Curriculum Vitae | Huang-Cheng Chou

Summary

I am a Postdoctoral Scholar– NSTC Fellow at the Signal Analysis and Interpretation Laboratory (SAIL) at the University of Southern California, working with Prof. Shrikanth S. Narayanan, including the Speech Production and Articulation Knowledge (SPAN) effort. I received my Ph.D. in Electrical Engineering from National Tsing Hua University (NTHU), advised by Prof. Chi-Chun Lee (BIIC Lab). My dissertation, Revisiting Modeling and Evaluation Approaches in Speech Emotion Recognition: Considering Subjectivity of Annotators and Ambiguity of Emotions, received the ACLCLP Doctoral Dissertation Award, Honorable Mention. I am currently seeking full-time research and industry positions.

My work treats emotion labels as subjective, multi-label, and often disagreeing human judgments rather than a single ground truth. That program runs from annotator modeling and calibration (ICASSP, INTERSPEECH, IEEE TAFFC) through open evaluation (EMO-SUPERB) to fairness audits and a survey of bias in speech AI. I also work on assistant-style speech systems (unified ASR + SER at Amazon Alexa; on-device SER / KWS at RealTek), speech-LLM evaluation and resources, and first-author assessment of speech enhancement for real-time MRI audio.

Authorship and contribution notes. Name in bold is Huang-Cheng Chou. EMO-SUPERB / Open-Emotion is equal-first with Haibin Wu. On DeSTA2.5-Audio I contributed the emotion-data stack (label schema and dimensional annotations), not the full model. On Do You Hear What I Mean? I led the core evaluation pipeline, not the TTS model. Papers marked Mentored are student-led work I advised. The APSIPA ASC Best Regular Paper Award (2019) is for conversational deception detection, not later SER papers.

Research interests

Speech emotion recognition under annotator subjectivity and emotion ambiguity: multi-label learning, soft labels, calibration, and evaluation rules that keep minority ratings.
Speech / audio large language models: evaluation contracts, emotion-aware data, and downstream SER with speech LLMs.
Fairness, bias, and reliability of speech systems (SER, TTS evaluation, speaker, and cross-task surveys).
Conversational and dyadic social signal processing: deception, belongingness, and clinical affect such as depression-related speech.
Multitask and edge speech systems: unified ASR + SER, keyword spotting, and compute-constrained on-device models.
Low-resource and multilingual speech (including Taigi / Taiwanese Hokkien intent).
Speech enhancement and downstream evaluation for real-time MRI (rtMRI) of vocal-tract shaping.

Education

Ph.D., Electrical Engineering

National Tsing Hua University (NTHU) · Advisor: Prof. Chi-Chun Lee (BIIC Lab)

Feb 2016 – Jul 2024 Hsinchu, Taiwan

GPA 3.82 / 4.0.
Dissertation: Revisiting Modeling and Evaluation Approaches in Speech Emotion Recognition: Considering Subjectivity of Annotators and Ambiguity of Emotions.
ACLCLP Doctoral Dissertation Award, Honorable Mention (2024).

Visiting Scholar (during Ph.D.)

The University of Texas at Dallas · MSP Lab · Prof. Carlos Busso · NSTC / MOST Graduate Students Study Abroad Grant

Aug 2021 – Sep 2022 Dallas, TX, USA

Perceptual annotation modeling, calibration, and robustness for speech emotion recognition; collaboration on MSP-Podcast and related SER evaluation work.
This is a visiting appointment during the NTHU Ph.D., not a separate UTD degree.

B.S., Electrical Engineering

National Tsing Hua University (NTHU)

Sep 2011 – Jun 2016 Hsinchu, Taiwan

Appointments

Postdoctoral Scholar (NSTC Fellow)

University of Southern California · SAIL / SPAN · Advisor: Prof. Shrikanth S. Narayanan

Oct 2025 – Present Los Angeles, CA, USA

NSTC Postdoctoral Research Abroad Program fellow at SAIL.
First-author work on speech enhancement for real-time MRI: evaluates Denoiser, PASE, and RE-USE across five rtMRI corpora on predicted quality, source preservation, ASR, speaker, and paralinguistic endpoints; preprint arXiv:2608.16125 (submitted to JASA), with an open demo at rmridemo.huangchengchou.com.
Speech emotion with speech LLMs; mentoring on VoxEmo (reproducible speech-LLM SER toolkit; IEEE TAFFC, under review).
Non-verbal vocalizations and speaker identity (INTERSPEECH 2026); cross-lingual speaker verification (AMECxSV); dyadic clinical / depression-related speech (mentored papers).
Collaborations continuing from the NTU SPML period, including DeSTA2.5-Audio, TaigiSpeech, and the fairness survey.

Independent Researcher / Collaborator

National Taiwan University · Speech Processing and Machine Learning (SPML) Lab · Prof. Hung-yi Lee

Sep 2024 – Oct 2025 Taipei, Taiwan

No official NTU visiting or employment appointment. Independent research while serving Taiwan substitute military service, in collaboration with SPML Lab members.
Fairness and debiasing in multi-label SER (Emo-bias, EMO-Debias, CO-VADA; INTERSPEECH 2025 subgroup-disparity work with fairness-metric gains above 28% at small accuracy cost).
Instruction-guided expressive TTS evaluation (Do You Hear What I Mean?, ICASSP 2026; evaluation pipeline).
Low-resource speech: TaigiSpeech (INTERSPEECH 2026 long paper).
INTERSPEECH 2026 co-author papers on emotion-embedding evaluation and compositional gender bias in instruction TTS.
Emotion-data / label schema contributions to DeSTA2.5-Audio (IEEE TASLP 2026).
Joint publications at INTERSPEECH, ASRU, ICASSP, and IEEE TASLP; roles vary (second / co-author / mentored).

Substitute Military Service

Taipei City Government · Taiwan mandatory substitute service

Sep 2024 – Sep 2025 Taipei, Taiwan

Completed Taiwan substitute (alternative) military service. Speech research in this period was independent collaboration with NTU SPML, not an official government research post.

Applied ML / DSP Engineer Intern

RealTek Semiconductor · Emerging Tech / Advanced DSP

Jun 2024 – Sep 2024 Hsinchu, Taiwan

Streaming on-device speech emotion recognition and keyword spotting (Python, TensorFlow) under FLOPs / MACs / parameter budgets for consumer devices.
Compressed SER models with about 30% smaller footprint while targeting the same accuracy operating point; estimated compute for neural KWS and SER on edge runtimes.

Applied Scientist Intern

Amazon AGI · Alexa Speech / Hybrid Science / ASR

Aug 2023 – Nov 2023 Pittsburgh, PA, USA

Emotion-aware spoken language understanding for assistant traffic: unified shared-layer ASR + multi-label SER, about 20% lower system complexity than separate ASR and SER stacks.
Diagnosed Whisper ASR degradation on emotional speech (about 15% higher error versus neutral). Two-stage fine-tuning improved WER by 8.85% absolute (not a relative 29.75% figure).
Related first-author paper: Tiny Whisper-SER (APSIPA ASC 2024).

Graduate Research Assistant

NTHU · BIIC Lab · Advisor: Prof. Chi-Chun Lee

Feb 2016 – Jul 2024 Hsinchu, Taiwan

Speech emotion recognition under annotator subjectivity and emotion ambiguity: multi-label learning, co-rater training, calibration, and all-inclusive aggregation for evaluation.
Led / co-led Mandarin dyadic corpora NNIME (interactive multimodal emotion) and DDDM (deception in dialog games) as community data resources.
Co-led EMO-SUPERB / Open-Emotion (IEEE SLT 2024; equal-first with Haibin Wu): standardized splits, codebase, and live leaderboard.
Mentored junior students on experiments and publications in SER, deception, and small-group conversation.

Research Assistant — automatic meeting summarization

Industrial Technology Research Institute (ITRI)

Dec 2018 – Dec 2019 Hsinchu, Taiwan

Transformer / BERT pipelines for multi-party spoken meeting summarization.

Research Intern

Industrial Technology Research Institute (ITRI)

Jul 2015 – Sep 2015 Hsinchu, Taiwan

Polarity-term discovery with NLP over web text (BBS, Yahoo, Twitter) and parallel processing on Apache Spark.

Undergraduate Research Assistant

NTHU · BIIC Lab · Prof. Chi-Chun Lee

Sep 2014 – Jan 2016 Hsinchu, Taiwan

Collection of a Taiwan Mandarin interactive multimodal emotion corpus (NNIME) and early machine-learning baselines for Mandarin multimodal emotion recognition; continued into the Ph.D.

Selected research highlights

Grouped by theme. Full bibliographic entries are in Publications.

rtMRI speech and source preservation

[First] Systematic assessment of off-the-shelf enhancement (Denoiser, PASE, RE-USE) on five rtMRI corpora: predicted quality does not reliably imply better ASR or source fidelity. Treat enhanced rtMRI audio as a task-specific derivative, not a universal replacement. arXiv:2608.16125; submitted to JASA.

Subjective & ambiguous SER

[First] Annotator-aware SER from Every Rating Matters (ICASSP 2019) through co-rater training, co-occurrence, typed descriptions, calibration (INTERSPEECH 2023), and all-inclusive aggregation (IEEE TAFFC 2024; SLT 2024).
[Equal first] EMO-SUPERB / Open-Emotion: leakage-aware splits, SSL baselines, codebase, and live leaderboard (IEEE SLT 2024).

Fairness, safety, and evaluation of expressive speech

[Co] Toward Fair Speech Technologies — survey of bias and fairness in speech AI (arXiv:2605.01597; submitted to TMLR), with awesome-speech-fairness and a Hugging Face collection.
[Co] INTERSPEECH 2026: emotion-embedding similarity is a misleading TTS/VC metric; compositional gender bias in instruction TTS.
[Second] Subgroup-disparity mitigation without requiring explicit demographics (INTERSPEECH 2025); EMO-Debias (ASRU 2025).
[Co] Emo-bias, CO-VADA; [Second] instruction–perception gap in expressive TTS (Do You Hear What I Mean?, ICASSP 2026; evaluation pipeline).

Speech / audio LLMs and assistant systems

[Co] DeSTA2.5-Audio (IEEE TASLP 2026) — emotion-data / labels, not the full model.
[First] Tiny Whisper-SER; Amazon Alexa intern: shared-layer ASR + SER and emotional-speech WER diagnosis.
[Mentored] VoxEmo toolkit for speech-LLM SER (IEEE TAFFC, under review).
[Mentored] Layer-wise ASR/SER task-vector merging for categorical SER (INTERSPEECH 2026).

Low-resource, speaker, and clinical speech

[Co] TaigiSpeech; under-resourced SER via speech-to-speech translation (ICASSP 2025).
[Mentored] Speaker identity in non-verbal vocalizations (INTERSPEECH 2026); AMECxSV; dyadic depression detection papers.

Conversational social signals

[First] Deception in Mandarin dialog games (APSIPA ASC 2019 Best Regular Paper; APSIPA TSIP 2021; ACL Findings 2021).
[First / lead] NNIME dyadic corpus (ACII 2017); [Second] belongingness and group emotion at ICMI 2021.

Awards & honors

NSTC Postdoctoral Research Abroad Fellowship — National Science and Technology Council, Taiwan, 2025–2026
Merry Electronics Electroacoustics Thesis Award — Silver (2025) and Bronze (2021)
ACLCLP Doctoral Dissertation Award — Honorable Mention (2024)
NOVATEK Ph.D. Excellence Scholarship — 2022–2023
The Rotary Foundation Excellence Scholarship — 2021
MOST (NSTC) Graduate Students Study Abroad Grant — 2020–2022 (UT Dallas visiting year)
APSIPA ASC Best Regular Paper Award — 2019 (conversational deception detection)
MOST Futuretek Breakthrough Award — 2019
NTHU Dean Ph.D. Student Excellence Scholarship — 2016–2020
TITC Excellence Scholarship — 2015
TSMC Excellence Scholarship — 2014

Travel support

IEEE SPS ICASSP Travel Grant — 2025
IEEE SLT Travel Grant — 2024
ACLCLP Outstanding Students Conference Travel Grant — 2019, 2022, 2024, 2025
FAOS Outstanding Students Conference Travel Grant — 2019, 2022, 2023
Google East Asia Student Travel Grants — ICASSP 2022 and INTERSPEECH 2022
ISCA INTERSPEECH Grant — 2022
AAAC ACII Student Travel Grant — 2017

Academic service & mentoring

Journal reviewer: IEEE/ACM TASLP; IEEE TAFFC; Elsevier Pattern Recognition; Computer Speech and Language; Information Processing & Management; APSIPA TSIP; IEEE Transactions on Multimedia.
Conference reviewer: INTERSPEECH (2022–2025); ICASSP (2022–2023); ACM Multimedia (2024).
ISCA Student Advisory Committee (2023–2024), including student mentoring events.
IEEE SLT 2024 committee service.
Mentoring: VoxEmo; layer-wise ASR/SER task-vector merging (INTERSPEECH 2026); dyadic depression detection; speaker identity in non-verbal vocalizations (INTERSPEECH 2026); AMECxSV. Junior BIIC students on SER and conversational experiments during the Ph.D.

Languages

Mandarin Chinese — native.
English — professional working proficiency.
Taiwanese (Taigi / Hokkien) — full professional proficiency.

Open resources

EMO-SUPERB / Open-Emotion — reproducible SER benchmark, splits, and leaderboard. Code: github.com/ag027592/EMO-SUPERB.
awesome-speech-fairness — living bibliography for the fairness survey. Hub: Hugging Face collection.
rtMRI speech enhancement demo — companion to arXiv:2608.16125.
MSP-Podcast — large naturalistic SER corpus (IEEE TAFFC 2026); paper: DOI.
NNIME — NTHU–NTUA Chinese interactive multimodal emotion corpus (ACII 2017).
VoxEmo — mentored reproducibility toolkit for speech-LLM SER.
emotional TTS labeling instructions — annotation interface and examples for expressive TTS perceptual labels.

Technical skills

Speech / ML: ASR, SER, speech LLMs, Whisper / SSL fine-tuning, TTS evaluation, neural codecs, KWS, multilingual and low-resource speech; calibration and fairness evaluation; PyTorch, TensorFlow, Hugging Face.
Systems: Python, SQL, Git, Linux; AWS / S3 speech-data workflows; Praat, openSMILE, librosa, Fairseq.
Edge: Streaming inference, on-device FLOPs / MACs / parameter budgets, model compression for SER / KWS.

Publications

Complete list grouped by authorship role. Huang-Cheng Chou in bold. Also on Google Scholar (722 citations; h-index 15; i10-index 23 as of 29 Aug 2026).

First-author (including equal-first)

First Navigating Speech Enhancement for Real-Time MRI: A Systematic Assessment of Signal Quality, Source Preservation, and Downstream Tasks Huang-Cheng Chou, Sean Foley, Haley Hsu, Kevin Huang, Szu-Jui Chen, Rong Chao, Louis Goldstein, Khalil Iskarous, Dani Byrd, Yu Tsao, Sudarsana Reddy Kadiri, John H. L. Hansen, Shrikanth Narayanan arXiv:2608.16125, 2026 (submitted to JASA) arXiv · Demo
First Stimulus Modality Matters: Impact of Perceptual Evaluations from Different Modalities on Speech Emotion Recognition System Performance Huang-Cheng Chou, Haibin Wu, Chi-Chun Lee ICASSP 2025 DOI
First A Tiny Whisper-SER: Unifying Automatic Speech Recognition and Multi-label Speech Emotion Recognition Tasks Huang-Cheng Chou APSIPA ASC 2024 DOI
First Empower Typed Descriptions by Large Language Models for Speech Emotion Recognition Huang-Cheng Chou, Haibin Wu, Kai-Wei Chang, Lucas Goncalves, Jiawei Du, Jyh-Shing Roger Jang, Chi-Chun Lee, Hung-yi Lee APSIPA ASC 2024 DOI
Equal first Open-Emotion: A Reproducible EMO-Superb For Speech Emotion Recognition Systems Huang-Cheng Chou^*, Haibin Wu^*, Kai-Wei Chang, Lucas Goncalves, Jiawei Du, Jyh-Shing Roger Jang, Chi-Chun Lee, Hung-yi Lee IEEE SLT 2024 *Equal contribution with Haibin Wu. DOI · Project · Code
Equal first EMO-SUPERB: An In-depth Look at Speech Emotion Recognition Haibin Wu^*, Huang-Cheng Chou^*, Kai-Wei Chang, Lucas Goncalves, Jiawei Du, Jyh-Shing Roger Jang, Chi-Chun Lee, Hung-yi Lee arXiv:2402.13018, 2024 — extended preprint of the IEEE SLT 2024 EMO-SUPERB / Open-Emotion paper, not a separate publication. arXiv
First Embracing Ambiguity And Subjectivity Using The All-Inclusive Aggregation Rule For Evaluating Multi-Label Speech Emotion Recognition Systems Huang-Cheng Chou, Lucas Goncalves, Haibin Wu, Hung-yi Lee, Chi-Chun Lee IEEE SLT 2024 DOI
First Minority Views Matter: Evaluating Speech Emotion Classifiers with Human Subjective Annotations by an All-Inclusive Aggregation Rule Huang-Cheng Chou, Lucas Goncalves, Seong-Gyun Leem, Ali N. Salman, Chi-Chun Lee, Carlos Busso IEEE Transactions on Affective Computing, 2024 DOI
First The Importance of Calibration: Rethinking Confidence and Performance of Speech Multi-label Emotion Classifiers Huang-Cheng Chou, Lucas Goncalves, Seong-Gyun Leem, Chi-Chun Lee, Carlos Busso INTERSPEECH 2023 DOI
First Do Minority Views in Perceptual Evaluations Affect Confidence of Speech Emotion Classifiers? Huang-Cheng Chou ACII Workshops and Demos (ACIIW) 2022 DOI
First Predicting Inter-annotator Agreements to Improve Calibration and Performance of Speech Emotion Classifiers Huang-Cheng Chou 8th Doctoral Consortium, INTERSPEECH 2022 PDF
First Exploiting Co-occurrence Frequency of Emotions in Perceptual Evaluations To Train A Speech Emotion Classifier Huang-Cheng Chou, Chi-Chun Lee, Carlos Busso INTERSPEECH 2022 DOI · ISCA
First Exploiting Annotators' Typed Description of Emotion Perception to Maximize Utilization of Ratings for Speech Emotion Recognition Huang-Cheng Chou, Wei-Cheng Lin, Chi-Chun Lee, Carlos Busso ICASSP 2022 DOI
First “Does it Matter When I Think You Are Lying?” Improving Deception Detection by Integrating Interlocutor’s Judgements in Conversations Huang-Cheng Chou, Woan-Shiuan Chien, Da-Cheng Juan, Chi-Chun Lee Findings of ACL-IJCNLP 2021 ACL · DOI
First Automatic Deception Detection using Multiple Speech and Language Communicative Descriptors in Dialogs Huang-Cheng Chou, Yi-Wen Liu, Chi-Chun Lee APSIPA Transactions on Signal and Information Processing, 2021 DOI
First “Your Behavior Makes Me Think It Is a Lie”: Recognizing Perceived Deception using Multimodal Data in Dialog Games Huang-Cheng Chou, Chi-Chun Lee APSIPA ASC 2020 IEEE
First Learning to Recognize Per-Rater’s Emotion Perception Using Co-Rater Training Strategy with Soft and Hard Labels Huang-Cheng Chou, Chi-Chun Lee INTERSPEECH 2020 DOI
First Joint Learning of Conversational Temporal Dynamics and Acoustic Features for Speech Deception Detection in Dialog Games Huang-Cheng Chou, Yi-Wen Liu, Chi-Chun Lee APSIPA ASC 2019 — Best Regular Paper Award DOI
First Every Rating Matters: Joint Learning of Subjective Labels and Individual Annotators for Speech Emotion Classification Huang-Cheng Chou, Chi-Chun Lee ICASSP 2019 DOI
First NNIME: The NTHU-NTUA Chinese Interactive Multimodal Emotion Corpus Huang-Cheng Chou, Wei-Cheng Lin, Lien-Chiang Chang, Chyi-Chang Li, Hsi-Pin Ma, Chi-Chun Lee ACII 2017 DOI
First Amplifying a Sense of Emotion toward Drama—Long Short-Term Memory Recurrent Neural Network for Dynamic Emotion Recognition Huang-Cheng Chou, Chun-Min Chang, Yu-Shuo Liu, Shiuan-Kai Kao, Chi-Chun Lee ROCLING 2017 ACL

Second-author

Second Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-to-Speech Systems Yi-Cheng Lin, Huang-Cheng Chou, Tzu-Chieh Wei, Kuan-Yu Chen, Hung-yi Lee ICASSP 2026 Contribution: core evaluation pipeline for the instruction–perception gap, not the TTS model itself. DOI
Second EMO-Debias: Benchmarking Gender Debiasing Techniques in Multi-Label Speech Emotion Recognition Yi-Cheng Lin, Huang-Cheng Chou, Yu-Hsuan Li Liang, Hung-yi Lee IEEE ASRU 2025 DOI
Second Mitigating Subgroup Disparities in Multi-Label Speech Emotion Recognition: A Pseudo-Labeling and Unsupervised Learning Approach Yi-Cheng Lin, Huang-Cheng Chou, Hung-yi Lee INTERSPEECH 2025 DOI
Second Jointly Learning From Unimodal and Multimodal-Rated Labels in Audio-Visual Emotion Recognition Lucas Goncalves, Huang-Cheng Chou, Ali N. Salman, Chi-Chun Lee, Carlos Busso IEEE Open Journal of Signal Processing, 2025 DOI
Second Contextual Attention for Robust Audio-Visual Emotion Recognition Lucas Goncalves, Huang-Cheng Chou, Ali N. Salman, Chi-Chun Lee, Carlos Busso IEEE Open Journal of Signal Processing, 2025 DOI
Second Belongingness and Satisfaction Recognition from Physiological Synchrony with A Group-Modulated Attentive BLSTM under Small-group Conversation Woan-Shiuan Chien, Huang-Cheng Chou, Chi-Chun Lee ICMI Companion 2021 DOI
Second Self-assessed Emotion Classification from Acoustic and Physiological Features within Small-group Conversation Woan-Shiuan Chien, Huang-Cheng Chou, Chi-Chun Lee ICMI Companion 2021 DOI
Second Acoustic Indicators of Deception in Mandarin Daily Conversations Recorded from an Interactive Game Chih-Hsiang Huang, Huang-Cheng Chou, Yi-Tong Wu, Chi-Chun Lee, Yi-Wen Liu INTERSPEECH 2019 DOI
Second Development of a rapid and economic in vivo electrocardiogram platform for cardiovascular drug assay and electrophysiology research in adult zebrafish Min-Hsuan Lin, Huang-Cheng Chou, Yu-Fu Chen, Wangta Liu, Chi-Chun Lee, Lawrence Yu-Min Liu, Yung-Jen Chuang Scientific Reports, 2018 DOI

Co-author

Co Toward Fair Speech Technologies: A Comprehensive Survey of Bias and Fairness in Speech AI Yi-Cheng Lin, Yun-Shao Tsai, Kuan-Yu Chen, Hsiao-Ying Huang, Huang-Cheng Chou, Shrikanth Narayanan, Yu Tsao, Jian-Jiun Ding, Hung-yi Lee arXiv:2605.01597, 2026 (submitted to TMLR) arXiv · Code · Hub
Co DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model With Self-Generated Cross-Modal Alignment Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu, Chao-Han Huck Yang, Sung-Feng Huang, Chih-Kai Yang, Chee-En Yu, Chun-Wei Chen, Wei-Chih Chen, Chien-yu Huang, Yi-Cheng Lin, Yu-Xiang Lin, Chi-An Fu, Chun-Yi Kuan, Wenze Ren, Xuanjun Chen, Wei-Ping Huang, En-Pei Hu, Tzu-Quan Lin, Yuan-Kuei Wu, Kuan-Po Huang, Hsiao-Ying Huang, Huang-Cheng Chou, Kai-Wei Chang, Cheng-Han Chiang, Boris Ginsburg, Yu-Chiang Frank Wang, Hung-yi Lee IEEE Transactions on Audio, Speech and Language Processing, 2026 Contribution: emotion-data stack (label schema and dimensional annotations), not the full model architecture. DOI · Model
Co TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wild Kai-Wei Chang, Yi-Cheng Lin, Huang-Cheng Chou, Wenze Ren, Yu-Han Huang, Yun-Shao Tsai, Chien-Cheng Chen, Yu Tsao, Yuan-Fu Liao, Shrikanth Narayanan, James Glass, Hung-yi Lee INTERSPEECH 2026 (long paper); arXiv:2603.21478 arXiv
Co The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation Yun-Shao Tsai, Yi-Cheng Lin, Huang-Cheng Chou, Tzu-Wen Hsu, Yun-Man Hsu, Chun Wei Chen, Shrikanth Narayanan, Hung-yi Lee INTERSPEECH 2026; arXiv:2604.26347 arXiv
Co The Binding Effect: Analyzing How Multi-Dimensional Cues Form Gender Bias in Instruction TTS Kuan-Yu Chen, Yi-Cheng Lin, Po-Chung Hsieh, Huang-Cheng Chou, Chih-Fan Hsu, Jeng-Lin Li, Hung-yi Lee, Jian-Jiun Ding INTERSPEECH 2026; arXiv:2603.20743 arXiv
Co AV-EMO-Reasoning: Benchmarking Emotional Reasoning Capabilities in Omni-modal LLMs with Audio-visual Cues Dingkun Zhou, Krish Patel, Ajay Kankipati, Akshaj Gupta, Zeyi Austin Li, Mohul Shukla, Vibhor Narang, Sara Kofman, Zongli Ye, Grace Wang, Xiaoyu Shi, Tingle Li, Guan-Ting Lin, Kan Jen Cheng, Huang-Cheng Chou, Jiachen Lian, Gopala Anumanchipalli arXiv:2510.07355, 2025 arXiv
Co The MSP-Podcast Corpus Carlos Busso, Reza Lotfian, Kusha Sridhar, Ali N. Salman, Wei-Cheng Lin, Lucas Goncalves, Srinivas Parthasarathy, Abinay Reddy Naini, Seong-Gyun Leem, Luz Martinez-Lucas, Huang-Cheng Chou, Pravin Mote IEEE Transactions on Affective Computing, 2026 (early access) DOI · arXiv · Corpus
Co CO-VADA: A Confidence-Oriented Voice Augmentation Debiasing Approach for Fair Speech Emotion Recognition Yun-Shao Tsai, Yi-Cheng Lin, Huang-Cheng Chou, Hung-yi Lee IEEE ASRU 2025 DOI
Co EMO-Reasoning: Benchmarking Emotional Reasoning Capabilities in Spoken Dialogue Systems Jingwen Liu, Kan Jen Cheng, Jiachen Lian, Akshay Anand, Rishi Jain, Faith Qiao, Robin Netzorg, Huang-Cheng Chou, Tingle Li, Guan-Ting Lin, Gopala Anumanchipalli IEEE ASRU 2025 DOI
Co Meta-PerSER: Few-Shot Listener Personalized Speech Emotion Recognition via Meta-learning Shi-Xin Fang, Liang-Yeh Shen, Yi-Cheng Lin, Huang-Cheng Chou, Hung-yi Lee INTERSPEECH 2025 DOI · Code
Co Improving Speech Emotion Recognition in Under-Resourced Languages via Speech-to-Speech Translation with Bootstrapping Data Selection Hsi-Che Lin, Yi-Cheng Lin, Huang-Cheng Chou, Hung-yi Lee ICASSP 2025 DOI
Co Emo-bias: A Large Scale Evaluation of Social Bias on Speech Emotion Recognition Yi-Cheng Lin, Haibin Wu, Huang-Cheng Chou, Chi-Chun Lee, Hung-yi Lee INTERSPEECH 2024 DOI
Co EMO-Codec: An In-Depth Look at Emotion Preservation Capacity of Legacy and Neural Codec Models with Subjective and Objective Evaluations Wenze Ren, Yi-Cheng Lin, Huang-Cheng Chou, Haibin Wu, Yi-Chiao Wu, Chi-Chun Lee, Hung-yi Lee, Hsin-Min Wang, Yu Tsao APSIPA ASC 2024 DOI

Mentored

Mentored VoxEmo: A Reproducible Toolkit for Speech Emotion Recognition with Speech LLMs Hezhao Zhang, Huang-Cheng Chou, Shrikanth Narayanan, Thomas Hain IEEE Transactions on Affective Computing (under review); arXiv:2603.08936 arXiv
Mentored Layer-wise Task Vector Merging: Leveraging ASR and SER Task Vectors for Enhanced Speech Emotion Representation Chia-Yu Lee, Huang-Cheng Chou, Tzu-Quan Lin, Yuanchao Li, Ya-Tse Wu, Shrikanth Narayanan, Chi-Chun Lee INTERSPEECH 2026; arXiv:2603.25041 (AdaLTM) arXiv
Mentored Speaker-Aware Temporal Aggregation Strategies on Segment Representations for Depression Detection in Dyadic Interaction: A Benchmark Study Anisha Pattanayak, Huang-Cheng Chou, Shrikanth Narayanan, Sudarsana Reddy Kadiri arXiv:2607.02904, 2026 arXiv
Mentored Layer-wise Cross-Lingual Depression Detection from Speech: Analysis with Contrastive Alignment Anisha Pattanayak, Hanie Kang, Huang-Cheng Chou, Shrikanth Narayanan, Sudarsana Reddy Kadiri arXiv:2607.02920, 2026 arXiv
Mentored Can Conversational Temporal Dynamics Improve Depression Detection in Dyads? A Preliminary Investigation in Multi-Modality Perspectives Hanie Kang, Huang-Cheng Chou, Sudarsana Reddy Kadiri, Shrikanth Narayanan arXiv:2607.03744, 2026 arXiv
Mentored Speaker Identity in Non-Verbal Vocalizations: Conditional Distillation and Mixture of Experts Approach Tzu-Chieh Wei, Yi-Cheng Lin, Huang-Cheng Chou, Kuan-Yu Chen, Hsin-Yen Sung, Shrikanth Narayanan, Hung-yi Lee INTERSPEECH 2026; arXiv:2606.21215 arXiv
Mentored AMECxSV: Adaptive Metadata-Driven Embedding-Fusion Calibration for X-Lingual Speaker Verification Xin Wei, Shi He, Yihe Yuan, Huang-Cheng Chou, Sudarsana Reddy Kadiri, Shrikanth Narayanan IEEE SLT 2026 (submitted); arXiv:2607.16532 arXiv

Contact

Currently seeking full-time roles. Open to conversations on speech AI, voice assistants, and research collaboration.

huangchengchou@gmail.com

Home PDF GitHub LinkedIn Scholar SAIL Lab MSP Lab BIIC Lab SPML Lab