Heading Speech Information Processing Group
Associate Professor, Department of Electrical Engineering, IIT Hyderabad
Working on Speaker Recognition
Working on Speech Synthesis
Working on Speaker Recogntion
Working on Speech Enhancement
Speech Representation Learning
Working on Machine Translation
Working on Machine Translation
Working on Robot Audition
Keyword spotting, Speech recognition
Speech synthesis
Acoustic Event Detection
Automatic Speech Recognition
Speech Recognition & Keyword Spotting
Source Separation
Working on Keyword Spotting
Speech Recognition
Speaker Recognition
Speech Enhancement
Unsupervised Speech Signal to Symbol Transformation for Zero Resource Speech Processing (Chief Engineer, Samsung R&D Institute, Bangalore)
Automatic Gharana Recognition from Audio music recordings of Tabla Solo performances (PhD at IIT Madras, India)
Speech Source Separation using ICA in Constant Q Transform Domain (Qualcomm Hyderabad)
Single channel speech enhancement using Deep Neural Networks (Meeami Tech. Pvt. Ltd)
Unsupervised Spoken Term Discovery for Zero Resource Speech Processing (PhD at JHU, US)
Significance of Phase in Speech Analysis (Research fellow, Dept. of ECE, National University of Singapore)
HMM Based Text-to-Speech Synthesis for Telugu
Acoustic Segment Modeling using Spectral Clustering techniques (PhD at UCSC, US)
Keyword spotting from Low Resource Indian Languages (Mathworks Pvt. Ltd.)
Representation Learning for Spoken Term Detection (PhD at JHU, US)
Prosodically guided phonetic engine for searching speech databases in Indian languages (Meeami Tech. Pvt. Ltd.)
Prosody modifications for voice conversion (PhD at IISc Bangalore, India)