Berrak Sisman

Home / People / Faculty / Berrak Sisman
Go back to faculty list

Assistant Professor

Email: 
Website: https://sites.google.com/view/sislab
Office #: 1.702-03
Pillar / Cluster: Information Systems Technology and Design
Research Areas:Artificial and Augmented Intelligence, Interactive Computing, Data Science

Announcement (Job Opening):

  • I am currently hiring multiple Research Fellows to join my team at SUTD. If you’re interested, please apply. You’ll be working with researchers and students to advance machine learning research for speech synthesis and recognition.
  • I have positions at SUTD SIS Lab for undergraduate and graduate student assistants. Feel free to approach me via email.
    • You’ll implement machine learning algorithms for speech synthesis, speech recognition, voice cloning, accent, and emotion manipulation/generation.

Biography

Dr. Berrak Sisman is a tenure-track Assistant Professor at the Singapore University of Technology and Design (SUTD).  She is also an Affiliated Researcher at Human Language Technology Lab at the National University of Singapore, where she serves as the team leader. She received a Ph.D. degree in Electrical and Computer Engineering from the National University of Singapore, Singapore, in 2020.  Prior to joining SUTD, she was a Postdoctoral Research Fellow with the National University of Singapore, and a Visiting Researcher with Columbia University, New York, United States. During her Ph.D., she was a Visiting Scholar with The Centre for Speech Technology Research (CSTR), the University of Edinburgh in 2019. She was also attached to RIKEN Advanced Intelligence Project, Japan in 2018.

Dr. Berrak Sisman has published in leading journals and conferences, including IEEE/ACM Transactions on Audio, Speech and Language Processing, Neural Networks, IEEE Signal Processing Letters, ASRU, INTERSPEECH, and ICASSP. She is currently an Associate TC Member of IEEE SLTC and serves as a reviewer at IEEE Signal Processing Letters,  IEEE/ACM Transactions on Audio, Speech, and Language Processing, ICASSP, and INTERSPEECH.

Research Team: Speech & Intelligent Systems (SIS) Lab

At SUTD, Asst. Prof. Berrak Sisman and her team focus on an interdisciplinary study that involves computational linguistics, speech information processing, and deep learning methodology. The SIS Lab develops cutting-edge neural models for speech information processing. Click here to learn more about SUTD SIS Lab.

Education

  • Ph.D. in Electrical and Computer Engineering, National University of Singapore (Jan 2016 — Jan 2020)
    Supervisors: Prof. Haizhou Li, Prof. Tan Kay Chen
  • Ph.D. (Exchange), The University of Edinburgh, Scotland (2019)
    Supervisor: Prof. Simon King
  • Ph.D. (Exchange), RIKEN Center for Advanced Intelligence Project & Nara Institute of Science and Technology, Japan (2018)
    Supervisor: Prof. Satoshi Nakamura

Professional Service

  • Elected Member, IEEE Speech and Language Processing Technical Committee (SLTC) (Jan 2022 – Dec 2024)
  • Area Chair (Speech Synthesis and Spoken Language Generation), INTERSPEECH 2022
  • Publication Chair, ICASSP 2022
  • General Coordinator, ISCA Postdoc & Early Career Researcher Advisory Committee (PECRAC) (2021 – ongoing)
  • Area Chair (Speech Synthesis and Spoken Language Generation), INTERSPEECH 2021 
  • Co-chair, Workshop for Young Female Researchers in Speech Science & Technology (YFRSW) @ INTERSPEECH 2021
  • Local Chair, SIGDIAL 2021
  • Chair, Young Female Researchers Mentoring, IEEE ASRU2019
  • General Coordinator, ISCA Student Advisory Committee (2017 – 2019)
  • Local Arrangement Co-chair, IEEE Automatic Speech Recognition and Understanding Workshop, 2019
  • Chair, Doctoral Consortium, Students Meet Experts, and Open Doors events of INTERSPEECH 2018, India
  • Chair, Doctoral Consortium, Students Meet Experts, and Mentoring events of INTERSPEECH 2019, Austria

Selected Publications

  • B Sisman, J Yamagishi, S King, H Li, ‘An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learning’ IEEE/ACM Transactions on Audio, Speech and Language Processing, 2020.
  • B. Sisman, M. Zhang, H.Li, ‘Group Sparse Representation with WaveNet Vocoder Adaptation for Spectrum and Prosody Conversion’  IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2019.
  • R Liu, B Sisman, Y Lin, H Li ‘FastTalker: A Neural Text-to-Speech Architecture with Shallow and Group Autoregression’ Neural Networks, 2021.
  • R Liu, B Sisman, G Gao, H Li, ‘Expressive TTS Training with Frame and Style Reconstruction Loss’ IEEE/ACM Transactions on Audio, Speech and Language Processing, 2021.
  • R Liu, B Sisman, F Bao, G Gao, H Li  ‘Exploiting Morphological and Phonological Features to Improve Prosodic Phrasing for Mongolian Speech Synthesis’, IEEE/ACM Transactions on Audio, Speech and Language Processing, November 2020.
  • B. Sisman, M. Zhang, M. Dong, H. Li ‘On the Study of Generative Adversarial Networks for Cross-lingual Voice Conversion’ IEEE ASRU 2019.
  • A. Tjandra, B. Sisman, M. Zhang, S. Sakriani, H. Li, S. Nakamura, ‘VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019’ INTERSPEECH 2019.
  • B. Sisman, H. Li ‘Generative Adversarial Networks for Singing Voice Conversion with and without parallel data’ published in Speaker Odyssey 2020, Tokyo, Japan
  • B. Sisman, M. Zhang, H. Li, ‘A Voice Conversion Framework with Tandem Feature Sparse Representation and Speaker-Adapted WaveNet Vocoder’, INTERSPEECH 2018
  • B. Sisman, H. Li, ‘Wavelet Analysis of Speaker Dependent and Independent Prosody for Voice Conversion’, INTERSPEECH 2018
  • B. Sisman, M. Zhang, S. Sakriani, H. Li, S. Nakamura, ‘Adaptive WaveNet Vocoder for Residual Compensation in GAN-based Voice Conversion’, IEEE SLT 2018, Greece.
  • B. Sisman, H. Li, K. C. Tan ‘Sparse Representation of Phonetic Features for Voice Conversion with and without Parallel Data’, IEEE ASRU 2017, Okinawa, Japan
  • R Liu, B Sisman, F Bao, G Gao, H Li  ‘Modeling Prosodic Phrasing with Multi-Task Learning in Tacotron-based TTS’, IEEE Signal Processing Letters, September 2020.
  • M. Zhang, B. Sisman, L. Zhao, H. Li ‘DeepConversion: Voice conversion with limited parallel training data’ Speech Communication, 2020.
  • K Zhou, B Sisman, R Liu, H Li ‘Seen and unseen emotional style transfer for voice conversion with a new emotional speech dataset’ IEEE ICASSP 2021 – International Conference on Acoustics, Speech, and Signal Processing 2021.
  • R Liu, B Sisman, H Li ‘GraphSpeech: Syntax-Aware Graph Attention Network for Neural Speech Synthesis’ IEEE ICASSP 2021 – International Conference on Acoustics, Speech, and Signal Processing 2021.
  • K Zhou, B Sisman, H Li ‘VAW-GAN for Disentanglement and Recomposition of Emotional Elements in Speech’ IEEE Spoken Language Technology Workshop (SLT 2021).
  • R. Liu, B. Sisman, J Li, F Bao, G Gao, H Li, ‘Teacher-Student Training for Robust Tacotron-based TTS’ IEEE ICASSP 2020 – International Conference on Acoustics, Speech, and Signal Processing 2020.
  • Kun, B. Sisman, H. Li ‘Transforming Spectrum and Prosody for Emotional Voice Conversion with Non-Parallel Training Data’ Speaker Odyssey 2020, Tokyo, Japan

For the full list of publications, please check here.

Positions

We have the following positions available at SUTD Speech & Intelligent Systems (SIS) Lab:

  • SUTD undergraduate students: Student assistant positions are available. Please send an email to Prof. Berrak Sisman.
  • Master students: For further information, please send an email to Prof. Berrak Sisman.
  • Fully-funded Ph.D. positions: If you want to pursue a fully-funded Ph.D. at SIS Lab, please apply for SUTD PhD program.
  • Postdoc positions: Please apply by sending your CV and 1-2 representative publications. Candidates should hold a Ph.D. degree and show evidence of a strong publication record and/or project experience in speech information processing, speech synthesis, TTS, voice conversion, ASR, and machine learning.
Go back to faculty list