arXiv subjects

Chi-Chun Lee

Publications and source records attributed to Chi-Chun Lee.

At least 19 recordsLinked to original sources

arXiv2026

Bridging the Age Gap: Towards Detecting Neural Audio Codec Synthesized Elderly Speech Deepfake

In this study, we introduce the Elderly CodecFake Detection (ECFD) task and release the Elderly-CodecFake (ECF) dataset in English and Chinese. We show that state-of-the-art CF detectors trained on previous benchmark CF datasets generalize poorly to elderly speech, revealing a critical vulnerability. We further hypothesize and demonstrate that multimodal foundation models (FMs) such as LanguageBind (LB) and ImageBind (IB) are more effective for ECFD due to their exposure to elderly content during cross-modal pretraining. Motivated by prior evidence that fusion of FMs enhances downstream performance, we explore fusion of FMs for ECFD. To this end, we propose BONSAI, a novel framework that employs Jensen-Shannon Divergence as the fusion mechanism. BONSAI with the fusion of LB and IB achieves an average EER (%) of 1.66 and outperforms individual FMs as well as competitive SOTA baselines, establishing a new benchmark for the ECFD task.

eess.AS↗

arXiv2026

AdaLTM: Adaptive Layer-wise Task Vector Merging for Categorical Speech Emotion Recognition with ASR Knowledge Integration

Integrating Automatic Speech Recognition (ASR) into Speech Emotion Recognition (SER) enhances modeling by providing linguistic context. However, conventional feature fusion faces performance bottlenecks, and multi-task learning often suffers from optimization conflicts. While task vectors and model merging have addressed such conflicts in NLP and CV, their potential in speech tasks remains largely unexplored. In this work, we propose an Adaptive Layer-wise Task Vector Merging (AdaLTM) framework based on WavLM-Large. Instead of joint optimization, we extract task vectors from in-domain ASR and SER models fine-tuned on emotion datasets. These vectors are integrated into a frozen base model using layer-wise learnable coefficients. This strategy enables depth-aware balancing of linguistic and paralinguistic knowledge across transformer layers without gradient interference. Experiments on the MSP-Podcast demonstrate that the proposed approach effectively mitigates conflicts between ASR and SER.

eess.AS↗

arXiv2026

RE-LLM: Refining Empathetic Speech-LLM Responses by Integrating Emotion Nuance

With generative AI advancing, empathy in human-AI interaction is essential. While prior work focuses on emotional reflection, emotional exploration, key to deeper engagement, remains overlooked. Existing LLMs rely on text which captures limited emotion nuances. To address this, we propose RE-LLM, a speech-LLM integrating dimensional emotion embeddings and auxiliary learning. Experiments show statistically significant gains in empathy metrics across three datasets. RE-LLM relatively improves the Emotional Reaction score by 14.79% and 6.76% compared to text-only and speech-LLM baselines on ESD. Notably, it raises the Exploration score by 35.42% and 3.91% on IEMOCAP, 139.28% and 9.83% on ESD, and 60.95% and 22.64% on MSP-PODCAST. It also boosts unweighted accuracy by 5.4% on IEMOCAP, 2.3% on ESD, and 6.9% on MSP-PODCAST in speech emotion recognition. These results highlight the enriched emotional understanding and improved empathetic response generation of RE-LLM.

eess.AS↗

arXiv2026

ASR for Affective Speech: Investigating Impact of Emotion and Speech Generative Strategy

This work investigates how emotional speech and generative strategies affect ASR performance. We analyze speech synthesized from three emotional TTS models and find that substitution errors dominate, with emotional expressiveness varying across models. Based on these insights, we introduce two generative strategies: one using transcription correctness and another using emotional salience, to construct fine-tuning subsets. Results show consistent WER improvements on real emotional datasets without noticeable degradation on clean LibriSpeech utterances. The combined strategy achieves the strongest gains, particularly for expressive speech. These findings highlight the importance of targeted augmentation for building emotion-aware ASR systems.

eess.AS↗

arXiv2025

Stimulus Modality Matters: Impact of Perceptual Evaluations from Different Modalities on Speech Emotion Recognition System Performance

Speech Emotion Recognition (SER) systems rely on speech input and emotional labels annotated by humans. However, various emotion databases collect perceptional evaluations in different ways. For instance, the IEMOCAP dataset uses video clips with sounds for annotators to provide their emotional perceptions. However, the most significant English emotion dataset, the MSP-PODCAST, only provides speech for raters to choose the emotional ratings. Nevertheless, using speech as input is the standard approach to training SER systems. Therefore, the open question is the emotional labels elicited by which scenarios are the most effective for training SER systems. We comprehensively compare the effectiveness of SER systems trained with labels elicited by different modality stimuli and evaluate the SER systems on various testing conditions. Also, we introduce an all-inclusive label that combines all labels elicited by various modalities. We show that using labels elicited by voice-only stimuli for training yields better performance on the test set, whereas labels elicited by voice-only stimuli.

eess.AS↗

arXiv2025

Revisiting Modeling and Evaluation Approaches in Speech Emotion Recognition: Considering Subjectivity of Annotators and Ambiguity of Emotions

Over the past two decades, speech emotion recognition (SER) has received growing attention. To train SER systems, researchers collect emotional speech databases annotated by crowdsourced or in-house raters who select emotions from predefined categories. However, disagreements among raters are common. Conventional methods treat these disagreements as noise, aggregating labels into a single consensus target. While this simplifies SER as a single-label task, it ignores the inherent subjectivity of human emotion perception. This dissertation challenges such assumptions and asks: (1) Should minority emotional ratings be discarded? (2) Should SER systems learn from only a few individuals' perceptions? (3) Should SER systems predict only one emotion per sample? Psychological studies show that emotion perception is subjective and ambiguous, with overlapping emotional boundaries. We propose new modeling and evaluation perspectives: (1) Retain all emotional ratings and represent them with soft-label distributions. Models trained on individual annotator ratings and jointly optimized with standard SER systems improve performance on consensus-labeled tests. (2) Redefine SER evaluation by including all emotional data and allowing co-occurring emotions (e.g., sad and angry). We propose an ``all-inclusive rule'' that aggregates all ratings to maximize diversity in label representation. Experiments on four English emotion databases show superior performance over majority and plurality labeling. (3) Construct a penalization matrix to discourage unlikely emotion combinations during training. Integrating it into loss functions further improves performance. Overall, embracing minority ratings, multiple annotators, and multi-emotion predictions yields more robust and human-aligned SER systems.

eess.AS↗

arXiv2025

Reasoning Beyond Majority Vote: An Explainable SpeechLM Framework for Speech Emotion Recognition

Speech Emotion Recognition (SER) is typically trained and evaluated on majority-voted labels, which simplifies benchmarking but masks subjectivity and provides little transparency into why predictions are made. This neglects valid minority annotations and limits interpretability. We propose an explainable Speech Language Model (SpeechLM) framework that frames SER as a generative reasoning task. Given an utterance, the model first produces a transcript, then outputs both an emotion label and a concise natural-language rationale grounded in lexical and acoustic cues. Rationales are generated by a reasoning-capable teacher LLM and used as intermediate supervision, combined with majority labels during fine-tuning. Unlike prior work primarily focused on boosting classification accuracy, we aim to enhance explainability while preserving competitive performance. To this end, we complement majority-label metrics with annotator-aware scoring that credits matches with any annotator label. On MSP-Podcast v1.12, our model maintains improvements over zero-shot SpeechLM baselines, and produces rationales that human evaluators find plausible and well grounded. This demonstrates that incorporating rationale supervision offers a practical path toward interpretable SER without sacrificing predictive quality.

eess.AS↗

arXiv2025

ZSDEVC: Zero-Shot Diffusion-based Emotional Voice Conversion with Disentangled Mechanism

The human voice conveys not just words but also emotional states and individuality. Emotional voice conversion (EVC) modifies emotional expressions while preserving linguistic content and speaker identity, improving applications like human-machine interaction. While deep learning has advanced EVC models for specific target speakers on well-crafted emotional datasets, existing methods often face issues with emotion accuracy and speech distortion. In addition, the zero-shot scenario, in which emotion conversion is applied to unseen speakers, remains underexplored. This work introduces a novel diffusion framework with disentangled mechanisms and expressive guidance, trained on a large emotional speech dataset and evaluated on unseen speakers across in-domain and out-of-domain datasets. Experimental results show that our method produces expressive speech with high emotional accuracy, naturalness, and quality, showcasing its potential for broader EVC applications.

eess.AS↗

arXiv2025

Lessons Learnt: Revisit Key Training Strategies for Effective Speech Emotion Recognition in the Wild

In this study, we revisit key training strategies in machine learning often overlooked in favor of deeper architectures. Specifically, we explore balancing strategies, activation functions, and fine-tuning techniques to enhance speech emotion recognition (SER) in naturalistic conditions. Our findings show that simple modifications improve generalization with minimal architectural changes. Our multi-modal fusion model, integrating these optimizations, achieves a valence CCC of 0.6953, the best valence score in Task 2: Emotional Attribute Regression. Notably, fine-tuning RoBERTa and WavLM separately in a single-modality setting, followed by feature fusion without training the backbone extractor, yields the highest valence performance. Additionally, focal loss and activation functions significantly enhance performance without increasing complexity. These results suggest that refining core components, rather than deepening models, leads to more robust SER in-the-wild.

eess.AS↗

arXiv2025

Speaker Style-Aware Phoneme Anchoring for Improved Cross-Lingual Speech Emotion Recognition

Cross-lingual speech emotion recognition (SER) remains a challenging task due to differences in phonetic variability and speaker-specific expressive styles across languages. Effectively capturing emotion under such diverse conditions requires a framework that can align the externalization of emotions across different speakers and languages. To address this problem, we propose a speaker-style aware phoneme anchoring framework that aligns emotional expression at the phonetic and speaker levels. Our method builds emotion-specific speaker communities via graph-based clustering to capture shared speaker traits. Using these groups, we apply dual-space anchoring in speaker and phonetic spaces to enable better emotion transfer across languages. Evaluations on the MSP-Podcast (English) and BIIC-Podcast (Taiwanese Mandarin) corpora demonstrate improved generalization over competitive baselines and provide valuable insights into the commonalities in cross-lingual emotion representation.

cs.CL↗

arXiv2025

Joint Learning using Mixture-of-Expert-Based Representation for Speech Enhancement and Robust Emotion Recognition

Speech emotion recognition (SER) plays a critical role in building emotion-aware speech systems, but its performance degrades significantly under noisy conditions. Although speech enhancement (SE) can improve robustness, it often introduces artifacts that obscure emotional cues and adds computational overhead to the pipeline. Multi-task learning (MTL) offers an alternative by jointly optimizing SE and SER tasks. However, conventional shared-backbone models frequently suffer from gradient interference and representational conflicts between tasks. To address these challenges, we propose the Sparse Mixture-of-Experts Representation Integration Technique (Sparse MERIT), a flexible MTL framework that applies frame-wise expert routing over self-supervised speech representations. Sparse MERIT incorporates task-specific gating networks that dynamically select from a shared pool of experts for each frame, enabling parameter-efficient and task-adaptive representation learning. Experiments on the MSP-Podcast corpus show that Sparse MERIT consistently outperforms baseline models on both SER and SE tasks. Under the most challenging condition of -5 dB signal-to-noise ratio (SNR), Sparse MERIT improves SER F1-macro by an average of 12.0% over a baseline relying on a SE pre-processing strategy, and by 3.4% over a naive MTL baseline, with statistical significance on unseen noise conditions. For SE, Sparse MERIT improves segmental SNR (SSNR) by 28.2% over the SE pre-processing baseline and by 20.0% over the naive MTL baseline. These results demonstrate that Sparse MERIT provides robust and generalizable performance for both emotion recognition and enhancement tasks in noisy environments.

eess.AS↗

arXiv2025

Improving the Robustness and Clinical Applicability of Automatic Respiratory Sound Classification Using Deep Learning-Based Audio Enhancement: Algorithm Development and Validation

Deep learning techniques have shown promising results in the automatic classification of respiratory sounds. However, accurately distinguishing these sounds in real-world noisy conditions remains challenging for clinical deployment. In addition, predicting signals with only background noise may reduce user trust in the system. This study explores the feasibility and effectiveness of incorporating a deep learning-based audio enhancement step into automatic respiratory sound classification systems to improve robustness and clinical applicability. We conducted extensive experiments using various audio enhancement model architectures, including time-domain and time-frequency-domain approaches, combined with multiple classification models to evaluate the module's effectiveness. The classification performance was compared against the noise injection data augmentation method. These experiments were carried out on two datasets: the ICBHI respiratory sound dataset and the FABS dataset. Furthermore, a physician validation study assessed the system's clinical utility. Integrating the audio enhancement module resulted in a 21.9% increase in the ICBHI classification score and a 4.1% improvement on the FABS dataset in multi-class noisy scenarios. Quantitative analysis revealed efficiency gains, higher diagnostic confidence, and increased trust, with workflows using enhanced audio improving diagnostic sensitivity by 11.6% and enabling high-confidence diagnoses. Incorporating an audio enhancement algorithm boosts the robustness and clinical utility of automatic respiratory sound classification systems, enhancing performance in noisy environments and fostering greater trust among medical professionals.

eess.AS↗

arXiv2025

Is It Still Fair? Investigating Gender Fairness in Cross-Corpus Speech Emotion Recognition

Speech emotion recognition (SER) is a vital component in various everyday applications. Cross-corpus SER models are increasingly recognized for their ability to generalize performance. However, concerns arise regarding fairness across demographics in diverse corpora. Existing fairness research often focuses solely on corpus-specific fairness, neglecting its generalizability in cross-corpus scenarios. Our study focuses on this underexplored area, examining the gender fairness generalizability in cross-corpus SER scenarios. We emphasize that the performance of cross-corpus SER models and their fairness are two distinct considerations. Moreover, we propose the approach of a combined fairness adaptation mechanism to enhance gender fairness in the SER transfer learning tasks by addressing both source and target genders. Our findings bring one of the first insights into the generalizability of gender fairness in cross-corpus SER systems.

cs.LG↗

arXiv2024

Mouth Articulation-Based Anchoring for Improved Cross-Corpus Speech Emotion Recognition

Cross-corpus speech emotion recognition (SER) plays a vital role in numerous practical applications. Traditional approaches to cross-corpus emotion transfer often concentrate on adapting acoustic features to align with different corpora, domains, or labels. However, acoustic features are inherently variable and error-prone due to factors like speaker differences, domain shifts, and recording conditions. To address these challenges, this study adopts a novel contrastive approach by focusing on emotion-specific articulatory gestures as the core elements for analysis. By shifting the emphasis on the more stable and consistent articulatory gestures, we aim to enhance emotion transfer learning in SER tasks. Our research leverages the CREMA-D and MSP-IMPROV corpora as benchmarks and it reveals valuable insights into the commonality and reliability of these articulatory gestures. The findings highlight mouth articulatory gesture potential as a better constraint for improving emotion recognition across different settings or domains.

cs.SD↗

arXiv2024

EMO-Codec: An In-Depth Look at Emotion Preservation capacity of Legacy and Neural Codec Models With Subjective and Objective Evaluations

The neural codec model reduces speech data transmission delay and serves as the foundational tokenizer for speech language models (speech LMs). Preserving emotional information in codecs is crucial for effective communication and context understanding. However, there is a lack of studies on emotion loss in existing codecs. This paper evaluates neural and legacy codecs using subjective and objective methods on emotion datasets like IEMOCAP. Our study identifies which codecs best preserve emotional information under various bitrate scenarios. We found that training codec models with both English and Chinese data had limited success in retaining emotional information in Chinese. Additionally, resynthesizing speech through these codecs degrades the performance of speech emotion recognition (SER), particularly for emotions like sadness, depression, fear, and disgust. Human listening tests confirmed these findings. This work guides future speech technology developments to ensure new codecs maintain the integrity of emotional information in speech.

eess.AS↗

arXiv2024

A Layer-Anchoring Strategy for Enhancing Cross-Lingual Speech Emotion Recognition

Cross-lingual speech emotion recognition (SER) is important for a wide range of everyday applications. While recent SER research relies heavily on large pretrained models for emotion training, existing studies often concentrate solely on the final transformer layer of these models. However, given the task-specific nature and hierarchical architecture of these models, each transformer layer encapsulates different levels of information. Leveraging this hierarchical structure, our study focuses on the information embedded across different layers. Through an examination of layer feature similarity across different languages, we propose a novel strategy called a layer-anchoring mechanism to facilitate emotion transfer in cross-lingual SER tasks. Our approach is evaluated using two distinct language affective corpora (MSP-Podcast and BIIC-Podcast), achieving a best UAR performance of 60.21% on the BIIC-podcast corpus. The analysis uncovers interesting insights into the behavior of popular pretrained models.

cs.SD↗

arXiv2024

Emo-bias: A Large Scale Evaluation of Social Bias on Speech Emotion Recognition

The rapid growth of Speech Emotion Recognition (SER) has diverse global applications, from improving human-computer interactions to aiding mental health diagnostics. However, SER models might contain social bias toward gender, leading to unfair outcomes. This study analyzes gender bias in SER models trained with Self-Supervised Learning (SSL) at scale, exploring factors influencing it. SSL-based SER models are chosen for their cutting-edge performance. Our research pioneering research gender bias in SER from both upstream model and data perspectives. Our findings reveal that females exhibit slightly higher overall SER performance than males. Modified CPC and XLS-R, two well-known SSL models, notably exhibit significant bias. Moreover, models trained with Mandarin datasets display a pronounced bias toward valence. Lastly, we find that gender-wise emotion distribution differences in training data significantly affect gender bias, while upstream model representation has a limited impact.

eess.AS↗

arXiv2024

EMO-SUPERB: An In-depth Look at Speech Emotion Recognition

Speech emotion recognition (SER) is a pivotal technology for human-computer interaction systems. However, 80.77% of SER papers yield results that cannot be reproduced. We develop EMO-SUPERB, short for EMOtion Speech Universal PERformance Benchmark, which aims to enhance open-source initiatives for SER. EMO-SUPERB includes a user-friendly codebase to leverage 15 state-of-the-art speech self-supervised learning models (SSLMs) for exhaustive evaluation across six open-source SER datasets. EMO-SUPERB streamlines result sharing via an online leaderboard, fostering collaboration within a community-driven benchmark and thereby enhancing the development of SER. On average, 2.58% of annotations are annotated using natural language. SER relies on classification models and is unable to process natural languages, leading to the discarding of these valuable annotations. We prompt ChatGPT to mimic annotators, comprehend natural language annotations, and subsequently re-label the data. By utilizing labels generated by ChatGPT, we consistently achieve an average relative gain of 3.08% across all settings.

eess.AS↗