Vipul Arora

About

My research interests include probabilistic machine learning and its applications to audio analysis, speech recognition, and computational Physics. I received my B. Tech. and PhD degrees in Electrical Engineering from the Indian Institute of Technology (IIT) Kanpur, India. I did a postdoc at Oxford University (UK), and then, worked at Amazon Alexa in Boston (USA). I have held visiting researcher positions at Surrey University, TIFR Mumbai, and TU Berlin. I am a senior member of IEEE and ISMIR.

Employment

• KU Leuven Tenure track lecturer
  2025 - Present
• Indian Institute of Technology Kanpur Associate Professor
  2022 - Present
• Indian Institute of Technology Kanpur Assistant Professor
  2018 - 2021
• Amazon Alexa Research Scientist
  2017 - 2018
• University of Oxford Postdoc Research Associate
  2015 - 2017
• KU Leuven Association

Education

• Indian Institute of Technology Kanpur Ph.D.
  2009 - 2014
• Indian Institute of Technology Kanpur B.Tech.
  2005 - 2009

Projects & Funding

Projects & funding information is unavailable.

Publications (71)

• CodecSep: Prompt-Driven Universal Sound Separation on Neural Audio Codec Latents
  ArXiv 2026
  +Save
• Automatic Detection and Analysis of Singing Mistakes for Music Learning by Imitation
  IEEE Transactions on Audio, Speech and Language Processing 2026 DOI: 10.1109/TASLPRO.2026.3682047
  +Save
• Recognizing Ornaments in Vocal Indian Art Music With Active Annotation
  IEEE Transactions on Audio, Speech and Language Processing 2026 DOI: 10.1109/TASLPRO.2025.3639738
  +Save
• Learning to Discover: A Generalized Framework for Raga Identification without Forgetting
  2026 NATIONAL CONFERENCE ON COMMUNICATIONS, NCC 2026 DOI: 10.1109/NCC68160.2026.11478900
  +Save
• Optimizing Query-By-Example Spoken Term Detection With Audio-to-Token Sequence Clustering and Query-Guided Retrieval
  IEEE Transactions on Audio, Speech and Language Processing 2026 DOI: 10.1109/TASLPRO.2026.3698014
  +Save
• Confidence-Enhanced Models for Indian Art Music Analysis
  2025 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING WORKSHOPS, ICASSPW 2025 DOI: 10.1109/ICASSPW65056.2025.11011163
  +Save
• Meta-Learning-Based Percussion Transcription and $T\bar{a}la$ Identification From Low-Resource Audio
  IEEE Transactions on Audio, Speech and Language Processing 2025 DOI: 10.1109/TASLPRO.2025.3581091
  +Save
• Language-Agnostic Speech Tokenizer for Spoken Term Detection with Efficient Retrieval
  Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2025 DOI: 10.21437/Interspeech.2025-2722
  +Save
• H-QuEST: Accelerating Query-by-Example Spoken Term Detection with Hierarchical Indexing
  Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2025 DOI: 10.21437/Interspeech.2025-2631
  +Save
• Explainable Deep Learning Analysis for Raga Identification in Indian Art Music
  IEEE Transactions on Audio, Speech and Language Processing 2025 DOI: 10.1109/TASLPRO.2025.3574839
  +Save