu, Linlin Wang, Liang Xu

Evaluating the Efficacy of Large Acoustic Model for Documenting Non-Orthographic Tribal Languages in India (2024.lrec-main)

Challenge:	Chinese Spelling Correction (CSC) is a task of detecting and correcting misspelled charac- ters in Chinese texts.
Approach:	They propose a model to learn detection and correction parts together from a multi-task learning perspective.
Outcome:	The proposed model can learn detection and correction parts together from a multi-task learning perspective.

Copied to clipboard

Tonmoy Rajkhowa, Amartya Roy Chowdhury, Hrishikesh Ravindra Karande, S. R. Mahadeva Prasanna

Arab Voices: Mapping Standard and Dialectal Arabic Speech Technology (2026.findings-acl)

Challenge:	Pre-trained Large Acoustic Models have been shown to improve performance in spoken languages . however, their potential for novel under-resourced languages is not fully known .
Approach:	They propose to use pre-trained Large Acoustic Models to document under-resourced languages . they use scripts from languages that hold a prominent presence in the geographical regions .
Outcome:	The proposed model can document under-resourced languages in the electronic domain . the model can be used to document languages with a written script .

Copied to clipboard

Peter Sullivan, AbdelRahim A. Elmadany, Alcides Alcoba Inciarte, Muhammad Abdul-Mageed

Evaluating Workflows for Creating Orthographic Transcripts for Oral Corpora by Transcribing from Scratch or Correcting ASR-Output (2024.lrec-main)

Challenge:	Dialectal Arabic datasets embody a range of domain, dialect, and quality.
Approach:	They propose a framework for automatic speech recognition in dialectal Arabic to address the limited data availability encountered in dialects.
Outcome:	The proposed framework provides access to 31 datasets covering 14 dialects to better address the limited data availability encountered in dialectal Arabic speech processing.

Copied to clipboard

Jan Gorisch, Thomas Schmidt

WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models (2025.acl-long)

Challenge:	Automated speech recognition systems can reduce transcription effort, but few studies have evaluated this potential.
Approach:	They compare efforts for manual transcription vs. automatic correction of ASR-output . they use audio recordings from varying settings to create orthographic transcripts .
Outcome:	The proposed methods reduce transcription time by 7 times on average for selected data and transcription conventions compared with corrected transcripts . the more complex the primary data, the more time has to be spent on corrections - the paper concludes a similar study could be conducted in 2022 .

Copied to clipboard

Yifu Chen, Shengpeng Ji, Haoxiao Wang, Ziqing Wang, Siyu Chen, Jinzheng He, Jin Xu, Zhou Zhao

Extracting Biomedical Entities from Noisy Audio Transcripts (2024.lrec-main)

Challenge:	Existing RAG frameworks rely on Automatic Speech Recognition to process speech input, which discards crucial audio information and increases computational overhead.
Approach:	They propose a retrieval augmented generation framework with native, end-to-end audio support that integrates audio and text into a unified knowledge representation.
Outcome:	The proposed framework can perform 10x faster than current pipelines while delivering 10x acceleration.

Copied to clipboard

Nima Ebadi, Kellen Morgan, Adrian Tan, Billy Linares, Sheri Osborn, Emma Majors, Jeremy Davis, Anthony Rios

INTapt: Information-Theoretic Adversarial Prompt Tuning for Enhanced Non-Native Speech Recognition (2023.findings-acl)

Challenge:	Named Entity Recognition (NER) is particularly affected by noise, often termed the ASR-NLP gap.
Approach:	They propose a dataset to bridge the ASR-NLP gap in the biomedical domain by extracting adverse drug reactions and mentions of entities from the Brief Test of Adult Cognition by Telephone (BTACT) exam.
Outcome:	The proposed method can clean 2,000 clean and noisy recordings and eliminate errors using zero-shot and few-shot methods.

Copied to clipboard

Eunseop Yoon, Hee Suk Yoon, John Harvill, Mark Hasegawa-Johnson, Chang Yoo

Responsible & Trustworthy NLP

Challenge:	Existing approaches to improve ASR performance with pre-trained models require updating the pre-training model weights.
Approach:	They propose a method that uses prompts concatenated to the original input to re-modulate attention of the pre-trained model.
Outcome:	The proposed model improves the performance of L2 English and increases similarity between L2 and L1 accents.

From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition (2025.emnlp-main)

Copied to clipboard

Tianduo Wang, Lu Xu, Wei Lu, Shanbo Cheng

Effectively pretraining a speech translation decoder with Machine Translation data (2020.emnlp-main)

Challenge:	Recent advances in Automatic Speech Recognition (ASR) have been fueled by massive speech corpora, but extending coverage to diverse languages with limited resources remains a formidable challenge.
Approach:	They propose a pipeline that converts large-scale text corpora into synthetic speech using off-the-shelf text-to-speech (TTS) models.
Outcome:	The proposed pipeline generates 500,000 hours of synthetic speech in ten languages and achieves transcription error reductions of over 30%.

Copied to clipboard

Ashkan Alinejad, Anoop Sarkar

AccentDB: A Database of Non-Native English Accents to Assist Neural Speech Recognition (2020.lrec-1)

Challenge:	Existing approaches to improve the performance of AST systems are based on pretraining the encoder parameters using an ASR model, but using a pretrained MT decoder is not beneficial or improves the results.
Approach:	They propose to use an adversarial regularizer to bring the encoder representations of the ASR and NMT tasks closer even though they are in different modalities.
Outcome:	The proposed model can be pre-trained using the Automatic Speech Recognition (ASR) task even in different languages and improves in low resource settings.

Copied to clipboard

Afroz Ahamad, Ankit Anand, Pranesh Bhargava

Multi-Sentence Resampling: A Simple Approach to Alleviate Dataset Length Bias and Beam-Search Degradation (2021.emnlp-main)

Challenge:	aaron e. sanchez and joe saunders: automatic speech recognition still faces a major challenge . they say accents are a way of pronouncing a language, and speakers always have manner of speaking . esassen: accents can be used to identify non-native speakers of a speech .
Approach:	They propose to create a database of speech samples in non-native accents for ASR testing . they also propose to introduce accent neutralization of non- native accents to native accent .
Outcome:	The proposed model is compared against human-labelled accent classes and is generalized against human data.

Copied to clipboard

Ivan Provilkov, Andrey Malinin

Multilinguality

Challenge:	Neural Machine Translation suffers from a beam-search problem after a certain point, especially for long sentences.
Approach:	They propose a data augmentation technique that concatenates several sentences from the original dataset to make a long training example.
Outcome:	The proposed technique significantly reduces degradation with growing beam size and improves translation quality on the IWSTL15 En-Vi, IWStl17 En-Fr, and WMT14 En-De datasets.

To Distill or Not to Distill? On the Robustness of Robust Knowledge Distillation (2024.acl-long)

Copied to clipboard

Abdul Waheed, Karima Kadaoui, Muhammad Abdul-Mageed

Responsible & Trustworthy NLP

Challenge:	Existing models for multilingual automatic speech recognition (ASR) are computationallyintensive and lack proper comprehensive evaluations.
Approach:	They propose to distill knowledge from large teacher models into smaller student variants that are more efficient.
Outcome:	The proposed model outperforms existing models on standard benchmarks and dialectal data.

Masked Audio Text Encoders are Effective Multi-Modal Rescorers (2023.findings-acl)

Copied to clipboard

Jinglun Cai, Monica Sunkara, Xilai Li, Anshu Bhatia, Xiao Pan, Sravan Bodapati

Resilience of Large Language Models for Noisy Instructions (2024.findings-emnlp)

Challenge:	Masked Language Models (MLMs) have proven to be effective for second-pass rescoring in Automatic Speech Recognition systems.
Approach:	They propose a multi-modal masked language model rescorer which integrates acoustic representations into the input space of MLM.
Outcome:	The proposed model reduces word error rate (WER) by 4%-16% on in-domain and 3%-7% on out-of-domain datasets over the text-only baseline.

Copied to clipboard

Bin Wang, Chengwei Wei, Zhengyuan Liu, Geyu Lin, Nancy Chen

PersonaLM: Language Model Personalization via Domain-distributed Span Aggregated K-Nearest N-gram Retrieval Augmentation (2023.findings-emnlp)

Challenge:	Large language models (LLMs) are powerful tools for interpreting human commands and generating text.
Approach:	They examine the resilience of large language models against five common types of disruptions including ASR, OCR, grammatical errors, typographical errors and distractive content.
Outcome:	The models show resistance to noise, but their performance suffers . authors evaluated the models against five common types of disruptions based on their results .

Copied to clipboard

Puneet Mathur, Zhe Liu, Ke Li, Yingyi Ma, Gil Keren, Zeeshan Ahmed, Dinesh Manocha, Xuedong Zhang

MASRI-HEADSET: A Maltese Corpus for Speech Recognition (2020.lrec-1)

Challenge:	Existing language modeling tools for automatic speech recognition (ASR) are difficult to personalize.
Approach:	They propose a domain-distributed Span-Aggregated K-nearest N-gram retrieval augmentation to improve language modeling for automatic speech recognition (ASR) personalization.
Outcome:	The proposed model outperforms baselines on Wikitext-103, UserLibri, and ASAP datasets with a 10-16% improvement in perplexity and a 5-8% reduction in word error rates.

Copied to clipboard

Carlos Daniel Hernandez Mena, Albert Gatt, Andrea DeMarco, Claudia Borg, Lonneke van der Plas, Amanda Muscat, Ian Padovani

DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction (2025.findings-acl)

Challenge:	Maltese is the national language of Malta and is spoken by approximately 500,000 people.
Approach:	They present the first spoken Maltese corpus designed purposely for Automatic Speech Recognition (ASR) it consists of 8 hours of speech paired with text, recorded by using short text snippets in a laboratory environment.
Outcome:	The MASRI-HEADSET corpus was developed by the MASR project at the University of Malta.

Copied to clipboard

Solee Im, Wonjun Lee, JinMyeong An, Yunsu Kim, Jungseul Ok, Gary Lee

Corpus Generation for Voice Command in Smart Home and the Effect of Speech Synthesis on End-to-End SLU (2020.lrec-1)

Challenge:	Recent studies have demonstrated that postprocessing speech recognition transcriptions with large language models can significantly enhance the accuracy of Automatic Speech Recognition (ASR).
Approach:	They propose a method to improve Named Entity (NE) correction in Automatic Speech Recognition systems by leveraging phonetic similarity and augmented definitions.
Outcome:	The proposed method outperforms baseline methods on common voice and STOP datasets and achieves a 28% reduction in WER and NE hit ratio.

Copied to clipboard

Thierry Desot, François Portet, Michel Vacher

Using Automatic Speech Recognition in Spoken Corpus Curation (2020.lrec-1)

Challenge:	Massive amounts of annotated data are often unavailable for novel tasks performed in real-world environments such as smart homes.
Approach:	They propose to use a synthetic semantically-annotated corpus of French commands for smart-home to train pipeline and end-to-end (E2E) SLU models.
Outcome:	The proposed model trains pipeline and end-to-end (E2E) SLU models on voice commands acquired in a real smart home.

Copied to clipboard

Jan Gorisch, Michael Gref, Thomas Schmidt

Automatic Speech Recognition for Uyghur through Multilingual Acoustic Modeling (2020.lrec-1)

Challenge:	Automatic Speech Recognition (ASR) is a new way to make audio-visual data accessible.
Approach:	They propose to use automatic speech recognition (ASR) to make audio-visual data accessible by systematic queries.
Outcome:	The proposed system has higher recognition scores for the north of Germany vs. lower scores for south of the country.

Copied to clipboard

Ayimunishagu Abulimiti, Tanja Schultz

CEASR: A Corpus for Evaluating Automatic Speech Recognition (2020.lrec-1)

Challenge:	Low-resource languages suffer from lower performance of Automatic Speech Recognition (ASR) due to the lack of data.
Approach:	They propose to use Turkish as donor language to train acoustic models using multilingual training to achieve more context coverage.
Outcome:	The proposed system performs better with multilingual training for the under-resourced Uyghur language.

Copied to clipboard

Malgorzata Anna Ulasik, Manuela Hürlimann, Fabian Germann, Esin Gedik, Fernando Benites, Mark Cieliebak

MaSS: A Large and Clean Multilingual Corpus of Sentence-aligned Spoken Utterances Extracted from the Bible (2020.lrec-1)

Challenge:	Automatic Speech Recognition (ASR) systems are increasingly needed for research and practical applications.
Approach:	They propose to use public speech corpora to evaluate the quality of automatic speech recognition (ASR) they calculate an average Word Error Rate (WER) per corpus, per system and per corpor-system pair .
Outcome:	The proposed corpus evaluates the quality of automatic speech recognition systems using public speech corpora and transcripts generated by state-of-the-art systems.

Copied to clipboard

Marcely Zanon Boito, William Havard, Mahault Garnerin, Éric Le Ferrand, Laurent Besacier

ÌròyìnSpeech: A Multi-purpose Yorùbá Speech Corpus (2024.lrec-main)

Challenge:	The Bible is the same for all the languages, thus constituting a multilingual and comparable 2 spoken corpus, is not exploited to date.
Approach:	They propose to add multilingual links between small speech segments in different languages . they use a large dataset of 8,130 parallel spoken utterances across 8 languages - maSS .
Outcome:	The proposed model can build automatic speech recognition models for 700 languages.

Copied to clipboard

Tolulope Ogunremi, Kola Tubosun, Anuoluwapo Aremu, Iroro Orife, David Ifeoluwa Adelani

On Construction of the ASR-oriented Indian English Pronunciation Dictionary (2020.lrec-1)

Challenge:	rynSpeech corpus is a dataset that can be used for both Text-to-Speecher (TTS) and Automatic Speech Recognition (ASR) speakers of many African languages have no access to voice-enabled applications in their native languages.
Approach:	They propose a dataset to collect Yorùbá speech data that can be used for both TTS and ASR tasks.
Outcome:	The proposed dataset can generate a good quality model with as little as 5 hours of speech . the results are consistent with previous studies on the Yorùbá language .

Copied to clipboard

Xian Huang, Xin Jin, Qike Li, Keliang Zhang

PRoDeliberation: Parallel Robust Deliberation for End-to-End Spoken Language Understanding (2024.findings-emnlp)

Challenge:	Indian English (IE) has distinctive characteristics, especially phonologically, from other varieties of English.
Approach:	They build a small IE spontaneous speech corpus and use a linguistically-guided IE pronunciation dictionary to apply it to IE.
Outcome:	The proposed system performs better on IE spontaneous speech data than the one trained with CMUdict.

Copied to clipboard

Trang Le, Daniel Lazar, Suyoun Kim, Shan Jiang, Duc Le, Adithya Sagar, Aleksandr Livshits, Ahmed Aly, Akshat Shrivastava

Visual-Aware Speech Recognition for Noisy Scenarios (2025.emnlp-main)

Challenge:	End-to-end models for Spoken Language Understanding have been autoregressive, resulting in higher latencies.
Approach:	They propose a method that uses Connectionist Temporal Classification to train robust non-autoregressive deliberation models.
Outcome:	The proposed method achieves 10x latency reduction over autoregressive models while preserving ability to correct ASR mistranscriptions.

Copied to clipboard

Balaji Darur, Karan Singla

DISCO: A Large Scale Human Annotated Corpus for Disfluency Correction in Indo-European Languages (2023.findings-emnlp)

Challenge:	Existing audio-only models that use visual cues for transcription struggle in noisy environments.
Approach:	They propose a method that correlates visual cues with noise sources to improve transcription by filtering speech from noise and predicting noise labels in video inputs.
Outcome:	The proposed model improves transcription by correlating noise sources to visual cues in audio inputs.

Copied to clipboard

Vineet Bhat, Preethi Jyothi, Pushpak Bhattacharyya

LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriors (2025.findings-emnlp)

Challenge:	Existing research on disfluency correction has primarily focused on English due to the unavailability of large-scale open-source datasets.
Approach:	They propose to use an annotated human-annotated corpus to analyze disfluency correction in four important Indo-European languages to demonstrate the benefits.
Outcome:	The proposed model improves BLEU scores by 5.65 points when used with a state-of-the-art machine translation system.

Copied to clipboard

Rao Ma, Tongzhou Chen, Kartik Audhkhasi, Bhuvana Ramabhadran

ATIR: Towards Audio-Text Interleaved Contextual Retrieval (2026.acl-long)

Challenge:	Recent studies show that pre-trained speech encoders and large language models can perform suboptimal performance on a range of spoken language processing tasks.
Approach:	They propose to combine large-scale pre-trained speech encoders and large-language models for better performance on automatic speech recognition tasks.
Outcome:	The proposed model can get an average of 49% WER reduction over the baseline model on 8 MLS testsets.

Copied to clipboard

Tong Zhao, Chenghao Zhang, Yutao Zhu, Zhicheng Dou

Fairness in Automatic Speech Recognition Isn’t a One-Size-Fits-All (2025.findings-emnlp)

Challenge:	Recent multimodal information retrieval research has focused on images, largely overlooking audio.
Approach:	They propose an audio-text interleaved contextual retrieval task where queries can alternate between audio and text modalities.
Outcome:	The proposed model significantly improves over baselines.

Copied to clipboard

Hend ElGhazaly, Bahman Mirheidari, Heidi Christensen, Nafise Sadat Moosavi

SamróMur MilljóN: An ASR Corpus of One Million Verified Read Prompts in Icelandic (2024.lrec-main)

Challenge:	Pre-trained speech models like Whisper exhibit inconsistent group-level performance that varies across domains.
Approach:	They fine-tune a Whisper model on the Fair-Speech corpus using basic fine- tuning, demographic rebalancing, gender-swapped data augmentation and a novel contrastive learning objective.
Outcome:	The proposed method achieves stable, cross-domain fairness improvements without changes to the training data distribution and with minimal accuracy trade-offs.

Copied to clipboard

Carlos Daniel Hernandez Mena, Þorsteinn Daði Gunnarsson, Jon Gudnason

Difference in Task Performance on Sparse Speech Representations (2026.acl-long)

Challenge:	samrómur is a crowdsourcing web application designed to collect speech data for the advancement of language technologies in Icelandic.
Approach:	They propose to use a crowdsourcing web application to collect and verify Icelandic speech data for automatic speech recognition (ASR) they introduce a dataset comprising one million audio clips from the application .
Outcome:	The proposed system can produce high-quality speech data for Icelandic . the proposed system is based on a crowdsourced web application built on Mozilla's Common Voice .

Copied to clipboard

Wenjie Peng, Chen Chen, Thomas Hain

Sonos Voice Control Bias Assessment Dataset: A Methodology for Demographic Bias Assessment in Voice Assistants (2024.lrec-main)

Challenge:	Existing methods for learning speech representations that are useful for a variety of downstream tasks have been extensively investigated in different domains.
Approach:	They propose to train Autoencoders with varying sparsity levels using three SSL features and evaluate them on six tasks of SUPERB: speech enhancement, speaker identification, speech Emotion Recognition, phone recognition, automatic speech recognition and slot filling.
Outcome:	The proposed model can be used to learn speech representations that are useful for a variety of downstream tasks.

Copied to clipboard

Chloe Sekkat, Fanny Leroy, Salima Mdhaffar, Blake Perry Smith, Yannick Estève, Joseph Dureau, Alice Coucke

Speech Recognition Corpus of the Khinalug Language for Documenting Endangered Languages (2024.lrec-main)

Challenge:	Recent studies show voice assistants do not perform equally well for everyone . however, research on demographic robustness of speech technologies is still scarce .
Approach:	They propose a statistical method to detect demographic bias using a large dataset with controlled demographic tags.
Outcome:	The proposed method shows statistically significant differences in performance across age, dialectal region and ethnicity.

Copied to clipboard

Zhaolin Li, Monika Rind-Pawlowski, Jan Niehues

The Influence of Automatic Speech Recognition on Linguistic Features and Automatic Alzheimer’s Disease Detection from Spontaneous Speech (2024.lrec-main)

Challenge:	Existing tools to document endangered languages are limited due to data scarcity and the need for training.
Approach:	They propose to use a speech corpus for Khinalug, an endangered language spoken in northern Azerbaijan, to create a model that can be used in language documentation scenarios.
Outcome:	The proposed model achieves 6.65 CER points and 25.53 WER points in low-resource scenarios.

Copied to clipboard

Jonathan Heitz, Gerold Schneider, Nicolas Langer

Unraveling Spontaneous Speech Dimensions for Cross-Corpus ASR System Evaluation for French (2024.lrec-main)

Challenge:	Existing biomarkers for AD diagnosis can only be applied to relatively small sample sizes due to limited availability, excessive costs and invasive nature.
Approach:	They compare automatic speech recognition systems in terms of Word Error Rate (WER) using a publicly available benchmark dataset of speech recordings of AD patients and controls.
Outcome:	The proposed method improves classification performance by replacing manual transcriptions with ASR output.

Copied to clipboard

Solene Virginie Evain, Solange Rossato, François Portet

MCGA: A Multi-task Classical Chinese Literary Genre Audio Corpus (2026.findings-acl)

Challenge:	'spontaneous speech' is a catch-all term used for situations like speaking with a friend, being interviewed on radio/TV or giving a lecture.
Approach:	They propose to use four dimensions to describe spontaneous speech variation in automatic speech recognition systems.
Outcome:	The proposed system can be used to predict the WER of speech recognition systems on face-to-face interactions.

Copied to clipboard

Yexing Du, Kaiyuan Liu, Bihe Zhang, Youcheng Pan, Bo Yang, Liangyu Huo, Xiyuan Zhang, Jian Xie, Daojing He, Yang Xiang, Ming Liu, Bing Qin

Mind the Pause: Disfluency-Aware Objective Tuning for Multilingual Speech Correction with LLMs (2026.acl-long)

Challenge:	Multimodal Large Language Models (MLLMs) have advanced Chinese Classical Studies (CCS) but the audio dimension of CCS remains underexplored due to a lack of high-quality, domain-specific audio corpora.
Approach:	They propose a 119-hour audio corpus comprising 22,000 audio samples to bridge this gap . it encompasses a diverse range of literary genres across six tasks .
Outcome:	The proposed corpus encompasses a diverse range of literary genres across six tasks: Automatic Speech Recognition (ASR), Speech-to-Text Translation (S2TT), Speech Emotion Captioning (SEC), Spoken Question Answering ( SQA), Speech Understanding (SU), and Speech Reasoning (SR).

Copied to clipboard

Deepak Kumar, Baban Gain, Asif Ekbal