Samik Sadhu

According to our database, Samik Sadhu authored at least 13 papers between 2017 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2023

Self-supervised Learning with Speech Modulation Dropout.

Samik Sadhu, Hynek Hermansky

CoRR, 2023

Stabilized training of joint energy-based models and their practical applications.

Martin Sustek, Samik Sadhu, Lukás Burget, Hynek Hermansky, Jesús Villalba, Laureano Moro-Velázquez, Najim Dehak

CoRR, 2023

Importance of Different Temporal Modulations of Speech: a Tale of two Perspectives.

Samik Sadhu, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2023

2022

Blind Signal Dereverberation for Machine Speech Recognition.

Samik Sadhu, Hynek Hermansky

CoRR, 2022

Dealing with Unknowns in Continual Learning for End-to-end Automatic Speech Recognition.

Martin Sustek, Samik Sadhu, Hynek Hermansky

Proceedings of the Interspeech 2022, 2022

Complex Frequency Domain Linear Prediction: A Tool to Compute Modulation Spectrum of Speech.

Samik Sadhu, Hynek Hermansky

Proceedings of the Interspeech 2022, 2022

2021

wav2vec-C: A Self-Supervised Model for Speech Representation Learning.

Samik Sadhu, Di He, Che-Wei Huang, Sri Harish Mallidi, Minhua Wu, Ariya Rastrow, Andreas Stolcke, Jasha Droppo, Roland Maas

Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

Radically Old Way of Computing Spectra: Applications in End-to-End ASR.

Samik Sadhu, Hynek Hermansky

Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

2020

Continual Learning in Automatic Speech Recognition.

Samik Sadhu, Hynek Hermansky

Proceedings of the Interspeech 2020, 2020

2019

Exploring Methods for the Automatic Detection of Errors in Manual Transcription.

Xiaofei Wang, Jinyi Yang, Ruizhi Li, Samik Sadhu, Hynek Hermansky

Proceedings of the Interspeech 2019, 2019

Modulation Vectors as Robust Feature Representation for ASR in Domain Mismatched Conditions.

Samik Sadhu, Hynek Hermansky

Proceedings of the Interspeech 2019, 2019

M-vectors: Sub-band Based Energy Modulation Features for Multi-stream Automatic Speech Recognition.

Samik Sadhu, Ruizhi Li, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2019

2017

Low resource point process models for keyword spotting using unsupervised online learning.

Samik Sadhu, Prasanta Kumar Ghosh

Proceedings of the 25th European Signal Processing Conference, 2017