Speaker: Prachi Singh
Affiliation: PhD, Dept. of EE, IISc Bangalore
Speaker: Dr. Srikanth Raj Chetupalli
Affiliation: Post Doc., IISc Bangalore
YouTube Link: https://youtu.be/XKFjbHXMy2U
Talk Timings: April 30, 2021 (Friday) 3.55 PM – 4.55 PM IST
Abstract:
Speech processing is the study of speech signals and the processing methods of signals. In the age of deep learning where we have access to huge amount of data, field of speech processing has gained a huge momentum in both research and applications. Speech analytics are widely used to improve customer satisfaction and voice assistants have now become mainstream. In this talk, we would like to discuss two sub-areas of speech processing and the interplay between them. Speech recognition and speaker diarization both play an important role in various speech applications like voice search, meeting transcription, clinical diagnosis etc. The talk will highlight various approaches and challenges of these fields in detail.
Bio (Prachi Singh):
Prachi Singh is a Ph.D student at Learning and Extraction of Acoustic Patterns (LEAP) lab, Electrical Engineering, Indian Institute of Science, Bangalore. In the past, she has worked in Fiat Chrysler Automobiles, Chennai, India from 2015 to 2017. She obtained her Bachelor of Technology in Electronics and Telecommunication from College of Engineering, Pune in 2015. She is a student member of IEEE and ISCA. Her research interests include speaker diarization, speaker verification, self-supervised learning and graph clustering.
Bio (Dr. Srikanth Raj Chetupalli):
Dr. Srikanth Raj Chetupalli is a post doctoral fellow at Learning and Extraction of Acoustic Patterns (LEAP) lab, Electrical Engineering, Indian Institute of Science, Bangalore. He obtained his PhD degree from IISc in 2020, Masters in Signal processing from IISc in 2011, and Bachelors from Jawaharlal Nehru Technological University, Hyderabad. He was a TCS research fellow from 2015-2019. He is a member of IEEE and ISCA. His research interests include Multi-channel speech processing, microphone arrays, speech recognition and diarization, speech dereverberation, and spatial audio