Samik Sadhu

Publication Activity (10 Years)

Years Active: 2017-2023
Publications (10 Years): 18

Top Topics

Temporal Ordering

Speech Recognition

Keyword Spotting

Top Venues

Publications

Samik Sadhu, Hynek Hermansky
Self-supervised Learning with Speech Modulation Dropout. CoRR (2023)
Martin Sustek, Samik Sadhu, Lukás Burget, Hynek Hermansky, Jesus Villalba, Laureano Moro-Velázquez, Najim Dehak
Stabilized training of joint energy-based models and their practical applications. CoRR (2023)
Samik Sadhu, Hynek Hermansky
Importance of Different Temporal Modulations of Speech: a Tale of two Perspectives. ICASSP (2023)
Samik Sadhu, Hynek Hermansky
Blind Signal Dereverberation for Machine Speech Recognition. CoRR (2022)
Samik Sadhu, Hynek Hermansky
Complex Frequency Domain Linear Prediction: A Tool to Compute Modulation Spectrum of Speech. INTERSPEECH (2022)
Martin Sustek, Samik Sadhu, Hynek Hermansky
Dealing with Unknowns in Continual Learning for End-to-end Automatic Speech Recognition. INTERSPEECH (2022)
Samik Sadhu, Hynek Hermansky
Importance of Different Temporal Modulations of Speech: A Tale of Two Perspectives. CoRR (2022)
Samik Sadhu, Hynek Hermansky
Complex Frequency Domain Linear Prediction: A Tool to Compute Modulation Spectrum of Speech. CoRR (2022)
Samik Sadhu, Hynek Hermansky
Radically Old Way of Computing Spectra: Applications in End-to-End ASR. CoRR (2021)
Samik Sadhu, Hynek Hermansky
Radically Old Way of Computing Spectra: Applications in End-to-End ASR. Interspeech (2021)
Samik Sadhu, Di He, Che-Wei Huang, Sri Harish Mallidi, Minhua Wu, Ariya Rastrow, Andreas Stolcke, Jasha Droppo, Roland Maas
Wav2vec-C: A Self-supervised Model for Speech Representation Learning. CoRR (2021)
Samik Sadhu, Di He, Che-Wei Huang, Sri Harish Mallidi, Minhua Wu, Ariya Rastrow, Andreas Stolcke, Jasha Droppo, Roland Maas
wav2vec-C: A Self-Supervised Model for Speech Representation Learning. Interspeech (2021)
Samik Sadhu, Hynek Hermansky
Continual Learning in Automatic Speech Recognition. INTERSPEECH (2020)
Samik Sadhu, Hynek Hermansky
Modulation Vectors as Robust Feature Representation for ASR in Domain Mismatched Conditions. INTERSPEECH (2019)
Xiaofei Wang, Jinyi Yang, Ruizhi Li, Samik Sadhu, Hynek Hermansky
Exploring Methods for the Automatic Detection of Errors in Manual Transcription. INTERSPEECH (2019)
Xiaofei Wang, Jinyi Yang, Ruizhi Li, Samik Sadhu, Hynek Hermansky
Exploring Methods for the Automatic Detection of Errors in Manual Transcription. CoRR (2019)
Samik Sadhu, Ruizhi Li, Hynek Hermansky
M-vectors: Sub-band Based Energy Modulation Features for Multi-stream Automatic Speech Recognition. ICASSP (2019)
Samik Sadhu, Prasanta Kumar Ghosh
Low resource point process models for keyword spotting using unsupervised online learning. EUSIPCO (2017)