I work on core algorithmic aspects of computer voice recognition, and artificial intelligence applied to voice forensics. My focus is on the development of technology for the automated discovery, measurement, representation and learning of the information encoded in voice signal for optimal voice intelligence. A consolidated description of my current research activities, along with my publications is now at the Center for Voice Intelligence and Security. I began working in the area of computer speech recognition and general audio processing in 1997. Until 2014, I worked on a wide range of topics, including algorithms that made speech processing systems completely generalizable (agnostic to language), algorithms that enabled automated discovery and learning of information from speech, algorithms that could process speech using minimal external (human-generated) knowledge etc. My goal was to enable greater automation, create more powerful search strategies and more scaleable learning algorithms for voice processing systems, and to find ways to make them work more accurately in high-noise and other kinds of complex acoustic environments.
In December 2014, I began building up the science of profiling humans from their voice. This involves the concurrent deduction of myriad human parameters from voice. Like the DNA and fingerprints, every human’s voice is unique. It carries more information than we realize (or can hear). It carries signatures of the speaker’s physical, physiological, medical, psychological, sociological, behavioral and environmental parameters, among other things. Profiling is based on quantitative discovery of information from the voice signal, guided by the intricacies of the physics and bio-mechanics of human voice production. Because it focuses on the voice signal, and not its semantic or pragmatic content, it is agnostic to language.
Currently my work includes the design of powerful AI systems to explore the depths of information in the human voice. Examples include systems for genetic discovery, systems for biomarker discovery and systems for other kinds of explorations into the human physical state and psyche, including emotions and personality, through the portal of voice.
In addition to my work on human profiling, I am working on creating core designs for general AI systems that are capable of universal speech and audio processing. The goal of this endeavor is to eventually build a system that is capable of all that our brain is capable of doing, in response to multisensory input from the world. This will require powerful computing. And then we will need to give it mobility. I have begun working on these aspects as well.
|
Profiling Humans from their Voice Rita Singh First published: July 2019 Copyright 2019 Springer-Nature, Switzerland, July 2019 ISBN: ISBN 978-981-13-8402-8 |
|
Techniques for Noise Robustness in Automatic Speech Recognition Tuomas Virtanen, Rita Singh, Bhiksha Raj (Eds) First published:5 October 2012 Copyright 2013 John Wiley & Sons, Ltd Print ISBN:9781119970880 Online ISBN:9781118392683 DOI:10.1002/9781118392683 |
I write poetry of all kinds, most rhyme, some don’t, some are difficult to read, some are very simple, some are for kids, some for everyone else, some are short, most are long… some are epic poetry… I’m also working on a comic book. Creative arts are my indulgence, it gives me great joy to create visual art and illustrations, and to write poetry and stories.
|
|
|
|
|
A corner of my office at home in Pittsburgh (An observational painting) 24x36 Oil on Canvas. Unfinished. March 2022
|
|
|
Three quick sketches: City crossing, A delightful day and A path through the trees Charcoal on paper. Nov. 2022, Drawn in Abu Dhabi, UAE