Publications

For a complete list please refer to my Google Scholar profile

2026

• Text-to-Stage: Spatial Layouts from Long-form Narratives
  J. Hernandez, S. Saha, C. Whitehouse, S. Parekh, C. Murdock, Y. Li, W. O. Brimijoin, V. K. Ithapu, I. Ananthabhotla
  arXiv 2026
• Spatial-Magnifier: Spatial upsampling for multichannel speech enhancement
  D. Lee, A. Pandey, S. Parekh, D. Wong, J. Donley, B. Xu, J. Azcarreta
  arXiv 2026
• Unified Diffusion Refinement for Multi-Channel Speech Enhancement and Separation
  Z. Xu, A. Pandey, J. Azcarreta, Z. Ni, S. Parekh, B. Xu, R. R. Choudhury
  arXiv 2026
• Sound Event Detection with Boundary-Aware Optimization and Inference
  F. Schmid, C. I. Tang, S. Parekh, V. K. Ithapu, J. Azcarreta Ortiz, G. Ferroni, Y. Qian, A. Jasonas, C. Frateanu, C. Clark, G. Widmer, Ç. Bilen
  IEEE SPL 2026 (accepted)
• Conditional Flow Matching for Visually-Guided Acoustic Highlighting
  H. Malard, G. L. Lan, D. Wong, D. L. Alon, Y. C. Wu, S. Parekh
  arXiv 2026
• More Than A Shortcut: A Hyperbolic Approach To Early-Exit Networks
  S. Bhosale, C. Frateanu, C. Clark, A. Jasonas, C. Mitchell, X. Zhu, V. K. Ithapu, G. Ferroni, C. Bilen, S. Parekh
  ICASSP 2026
• ArrayDPS-Refine: Generative Refinement of Discriminative Multi-Channel Speech Enhancement
  Z. Xu, A. Pandey, J. Azcarreta, Z. Ni, S. Parekh, B. Xu
  ICASSP 2026
• Hair Noise Analysis and Mitigation for Smart Glasses Audio Captures
  S. Biswas, D. Wong, B. Islam, S. Parekh, V. Tourbabin
  ICASSP 2026

2025

• Learning to highlight audio by watching movies
  C. Huang, R. Gao, J. Tsang, J. Kurcius, C. Bilen, C. Xu, A. Kumar, S. Parekh
  CVPR 2025
• Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment
  J. Hong, S. Parekh, H. Chen, J. Donley, K. Tan, B. Xu, A. Kumar
  TMLR 2025

2024

• Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization
  J. Parekh, S. Parekh, P. Mozharovskyi, G. Richard, F. d’Alché-Buc
  IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024

2022

• Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF
  J. Parekh, S. Parekh, P. Mozharovskyi, F. d’Alché-Buc, G. Richard
  NeurIPS 2022

2021

• Emotion Transfer Using Vector-Valued Infinite Task Learning
  A. Lambert, S. Parekh, Z. Szabó, F. d’Alché-Buc
  CtrlGen Workshop, NeurIPS 2021

2019

• Weakly supervised representation learning for audio-visual scene analysis
  S. Parekh, S. Essid, A. Ozerov, N. Duong, P. Pérez, G. Richard
  IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2019
• Identify, locate and separate: Audio-visual object extraction in large video collections using weak supervision
  S. Parekh, A. Ozerov, S. Essid, N. Duong, P. Pérez, G. Richard
  WASPAA 2019
• Learning representations for robust audio-visual scene analysis
  S. Parekh
  Ph.D. Thesis, Université Paris-Saclay, 2019

2018

• Weakly supervised representation learning for unsynchronized audio-visual events
  S. Parekh, S. Essid, A. Ozerov, N. Duong, P. Pérez, G. Richard
  CVPR Workshop on Sight and Sound 2018
• Deep pairwise classification and ranking for predicting media interestingness
  J. Parekh, H. Tibrewal, S. Parekh
  ACM ICMR 2018

2017

• Guiding audio source separation by video object information
  S. Parekh, S. Essid, A. Ozerov, N. Duong, P. Pérez, G. Richard
  WASPAA 2017
• Motion informed audio source separation
  S. Parekh, S. Essid, A. Ozerov, N. Duong, P. Pérez, G. Richard
  ICASSP 2017
• Multiview approaches to event detection and scene analysis
  S. Essid, S. Parekh, N. Duong, R. Serizel, A. Ozerov, F. Antonacci, A. Sarti
  Computational Analysis of Sound Scenes and Events (Springer), 2017
• The IITB Predicting Media Interestingness System for MediaEval 2017
  J. Parekh, H. Tibrewal, S. Parekh
  MediaEval 2017

2016

• Improving audio retrieval through loudness profile categorization
  S. Parekh, F. Font, X. Serra
  IEEE ISM 2016
• Content-based video indexing and retrieval using corr-lda
  R. R. Iyer, S. Parekh, V. Mohandoss, A. Ramsurat, B. Raj, R. Singh
  arXiv 2016
• The MLPBOON Predicting Media Interestingness System for MediaEval 2016
  J. Parekh, S. Parekh
  MediaEval 2016

2015

• Improving Audio Retrieval through Content and Metadata Categorization
  S. Parekh
  Master’s Thesis, Universitat Pompeu Fabra, 2015

2014

• Nyquist filter design using POCS methods: Including constraints in design
  S. Parekh, P. Shah
  IEEE ISSPIT 2014

Filed Patents

• Weakly Supervised Learning for Audio-Visual Events, 2018.
  S. Parekh, S. Essid, A. Ozerov, N. Duong, P. Pérez, G. Richard
  EP3540634A1

• New approaches to motion informed audio source separation, 2017.
  S. Parekh, S. Essid, A. Ozerov, N. Duong, P. Pérez, G. Richard
  US15956021