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

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

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

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

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.

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