Pranay Dighe
Research Assistant
Speech & Audio Processing
IDIAP Research Institute
Switzerland
Biography
I'm Pranay Dighe, currently a Ph.D. student in Doctoral School of Electrical Engineering at École polytechnique fédérale de Lausanne (EPFL), Switzerland and research assistant in Speech & Audio Processing group at IDIAP Research Institute under the supervision of Prof. Hervé Bourlard. I received Bachelor's and Master's degree in Computer Science & Enggineering from Indian Institute of Technology Kanpur under the supervision of Prof. Harish Karnick (CSE, IITK) and Prof. Bhiksha Raj (LTI, CMU). I am currently working on enhancing deep neural networks (DNN) based automatic speech recognition (ASR) using Dictionary Learning and Sparse Coding techniques, with special focus on extraction of low-rank structures in DNN outputs.
Research Interest
Siri Speech,Parsimonious Hierarchical Automatic Speech Recognition, Handling Overlapping Speech During Speaker Diarization, Automated Analysis of Indian Classical Music
Publications
-
Luyet, P. Dighe, A. Asaei, H. Bourlard "Low-Rank Representation of Nearest Neighbor Posterior Probabilities to Enhance DNN Based Acoustic Modeling", in Interspeech, San Francisco, USA, 2016.
-
P. Dighe, A. Asaei and H. Bourlard “Sparse Modeling of Neural Network Posterior Probabilities for Exemplar-based Speech Recognitionâ€, in Speech Communication: Special Issue on Advances in Sparse Modeling and Low-rank Modeling for Speech Processing, 2015.
-
P. Dighe, A. Asaei, H. Bourlard "Low-rank and Sparse Soft Targets to Learn Better DNN Acoustic Models", in ICASSP 2017, New Orleans, USA.
