Bhusan Chettri

About

Bhusan Chettri is an AI researcher working on machine learning and AI for sound and speech with a strong focus on explainable AI (understanding how a model forms its decision). Bhusan Chettri (Member, IEEE) received the M.Sc. degree in speech and language processing from the University of Sheffield in 2014. Then he worked as a Research Assistant with the Speech and Hearing Research group, Sheffield University for two years. He earned his undergraduate and post-graduate degrees in Computer Science from Sikkim Manipal University, India in 2005 and 2008 respectively. Before moving to Sheffield for MSc degree he also earned an MBA degree in Computer Systems from SMUDE, India. He received the Ph.D. degree in Electronic Engineering from Queen Mary University of London (QMUL) in 2020. During May to October 2019, he was a visiting researcher with the Computational Speech research group, University of Eastern Finland to work on Voice Anti-Spoofing project (NOTCH) with Professor Tomi Kinnunen. While doing his PhD at QMUL he served as a lab demonstrator during his first year and later got opportunity to teach Data Analytics to the MSc students as a part-time Lecturer. After his PhD completion he became a full time Lecturer in Data Analytics with the School of Electronic Engineering and Computer Science, Queen Mary University of London (QMUL), U.K. Between May to December 2020, he worked as a Postdoctoral Researcher on the speaker anti-spoofing NOTCH project. His main research focuses on machine learning and its applications to speaker recognition, spoofing and countermeasures for robust speaker recognition. He is also interested in opening black-boxes towards understanding how a model forms a particular decision. Interpretable machine learning, explainable machine learning, understanding biases in training data and how they influence predictions – are his current research interests.

Employment

• Borac Solutions AI Researcher
  2021 - Present
• Queen Mary, University of London Lecturer in Data Analytics
  2020 - 2021
• University of Eastern Finland Post-doctoral researcher
  2020 - 2021
• University of Eastern Finland Project Researcher on NOTCH project
  2019 - 2019
• Queen Mary University of London Lecturer in Data Analytics (PART-TIME)
  2018 - 2020
• University of Sheffield Research Assistant / Research Software Engineer
  2014 - 2016
• Sikkim Manipal Institute of Technology Associate Professor
  2010 - 2013
• Sikkim Manipal Institute of Technology Assistant Professor
  2006 - 2010

Education

• Queen Mary, University of London PhD
  2016 - 2020
• University of Sheffield MSc in Speech and Language Processing
  2013 - 2014
• Sikkim Manipal Institute of Technology MBA
  2008 - 2010

Projects & Funding

Projects & funding information is unavailable.

Publications (14)

• EXPLAINING THE PREDICTIONS OF DEEP VOICE SPOOFING DETECTOR
  To be submitted to TASLP or CSL 2023
  +Save
• THE CLEVER HANS EFFECT IN VOICE SPOOFING DETECTION
  IEEE Spoken Language Technology, 2022 2022 DOI: 10.1109/SLT54892.2023.10022624
  +Save
• Data Quality as Predictor of Voice Anti-Spoofing Generalization
  Interspeech 2021 2021 DOI: 10.21437/interspeech.2021-1180
  +Save
• Subband Modeling for Spoofing Detection in Automatic Speaker Verification
  The Speaker and Language Recognition Workshop (Odyssey 2020) 2020 DOI: 10.21437/odyssey.2020-48
  +Save
• Deep generative variational autoencoding for replay spoof detection in automatic speaker verification
  Computer Speech & Language 2020 DOI: 10.1016/j.csl.2020.101092
  +Save
• Dataset Artefacts in Anti-Spoofing Systems: A Case Study on the ASVspoof 2017 Benchmark
  IEEE/ACM Transactions on Audio, Speech, and Language Processing 2020 DOI: 10.1109/TASLP.2020.3036777
  +Save
• Ensemble Models for Spoofing Detection in Automatic Speaker Verification
  Interspeech 2019 2019 DOI: 10.21437/interspeech.2019-2505
  +Save
• Analysing The Predictions Of a CNN-Based Replay Spoofing Detection System
  2018 IEEE Spoken Language Technology Workshop (SLT) 2018 DOI: 10.1109/slt.2018.8639666
  +Save
• ANALYSING REPLAY SPOOFING COUNTERMEASURE PERFORMANCE UNDER VARIED CONDITIONS
  2018 IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP) 2018 DOI: 10.1109/mlsp.2018.8516968
  +Save
• A Deeper Look at Gaussian Mixture Model Based Anti-Spoofing Systems
  2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2018 DOI: 10.1109/icassp.2018.8461467
  +Save