Papers with transcription

16 papers
Cross-Lingual Transfer Learning for Speech Translation (2025.naacl-short)

Copied to clipboard

Challenge: Increasing interest in building multilingual foundation models for NLP and speech research has led to limited data collection for training ST systems.
Approach: They propose to use Whisper to explore the behavior of multilingual speech foundation models with restricted data.
Outcome: The proposed model can translate to Chinese with a single language, and it can perform transcriptions in other languages.
A Corpus of Spontaneous L2 English Speech for Real-situation Speaking Assessment (2024.lrec-main)

Copied to clipboard

Challenge: Existing automated scoring systems rely on highly controlled elicitation protocols, such as reading aloud isolated words or short sentences, limiting their ability to evaluate spontaneous speech.
Approach: They propose to collect a corpus of spontaneous L2 English speech from university students as part of a French national certificate in English.
Outcome: The results show that only 35.4% of the 6,350 targeted words had stress detected on the expected syllable, revealing a common stress shift to the final s.
Learning From Failure: Data Capture in an Australian Aboriginal Community (2022.acl-long)

Copied to clipboard

Challenge: a prototype of a language data capture app for speakers was tested in an Aboriginal community . elicitation of word lists, phrases, etc. has been used for decades to collect data for Indigenous languages . many software tools are developed to support linguists' work .
Approach: They propose to deploy an app for speakers to confirm system guesses in an approach to transcription based on word spotting.
Outcome: The proposed app was tested in an Aboriginal community in australia . it was able to confirm system guesses without a transcription bottleneck . the results were compared with other apps in the community .
Afrispeech Semantics: Evaluating Audio–Semantic Reasoning in Spoken Language Models Across Domains and Accents (2026.findings-acl)

Copied to clipboard

Challenge: Recent multimodal models are trained on large collections of audio-text pairs using contrastive learning or nexttoken prediction objectives.
Approach: They evaluate audio language models across five semantic and paralinguistic reasoning tasks: entailment, consistency, plausibility, accent drift, and accent restraint.
Outcome: The evaluations assess models across five tasks including entailment, consistency, plausibility, accent drift, and accent restraint.
ArzEn: A Speech Corpus for Code-switched Egyptian Arabic-English (2020.lrec-1)

Copied to clipboard

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.
Analyzing the Quality of Counseling Conversations: the Tell-Tale Signs of High-quality Counseling (L18-1)

Copied to clipboard

Challenge: Behavioral and mental health disorders are the most costly and prevalent conditions worldwide.
Approach: They propose to use a dataset to analyze counseling interactions by using aspects such as mirroring, empathy, and reflective listening to build text-based classifiers.
Outcome: The proposed dataset can be used to build text-based classifiers able to predict the overall quality of a counseling conversation and provide insights into the linguistic differences between low-quality and high-quality counseling.
Phonotomizer: A Compact, Unsupervised, Online Training Approach to Real-Time, Multilingual Phonetic Segmentation (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to phonetic segmentation are hierarchical and end-to-end . many mistakes in final output stem from subtle segmenter perturbations .
Approach: They propose a phonetic segmentation system that trains on raw sound files alone . it can modulate computational exactness and reduce acoustic model size, they argue .
Outcome: The proposed method reduces the size of the acoustic model and training epochs.
Manually Annotated Corpus of Polish Texts Published between 1830 and 1918 (L18-1)

Copied to clipboard

Challenge: a paper presents a manually annotated corpus of 625,000 tokens of Polish texts . the corpus provides three layers: transliteration, transcription and morphosyntactic annotation.
Approach: The paper presents a manually annotated large historical corpus of Polish . the corpus provides three layers: transliteration, transcription and morphosyntactic annotation.
Outcome: The corpus provides three layers: transliteration, transcription and morphosyntactic annotation.
VAST: A Corpus of Video Annotation for Speech Technologies (L18-1)

Copied to clipboard

Challenge: The video annotation for speech technologies corpus contains 2900 hours of video data . the data are intended to support speech technology development .
Approach: The Video Annotation for Speech Technologies corpus contains 2900 hours of video data . the data are intended to support speech technology development .
Outcome: The video annotation for speech technologies corpus contains 2900 hours of video data . the data are intended to support speech detection, language identification, speaker identification, and speech recognition .
Augmented Prompt Selection for Evaluation of Spontaneous Speech Synthesis (2020.lrec-1)

Copied to clipboard

Challenge: Spontaneous speech is unscripted and created on the fly by the speaker, whereas read speech is pre-planned.
Approach: They propose a tool that allows developers to select a varied, representative set of utterances from a spoken genre to be used for evaluation of TTS for a given domain.
Outcome: The proposed tool can be used to evaluate TTS for a given domain using visualisation and tree-based algorithm.
Development and Evaluation of Speech Synthesis Corpora for Latvian (2020.lrec-1)

Copied to clipboard

Challenge: Recent advances in neural speech synthesis have enabled the development of text to speech systems for all languages.
Approach: They propose to obtain a suitable corpus from unannotated Latvian audio recordings using automated speech recognition and speaker segmentation and identification.
Outcome: The proposed method and software tools are applied and evaluated on a Latvian public radio archive data.
Visual-Aware Speech Recognition for Noisy Scenarios (2025.emnlp-main)

Copied to clipboard

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.
Linguistically Motivated Sign Language Segmentation (2023.findings-emnlp)

Copied to clipboard

Challenge: Sign language segmentation is a crucial task in sign language processing systems.
Approach: They propose to combine two kinds of segmentation: segmentation into individual signs and segmentation to segment into phrases, larger units comprising several signs.
Outcome: The proposed model is based on linguistic cues observed in sign language corpora and replaces the predominant IO tagging scheme with BIO taging to account for continuous signing.
Linguistic Survey of India and Polyglotta Africana: Two Retrostandardized Digital Editions of Large Historical Collections of Multilingual Wordlists (2024.lrec-main)

Copied to clipboard

Challenge: Linguistic Survey of India and Polyglotta Africana are two of the largest historical collections of multilingual wordlists.
Approach: They present a retro-standardized edition of the Linguistic Survey of India and the Polyglotta Africana, which are two of the largest historical collections of multilingual wordlists.
Outcome: The LSI and PA are the largest historical collections of multilingual wordlists . but no editions in which the original data is presented in standardized form have been produced so far .
TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer-based ASR (2024.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to automatic speech recognition use cascaded pipelines for tasks like voice activity detection, diarization, transcription and subsequent processing.
Approach: They propose a single Transducer-based model that integrates task-specific tokens into the reference text during ASR model training, streamlining inference and eliminating the need for separate NLP models.
Outcome: The proposed model outperforms the existing pipeline on speaker change detection, endpointing, and NER tasks while outperforming the existing model in individual task performance.
Casablanca: Data and Models for Multidialectal Arabic Speech Recognition (2024.emnlp-main)

Copied to clipboard

Challenge: despite recent advances in speech processing, the majority of world languages and dialects remain uncovered.
Approach: They propose to collect and transcribe a new Arabic dataset for eight dialects . they also develop strong baselines exploiting the new dataset .
Outcome: The proposed dataset covers eight Arabic dialects, including Algerian, Egyptian, Emirati, Jordanian, Mauritanian, Moroccan, Palestinian, and Yemeni.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations