Unlocking Large Audio-Language Models for Interactive Language Learning (2026.findings-eacl)
Copied to clipboard
| Challenge: | Computer-Assisted Pronunciation Training (CAPT) systems provide unintuitive feedback that lacks actionable guidance. |
| Approach: | They propose to use audio-language models to provide more user-friendly feedback for pronunciation training. |
| Outcome: | The proposed model outperforms baselines on mispronunciation detection and suggestion generation. |
Similar Papers
Read to Hear: A Zero-Shot Pronunciation Assessment Using Textual Descriptions and LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Automatic pronunciation assessment is typically performed by acoustic models trained on audio-score pairs. |
| Approach: | They propose a zero-shot, textual description-based Pronunciation Assessment approach that utilizes human-readable representations of speech signals fed into an LLM to assess pronunciation accuracy and fluency. |
| Outcome: | The proposed approach is cost-efficient and competitive in performance . it significantly improves the performance of conventional audio-score-trained models on out-of-domain data . |
Toward Beginner-Friendly LLMs for Language Learning: Controlling Difficulty in Conversation (2026.findings-eacl)
Copied to clipboard
| Challenge: | Practicing conversations with large language models is a promising alternative to traditional in-person language learning. |
| Approach: | They propose a new token-level evaluation metric, Token Miss Rate, that measures the proportion of incomprehensible tokens per utterance and correlates strongly with human judgments. |
| Outcome: | The proposed methods improve comprehensibility for beginner speakers from 39.4% to 83.3%, compared with prompting alone and a token-level evaluation metric, Token Miss Rate (TMR). |
Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca (2024.findings-eacl)
Copied to clipboard
| Challenge: | Foundational large language models (LLMs) can be instruction-tuned to perform open-domain question answering, facilitating applications like chat assistants. |
| Approach: | They employ a dataset and machine translations of it to form multilingual data and use it to tune LLMs. |
| Outcome: | The proposed model is on par or better than a model for each language, and multilingual tuning with downsampled data is as powerful and robust. |
Spoken Conversational Agents with Large Language Models (2025.emnlp-tutorials)
Copied to clipboard
| Challenge: | This tutorial focuses on the evolution of voice-native LLMs . it reviews the adaptation of text LLM to audio, cross-modal alignment, and joint speech–text training . |
| Approach: | This tutorial examines the evolution of voice-native LLMs in conversational agents . it compares cascaded and voice-based LLM systems to end-to-end retrieval-and vision-grounded systems . |
| Outcome: | This tutorial examines the evolution of voice-native LLMs . it compares the performance of voice assistants to current open-domain agents . |
Speechworthy Instruction-tuned Language Models (2024.emnlp-main)
Copied to clipboard
Hyundong Cho, Nicolaas Jedema, Leonardo Ribeiro, Karishma Sharma, Pedro Szekely, Alessandro Moschitti, Ruben Janssen, Jonathan May
| Challenge: | Current instruction tuned language models are trained on textual preference data and therefore not aligned to speech domain. |
| Approach: | They propose to use radio-industry best practices to prompt and learn speech-based preference data to improve speech-suitability of popular instruction tuned language models. |
| Outcome: | The proposed methods achieve the best win rates in head-to-head comparisons, resulting in preferred or tied to the base model in 76.2% of comparisons on average. |
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. |
ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in natural language processing (NLP) have led to significant breakthroughs in the field. |
| Approach: | They evaluate ChatGPT over multiple tasks with diverse languages and large datasets to provide more comprehensive information for multilingual NLP applications. |
| Outcome: | The proposed model can process and generate texts for multiple languages due to its multilingual training data. |
Improving the Robustness of Large Language Models via Consistency Alignment (2024.lrec-main)
Copied to clipboard
Yukun Zhao, Lingyong Yan, Weiwei Sun, Guoliang Xing, Shuaiqiang Wang, Chong Meng, Zhicong Cheng, Zhaochun Ren, Dawei Yin
| Challenge: | Large language models have shown tremendous success in following user instructions and generating helpful responses, but their robustness is still far from optimal. |
| Approach: | They propose a two-stage training framework that helps a model generalize on following instructions via similar instruction augmentations. |
| Outcome: | The proposed training framework improves diversity and aligns the model with human expectations by differentiating subtle differences in similar responses. |
T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback (2025.acl-long)
Copied to clipboard
Zehan Wang, Ke Lei, Chen Zhu, Jiawei Huang, Sashuai Zhou, Luping Liu, Xize Cheng, Shengpeng Ji, Zhenhui Ye, Tao Jin, Zhou Zhao
| Challenge: | Text-to-audio (T2A) models still struggle to satisfy human preferences for prompt-following and acoustic quality when generating complex multi-event audio. |
| Approach: | They propose to use AI feedback learning to enhance basic capabilities of text-to-audio models . they use a large audio preference dataset to evaluate the model's capabilities . |
| Outcome: | The proposed model improves in simple and complex scenarios with AI feedback learning. |
Developing a Benchmark for Pronunciation Feedback: Creation of a Phonemically Annotated Speech Corpus of isiZulu Language Learner Speech (2024.lrec-main)
Copied to clipboard
Alexandra O’Neil, Nils Hjortnaes, Francis Tyers, Zinhle Nkosi, Thulile Ndlovu, Zanele Mlondo, Ngami Phumzile Pewa
| Challenge: | Existing corpora for computer-assisted pronunciation training (CAPT) do not apply well to research in pronunciation feedback. |
| Approach: | They propose to create a corpus of isiZulu language learner speech that has been annotated for phoneme errors and suprasegmental errors in tone. |
| Outcome: | The proposed corpus is comprised of gold standard recordings from isiZulu teachers and recordings from students that have been annotated for pronunciation errors. |