Got selected for the prestigious IUSSTF-Viterbi India Scholars program to spend the summers(2018) as an undergraduate researcher at the Signal Analysis and Interpretation Laboratory(SAIL) of the University of Southern California, under the guidance of Prof. Shrikanth Narayanan.
The title of my project was: 'AN I-VECTOR BASED NON-NEGATIVE MATRIX FACTORIZATION APPROACH TOWARDS NOISE ROBUST AUTOMATIC SPEECH RECOGNITION'. The code for the same is available at - https://github.com/KunalDhawan/noise-robust-acoustic-features
Motivation:
Given the rise of consumer-centric applications like voice interaction with mobile devices and home entertainment systems, it is imperative for Automatic Speech Recognition systems to be robust to the full range of real-world noise and other acoustic distorting conditions. Hence the goal is to obtain features that can efficiently model what a person has spoken, irrespective of what the recording conditions are.
Shared below is a brief presentation explaining the basic building blocks of this project: Non-negative matrix factorization(NMF) and the total variability approach
The title of my project was: 'AN I-VECTOR BASED NON-NEGATIVE MATRIX FACTORIZATION APPROACH TOWARDS NOISE ROBUST AUTOMATIC SPEECH RECOGNITION'. The code for the same is available at - https://github.com/KunalDhawan/noise-robust-acoustic-features
Motivation:
Given the rise of consumer-centric applications like voice interaction with mobile devices and home entertainment systems, it is imperative for Automatic Speech Recognition systems to be robust to the full range of real-world noise and other acoustic distorting conditions. Hence the goal is to obtain features that can efficiently model what a person has spoken, irrespective of what the recording conditions are.
Shared below is a brief presentation explaining the basic building blocks of this project: Non-negative matrix factorization(NMF) and the total variability approach
Link to arxiv pre-print of the above work can be found at - https://arxiv.org/pdf/1907.06859.pdf
A poster depicting the work done in brief can be found below-