arXiv subjects

Hung-yi Lee

Publications and source records attributed to Hung-yi Lee.

At least 145 records · Page 8Linked to original sources

arXiv2025

SUTA-LM: Bridging Test-Time Adaptation and Language Model Rescoring for Robust ASR

Despite progress in end-to-end ASR, real-world domain mismatches still cause performance drops, which Test-Time Adaptation (TTA) aims to mitigate by adjusting models during inference. Recent work explores combining TTA with external language models, using techniques like beam search rescoring or generative error correction. In this work, we identify a previously overlooked challenge: TTA can interfere with language model rescoring, revealing the nontrivial nature of effectively combining the two methods. Based on this insight, we propose SUTA-LM, a simple yet effective extension of SUTA, an entropy-minimization-based TTA approach, with language model rescoring. SUTA-LM first applies a controlled adaptation process guided by an auto-step selection mechanism leveraging both acoustic and linguistic information, followed by language model rescoring to refine the outputs. Experiments on 18 diverse ASR datasets show that SUTA-LM achieves robust results across a wide range of domains.

cs.CL↗

arXiv2025

Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks

Multimodal foundation models, such as Gemini and ChatGPT, have revolutionized human-machine interactions by seamlessly integrating various forms of data. Developing a universal spoken language model that comprehends a wide range of natural language instructions is critical for bridging communication gaps and facilitating more intuitive interactions. However, the absence of a comprehensive evaluation benchmark poses a significant challenge. We present Dynamic-SUPERB Phase-2, an open and evolving benchmark for the comprehensive evaluation of instruction-based universal speech models. Building upon the first generation, this second version incorporates 125 new tasks contributed collaboratively by the global research community, expanding the benchmark to a total of 180 tasks, making it the largest benchmark for speech and audio evaluation. While the first generation of Dynamic-SUPERB was limited to classification tasks, Dynamic-SUPERB Phase-2 broadens its evaluation capabilities by introducing a wide array of novel and diverse tasks, including regression and sequence generation, across speech, music, and environmental audio. Evaluation results show that no model performed well universally. SALMONN-13B excelled in English ASR and Qwen2-Audio-7B-Instruct showed high accuracy in emotion recognition, but current models still require further innovations to handle a broader range of tasks. We open-source all task data and the evaluation pipeline at https://github.com/dynamic-superb/dynamic-superb.

cs.CL↗

arXiv2025

TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-Judge

The LLM-as-a-judge paradigm uses large language models (LLMs) for automated text evaluation, where a numerical assessment is assigned by an LLM to the input text following scoring rubrics. Existing methods for LLM-as-a-judge use cross-entropy (CE) loss for fine-tuning, which neglects the numeric nature of score prediction. Recent work addresses numerical prediction limitations of LLM fine-tuning through regression-aware fine-tuning, which, however, does not consider chain-of-thought (CoT) reasoning for score prediction. In this paper, we introduce TRACT (Two-stage Regression-Aware fine-tuning with CoT), a method combining CoT reasoning with regression-aware training. TRACT consists of two stages: first, seed LLM is fine-tuned to generate CoTs, which serve as supervision for the second stage fine-tuning. The training objective of TRACT combines the CE loss for learning the CoT reasoning capabilities, and the regression-aware loss for the score prediction. Experiments across four LLM-as-a-judge datasets and two LLMs show that TRACT significantly outperforms existing methods. Extensive ablation studies validate the importance of each component in TRACT.

cs.CL↗

arXiv2025

Audio-Aware Large Language Models as Judges for Speaking Styles

Audio-aware large language models (ALLMs) can understand the textual and non-textual information in the audio input. In this paper, we explore using ALLMs as an automatic judge to assess the speaking styles of speeches. We use ALLM judges to evaluate the speeches generated by SLMs on two tasks: voice style instruction following and role-playing. The speaking style we consider includes emotion, volume, speaking pace, word emphasis, pitch control, and non-verbal elements. We use four spoken language models (SLMs) to complete the two tasks and use humans and ALLMs to judge the SLMs' responses. We compare two ALLM judges, GPT-4o-audio and Gemini-2.5-pro, with human evaluation results and show that the agreement between Gemini and human judges is comparable to the agreement between human evaluators. These promising results show that ALLMs can be used as a judge to evaluate SLMs. Our results also reveal that current SLMs, even GPT-4o-audio, still have room for improvement in controlling the speaking style and generating natural dialogues.

eess.AS↗

arXiv2025

EMO-Debias: Benchmarking Gender Debiasing Techniques in Multi-Label Speech Emotion Recognition

Speech emotion recognition (SER) systems often exhibit gender bias. However, the effectiveness and robustness of existing debiasing methods in such multi-label scenarios remain underexplored. To address this gap, we present EMO-Debias, a large-scale comparison of 13 debiasing methods applied to multi-label SER. Our study encompasses techniques from pre-processing, regularization, adversarial learning, biased learners, and distributionally robust optimization. Experiments conducted on acted and naturalistic emotion datasets, using WavLM and XLSR representations, evaluate each method under conditions of gender imbalance. Our analysis quantifies the trade-offs between fairness and accuracy, identifying which approaches consistently reduce gender performance gaps without compromising overall model performance. The findings provide actionable insights for selecting effective debiasing strategies and highlight the impact of dataset distributions.

eess.AS↗

arXiv2025

IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling

Text-to-audio generation synthesizes realistic sounds or music given a natural language prompt. Diffusion-based frameworks, including the Tango and the AudioLDM series, represent the state-of-the-art in text-to-audio generation. Despite achieving high audio fidelity, they incur significant inference latency due to the slow diffusion sampling process. MAGNET, a mask-based model operating on discrete tokens, addresses slow inference through iterative mask-based parallel decoding. However, its audio quality still lags behind that of diffusion-based models. In this work, we introduce IMPACT, a text-to-audio generation framework that achieves high performance in audio quality and fidelity while ensuring fast inference. IMPACT utilizes iterative mask-based parallel decoding in a continuous latent space powered by diffusion modeling. This approach eliminates the fidelity constraints of discrete tokens while maintaining competitive inference speed. Results on AudioCaps demonstrate that IMPACT achieves state-of-the-art performance on key metrics including Fréchet Distance (FD) and Fréchet Audio Distance (FAD) while significantly reducing latency compared to prior models. The project website is available at https://audio-impact.github.io/.

eess.AS↗

arXiv2025

Mitigating Subgroup Disparities in Multi-Label Speech Emotion Recognition: A Pseudo-Labeling and Unsupervised Learning Approach

While subgroup disparities and performance bias are increasingly studied in computational research, fairness in categorical Speech Emotion Recognition (SER) remains underexplored. Existing methods often rely on explicit demographic labels, which are difficult to obtain due to privacy concerns. To address this limitation, we introduce an Implicit Demography Inference (IDI) module that leverages pseudo-labeling from a pre-trained model and unsupervised learning using k-means clustering to mitigate bias in SER. Our experiments show that pseudo-labeling IDI reduces subgroup disparities, improving fairness metrics by over 28% with less than a 2% decrease in SER accuracy. Also, the unsupervised IDI yields more than a 4.6% improvement in fairness metrics with a drop of less than 3.6% in SER performance. Further analyses reveal that the unsupervised IDI consistently mitigates race and age disparities, demonstrating its potential when explicit demographic information is unavailable.

eess.AS↗

arXiv2025

Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback

While textless Spoken Language Models (SLMs) have shown potential in end-to-end speech-to-speech modeling, they still lag behind text-based Large Language Models (LLMs) in terms of semantic coherence and relevance. This work introduces the Align-SLM framework, which leverages preference optimization inspired by Reinforcement Learning with AI Feedback (RLAIF) to enhance the semantic understanding of SLMs. Our approach generates multiple speech continuations from a given prompt and uses semantic metrics to create preference data for Direct Preference Optimization (DPO). We evaluate the framework using ZeroSpeech 2021 benchmarks for lexical and syntactic modeling, the spoken version of the StoryCloze dataset for semantic coherence, and other speech generation metrics, including the GPT4-o score and human evaluation. Experimental results show that our method achieves state-of-the-art performance for SLMs on most benchmarks, highlighting the importance of preference optimization to improve the semantics of SLMs.

cs.CL↗

arXiv2025

Creativity in LLM-based Multi-Agent Systems: A Survey

Large language model (LLM)-driven multi-agent systems (MAS) are transforming how humans and AIs collaboratively generate ideas and artifacts. While existing surveys provide comprehensive overviews of MAS infrastructures, they largely overlook the dimension of \emph{creativity}, including how novel outputs are generated and evaluated, how creativity informs agent personas, and how creative workflows are coordinated. This is the first survey dedicated to creativity in MAS. We focus on text and image generation tasks, and present: (1) a taxonomy of agent proactivity and persona design; (2) an overview of generation techniques, including divergent exploration, iterative refinement, and collaborative synthesis, as well as relevant datasets and evaluation metrics; and (3) a discussion of key challenges, such as inconsistent evaluation standards, insufficient bias mitigation, coordination conflicts, and the lack of unified benchmarks. This survey offers a structured framework and roadmap for advancing the development, evaluation, and standardization of creative MAS.

cs.HC↗

arXiv2025

Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models

We introduce Speech-IFeval, an evaluation framework designed to assess instruction-following capabilities and quantify catastrophic forgetting in speech-aware language models (SLMs). Recent SLMs integrate speech perception with large language models (LLMs), often degrading textual capabilities due to speech-centric training. Existing benchmarks conflate speech perception with instruction-following, hindering evaluation of these distinct skills. To address this gap, we provide a benchmark for diagnosing the instruction-following abilities of SLMs. Our findings show that most SLMs struggle with even basic instructions, performing far worse than text-based LLMs. Additionally, these models are highly sensitive to prompt variations, often yielding inconsistent and unreliable outputs. We highlight core challenges and provide insights to guide future research, emphasizing the need for evaluation beyond task-level metrics.

eess.AS↗

arXiv2025

Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models?

Large reasoning models (LRMs) have demonstrated impressive performance across a range of reasoning tasks, yet little is known about their internal reasoning processes in multilingual settings. We begin with a critical question: {\it In which language do these models reason when solving problems presented in different languages?} Our findings reveal that, despite multilingual training, LRMs tend to default to reasoning in high-resource languages (e.g., English) at test time, regardless of the input language. When constrained to reason in the same language as the input, model performance declines, especially for low-resource languages. In contrast, reasoning in high-resource languages generally preserves performance. We conduct extensive evaluations across reasoning-intensive tasks (MMMLU, MATH-500) and non-reasoning benchmarks (CulturalBench, LMSYS-toxic), showing that the effect of language choice varies by task type: input-language reasoning degrades performance on reasoning tasks but benefits cultural tasks, while safety evaluations exhibit language-specific behavior. By exposing these linguistic biases in LRMs, our work highlights a critical step toward developing more equitable models that serve users across diverse linguistic backgrounds.

cs.CL↗

arXiv2025

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models

End-to-end training of Spoken Language Models (SLMs) commonly involves adapting pre-trained text-based Large Language Models (LLMs) to the speech modality through multi-stage training on diverse tasks such as ASR, TTS and spoken question answering (SQA). Although this multi-stage continual learning equips LLMs with both speech understanding and generation capabilities, the substantial differences in task and data distributions across stages can lead to catastrophic forgetting, where previously acquired knowledge is lost. This paper investigates catastrophic forgetting and evaluates three mitigation strategies-model merging, discounting the LoRA scaling factor, and experience replay to balance knowledge retention with new learning. Results show that experience replay is the most effective, with further gains achieved by combining it with other methods. These findings provide insights for developing more robust and efficient SLM training pipelines.

cs.CL↗

arXiv2025

Transferring Textual Preferences to Vision-Language Understanding through Model Merging

Large vision-language models (LVLMs) perform outstandingly across various multimodal tasks. However, their ability to evaluate generated content remains limited, and training vision-language reward models (VLRMs) with preference data is computationally expensive. This paper explores a training-free alternative by merging text-based reward models (RMs) with LVLMs to create VLRMs. Our approach shows that integrating these models leads to improved performance over LVLMs' scoring and text-based RMs, offering an efficient method for incorporating textual preferences into LVLMs.

cs.CL↗

arXiv2025

Meta-PerSER: Few-Shot Listener Personalized Speech Emotion Recognition via Meta-learning

This paper introduces Meta-PerSER, a novel meta-learning framework that personalizes Speech Emotion Recognition (SER) by adapting to each listener's unique way of interpreting emotion. Conventional SER systems rely on aggregated annotations, which often overlook individual subtleties and lead to inconsistent predictions. In contrast, Meta-PerSER leverages a Model-Agnostic Meta-Learning (MAML) approach enhanced with Combined-Set Meta-Training, Derivative Annealing, and per-layer per-step learning rates, enabling rapid adaptation with only a few labeled examples. By integrating robust representations from pre-trained self-supervised models, our framework first captures general emotional cues and then fine-tunes itself to personal annotation styles. Experiments on the IEMOCAP corpus demonstrate that Meta-PerSER significantly outperforms baseline methods in both seen and unseen data scenarios, highlighting its promise for personalized emotion recognition.

eess.AS↗

arXiv2025

ToxicTone: A Mandarin Audio Dataset Annotated for Toxicity and Toxic Utterance Tonality

Despite extensive research on toxic speech detection in text, a critical gap remains in handling spoken Mandarin audio. The lack of annotated datasets that capture the unique prosodic cues and culturally specific expressions in Mandarin leaves spoken toxicity underexplored. To address this, we introduce ToxicTone -- the largest public dataset of its kind -- featuring detailed annotations that distinguish both forms of toxicity (e.g., profanity, bullying) and sources of toxicity (e.g., anger, sarcasm, dismissiveness). Our data, sourced from diverse real-world audio and organized into 13 topical categories, mirrors authentic communication scenarios. We also propose a multimodal detection framework that integrates acoustic, linguistic, and emotional features using state-of-the-art speech and emotion encoders. Extensive experiments show our approach outperforms text-only and baseline models, underscoring the essential role of speech-specific cues in revealing hidden toxic expressions.

eess.AS↗

arXiv2025

Distilling a speech and music encoder with task arithmetic

Despite the progress in self-supervised learning (SSL) for speech and music, existing models treat these domains separately, limiting their capacity for unified audio understanding. A unified model is desirable for applications that require general representations, e.g. audio large language models. Nonetheless, directly training a general model for speech and music is computationally expensive. Knowledge Distillation of teacher ensembles may be a natural solution, but we posit that decoupling the distillation of the speech and music SSL models allows for more flexibility. Thus, we propose to learn distilled task vectors and then linearly interpolate them to form a unified speech+music model. This strategy enables flexible domain emphasis through adjustable weights and is also simpler to train. Experiments on speech and music benchmarks demonstrate that our method yields superior overall performance compared to ensemble distillation.

cs.SD↗

arXiv2025

ML-SUPERB: Multilingual Speech Universal PERformance Benchmark

Speech processing Universal PERformance Benchmark (SUPERB) is a leaderboard to benchmark the performance of Self-Supervised Learning (SSL) models on various speech processing tasks. However, SUPERB largely considers English speech in its evaluation. This paper presents multilingual SUPERB (ML-SUPERB), covering 143 languages (ranging from high-resource to endangered), and considering both automatic speech recognition and language identification. Following the concept of SUPERB, ML-SUPERB utilizes frozen SSL features and employs a simple framework for multilingual tasks by learning a shallow downstream model. Similar to the SUPERB benchmark, we find speech SSL models can significantly improve performance compared to FBANK features. Furthermore, we find that multilingual models do not always perform better than their monolingual counterparts. We will release ML-SUPERB as a challenge with organized datasets and reproducible training scripts for future multilingual representation research.

cs.SD↗

arXiv2025

Findings of the 2023 ML-SUPERB Challenge: Pre-Training and Evaluation over More Languages and Beyond

The 2023 Multilingual Speech Universal Performance Benchmark (ML-SUPERB) Challenge expands upon the acclaimed SUPERB framework, emphasizing self-supervised models in multilingual speech recognition and language identification. The challenge comprises a research track focused on applying ML-SUPERB to specific multilingual subjects, a Challenge Track for model submissions, and a New Language Track where language resource researchers can contribute and evaluate their low-resource language data in the context of the latest progress in multilingual speech recognition. The challenge garnered 12 model submissions and 54 language corpora, resulting in a comprehensive benchmark encompassing 154 languages. The findings indicate that merely scaling models is not the definitive solution for multilingual speech tasks, and a variety of speech/voice types present significant challenges in multilingual speech processing.

cs.SD↗