Short Bio
I am a Senior Applied Scientist in the Amazon Web Services (AWS) AI - speech science team, working on a wide variety of topics including emotion/sentiment recognition, speech recognition, conversational AI, spoken language identification, angry raised voice detection, and multimodal toxicity detection (trust and safety). Before, I was a Postdoctoral Research Fellow at UNSW Sydney (with Professor Julien Epps) and a research scientist at Sonde Health, working on automatic speech-based assessment of mental state (primarily depression) via mobile devices.
Check out my other profiles at Linkedin, ResearchGate, and Google Scholar.
Contact Email: zhaocheng.huang(at)gmail(dot)com
Education
2018 Ph.D. in Electrical Engineering (Machine Learning & Speech Processing), UNSW Sydney, Australia.
2013 B.Sc. (Eng) in Electronic Engineering (Underwater Acoustics), Harbin Engineering University, China.
Work Experience
12/2023 - now Senior Applied Scientist, AWS AI
01/2021 - 11/2023 Applied Scientist, AWS AI
01/2021 - 12/2021 Visiting Fellow, UNSW Sydney, Australia
01/2018 - 12/2020 Postdoctoral Research Fellow, UNSW Sydney, Australia && Research Scientist, Sonde Health, Inc., Boston, USA
Teaching Experience
S1, 2020 Lecturer-in-charge, ELEC 3104 Digital Signal Processing, School of EE&T, UNSW Sydney
Class size=76, 100% teaching satisfaction
The COVID-19 lockdown happened in the middle of the course and we switched it to pure online mode overnight!
2015 - 2017 Teaching Assistant, Taught many Electrical Engineering undergrate and postgraduate courses, UNSW Sydney
Research Interests
Speech Processing
Statistical Machine Learning & Deep Learning
Speech Recognition & Conversational AI
Affective Computing (esp. emotion recognition)
Digital Medicine & AI for Healthcare (esp. depression detection)
Responsible AI: Detecting toxcity from audio and/or text
Refereed Journals (5)
Brian Stasak, Zhaocheng Huang, Sabah Razavi, Dale Joachim, Julien Epps. "Automatic Detection of COVID-19 Based on Short Duration Acoustic Smartphone Speech Analysis", Journal of Healthcare Informatics Research, vol. 5, pp. 201 - 217, 2021. (IF = 2.87)
Zhaocheng Huang, Julien Epps, Dale Joachim, and Vidhyasaharan Sethu. "Natural Language Processing Methods for Acoustic and Landmark Event-based Features in Speech-based Depression Detection", IEEE Journals of Selected Topics in Signal Processing, vol. 14, pp. 435 - 448, 2020. (IF = 6.688)
Zhaocheng Huang, Julien Epps, and Dale Joachim. "Investigation of Speech Landmark Patterns for Depression Detection", IEEE Transactions on Affective Computing, 2019. (IF = 7.512). This work was featured regarding depression detection in this nature article.
Zhaocheng Huang, and Julien Epps. "An Investigation of Partition-based and Phonetically-aware Acoustic Features for Continuous Emotion Prediction from Speech", IEEE Transactions on Affective Computing, vol. 11, pp. 653 - 668, 2020. (IF = 7.512)
Zhaocheng Huang, and Julien Epps. "Prediction of Emotion Change from Speech", Frontiers in ICT, no. 11, vol. 5, 2018.
Refereed Conference Papers (18)
Juan Pablo Zuluaga-Gomez, Zhaocheng Huang*, Xing Niu*, Rohit Paturi, Sundararajan Srinavasan, Prashant Mathur, Brian Thompson, Marcello Federico, "End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Transalation", in the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023), Singapore. [slides] [arvix] [code]
Sundararajan Srinivasan, Zhaocheng Huang, Katrin Kirchhoff, "Representation Learning through Cross-modal Conditional Teacher-student Training for Speech Emotion Recognition", ICASSP '22, Singapore. [oral presentation] [slides] [arvix]
Brian Stasak, Zhaocheng Huang, Julien Epps, and Dale Joachim, "Depression Classification Using n-Gram Speech Errors from Manual and Automatic Stroop Color Test Transcripts", 2021 IEEE Engineering in Medicine and Biology Conference (EMBC' 21).
Brian Stasak, Zhaocheng Huang, Dale Joachim, and Julien Epps, "Automatic Elicitation Compliance for Short-Duration Speech-based Depression Detection", ICASSP '21, Toronto, Canada, pp. 7283 - 7287, 2021.
Zhaocheng Huang, Julien Epps, Dale Joachim, Brian Stasak, James. R. Williamson, and Thomas. F. Quatieri, "Domain Adaptation for Enhancing Speech-based Depression Detection in Natural Environmental Conditions Using Dilated CNNs", INTERSPEECH '20, Shanghai, China, pp. 4561-4565, 2020.
Sadari Jayawardena, Julien Epps, Zhaocheng Huang, "How Ordinal Are Your Data?", INTERSPEECH '20, Shanghai, China, pp. 1853-1857, 2020.
Zhaocheng Huang, Julien Epps, Dale Joachim, "Exploiting Vocal Tract Coordination using Dilated CNNs for Depression Detection in Natrualistic Environements." ICASSP '20, Barcelona, Spain, pp. 6549–6553, 2020. [oral presentation][slides]
Zhaocheng Huang, Julien Epps, Dale Joachim, "Speech Landmark Bigrams for Depression Detection from Naturalistic Smartphone Speech.", ICASSP '19, Brighton, UK, pp. 5856–5860, 2019. [oral presentation][slides]
Zhaocheng Huang, Julien Epps, Dale Joachim, Michael. C. Chen, "Depression Detection from Short Utterances via Diverse Smartphones in Natural Environmental Conditions." INTERSPEECH '18, Hyderabad, India, pp. 3393–3397, 2018. [poster]
Ting Dang, Brian Stasak, Zhaocheng Huang, Sadari Jayawardena, Mia Atcheson, Munawar Hayat, Phu Le, Vidhyasaharan Sethu, Roland Goecke, and Julien Epps, “Investigating Word Affect Features and Fusion of Probabilistic Predictions Incorporating Uncertainty in AVEC 2017.” In Proceedings of the 7th International Workshop on Audio/Visual Emotion Challenge (AVEC ’17). ACM, 2017, Mountain View, CA USA, pp. 27–35, 2017. [pdf] [oral presentation]
Zhaocheng Huang, and Julien Epps. "An Investigation of Emotion Dynamics and Kalman Filtering for Speech-based Emotion Prediction", INTERSPEECH '17, Stockholm, Sweden, pp. 3301–3305, 2017. [pdf] [poster]
Zhaocheng Huang, and Julien Epps. "A PLLR and Multi-Stage Staircase Regression Framework for Speech-based Emotion Prediction" 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '17), New Orleans, US, pp. 5145–5149, 2017. [pdf] [poster]
Zhaocheng Huang, and Julien Epps. "Time to Embrace Emotion Change: Selecting Emotionally Salient Segments for Speech-based Emotion Prediction" The 16th International Conference on Speech Science and Technology (SST '16), Sydney, Australia, pp. 281–284, 2016. [pdf] [oral presentation] [slides]
Zhaocheng Huang, Brian Stasak, Ting Dang, Kalani Wataraka Gamage, Phu Le, Vidhyasaharan Sethu, Julien Epps. "Staircase Regression in OA RVM, Data Selection and Gender Dependency in AVEC 2016" In Proceedings of the 6th International Workshop on Audio/Visual Emotion Challenge (AVEC '16), ACM Multimedia, pp. 19–26, 2016. [pdf] [oral presentation] [slides]
Zhaocheng Huang, and Julien Epps. "Detecting the instant of emotion change from speech using a martingale framework" 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '16), pp. 5195-5199, 2016. [pdf] [oral presentation] [slides]
Zhaocheng Huang, Ting Dang, Nicholas Cummins, Brian Stasak, Phu Le, Vidhyasaharan Sethu, and Julien Epps. "An Investigation of Annotation Delay Compensation and Output-Associative Fusion for Multimodal Continuous Emotion Prediction." In Proceedings of the 5th International Workshop on Audio/Visual Emotion Challenge (AV+EC '15), ACM Multimedia, pp. 41-48, 2015. [pdf] [oral presentation]
Zhaocheng Huang. "An investigation of emotion changes from speech." 2015 International Conference on Affective Computing and Intelligent Interaction (ACII '15), pp. 733-736, 2015. [pdf] [oral presentation]
Zhaocheng Huang, Julien Epps, and Eliathamby Ambikairajah. "An Investigation of Emotion Change Detection from Speech" The 16th Annual Conference of the International Speech Communication Association (INTERSPEECH '15), pp. 5195-5199, 2015. [pdf] [poster]
Awards & Grants
UNSW PhD Scholarship (2014 - 2017)
National ICT Australia Research Project Award (2014 - 2017)
5 Travel Grants: ICASSP 2016 & 2019 (Competetive), INTERSPEECH 2015 & 2017, ACII 2015
3 Competitions: AVEC 2017 (4th prize for both depression and emotion challenges), AV+EC 2015 (Equal 2nd prize)
National Texas Instrument C2000 and MCU Design Contest, Xi'an, China (2012), 1st prize (undergrad).
Professional Activities
Professional Societies
Member, IEEE Signal Processing Society (SPS), International Speech Communication Association (ISCA)
Programme Committee Member:
Refereeing - Journals (Selected):
IEEE Transactions on Affective Computing (2016, 2019 - 2024)
IEEE Transactions on Audio, Speech and Language Processing (2019, 2022 - 2023)
Computer Speech and Language (2018 - 2023), outstanding reviewer
Speech Communication (2020 - 2022)
JASA Express Letters (2022 - 2023)
IEEE Open Journal of Signal Processing (2023-2024)
IEEE Journal of Biomedical and Health Informatics (2023)
Frontiers in Psychiatry (2022)
IEEE Signal Processing Magazine (2021)
IEEE Transactions on Emerging Topics in Computational Intelligence (2019)
Journal of Selected Topics in Signal Processing (2018, 2024)
Image and Vision Computing (2016)
Refereeing - Conferences (Selected):
IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP 2023 - 2024), Int. Conf. on Affective Computing and Intelligent Interaction (ACII 2019 - 2022), ACM Multimedia (2019), AVEC (2019), IEEE Eng. in Medicine and Biology Conf. (EMBC 2020), IEEE Spoken Language Technology Workshop (SLT 2020), Int. Conf. on Multimodal Interaction (ICMI 2021)
Volunteer
Amazon Day 1 Science Mentor - 2022
Conference web chair, SST' 18, Coogee, Sydney, Australia
INTERSPEECH 2015