Research Interests


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. Speech, a highly ordered manifestation of the human voice, is also shaped and influenced by the external environment. Understanding general audio, it's interplay with human voice and it's contextual significance, is a vital part of my research. The final goal of my work is to enable computing machines to not only recognize the content of human speech better in general, but also to understand and respond to humans by gauging their persona, their intent and their staus vis-a-vis their environment from their voice alone, with an actuity that surpasses that of the human brain. This part of my research represents an intersection of the areas of AI and Voice Forensics. I continue to work towards making voice intelligence algorithms work much better than currently possible in high-noise and other kinds of complex environments, using minimal external (human-generated) knowledge. On the periphery, I work on the general quest for more automation, powerful search strategies and more scaleable learning algorithms for voice intelligence systems.

More......


On the voice of Anthony Hopkins in the movie Magic (1978) by Alex Best, Ace Ventriloquist, amongst other good things!

Helping fight federal crimes with Artificial (Sonic) Intelligence

Please note: Lately, there have been many news articles alluding to my work with statements such as "From something as simple as the sound of your breath, Rita Singh, a researcher at Carnegie Mellon University's Language Technologies Institute, can pull information about what you look like and the room from where you are calling". This is absolutely not true. Breath can identify people, but deriving infomation about the environment is not possible (from breath alone) at the moment. Many news reports out there are not endorsed by me, and many statements that are claimed to be made by me, have indeed not been made by me. I am writing up papers on what can or cannot be done with voice. They will appear soon on this webpage.

Courses

Spring 2017:
  1. Computational Forensics and Investigative Intelligence
    • CYSE-645 Hamad Bin Khalifa University (HBKU), Qatar
    • 15-498 (W) CMU Qatar
    • 15-498 (R) CMU Africa
  2. An Introduction to Knowledge based Deep Learning and Socratic Coaches
    • 11-364 CMU Pittsburgh
      • Backend collaboration. This course was taught in person by Prof. James Karl Baker at the CMU Pittsburgh location.

Students

  • Yolanda Gao, PhD, Electrical and Computer Engineering
  • Wayne Zhao, PhD, Electrical and Computer Engineering
  • Yandong Wen, PhD, Electrical and Computer Engineering

Recent Publications

  • Voice disguise by mimicry: deriving statistical articulometric evidence to evaluate claimed impersonation, Rita Singh, Abelino Jiminez and Anders Oland, IET Biometrics, January 2017. pdf

  • Minimizing Free Energy of Stochastic Functions of Markov Chains, Rita singh , in Recent Advances in Nonlinear Speech Processing pp 227-233. Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 48), Springer.

    • more below....
A message from me: The Amazon on your computer is destroying the Amazon in Brazil. Online shopping costs the planet heavily. Even a small product, like a toothpick, requires many resources to produce and package for sale. But online shopping adds volumes to that. Huge amounts of cardboard, indestructible styrofoam and plastic packaging material is used indiscriminately by the online shopping giants of today. Much of it ends up in landfills and in the oceans. The packaging process is automated for the most part. Machines do not think about your planet. You have to. In the end, with re-packaging and the fuel used for individualized transportation to your location, a packet of toothpick that is bought online costs the equivalent of a tree. Online shopping is an environmental hazard. It is a societal hazard. It destroys jobs of real people. It has destroyed the small stores, and is now destroying even the physical superstores. It is also a psychological hazard. Convenience is good, undoubtedly, but when it comes at such a great insidious cost, it is time to rethink our options. This is a plea to the world to reduce online shopping where feasible. Use it only when you really need it. The malls and stores around you are still magical and useful. Make that trip.
Please read this..


Books


Research publications (by topic)


  1. Forensics    Papers
    General theme: Forensic deductions from human voice, speech and audio signals in general. Publications in this area lag behind our current work by a couple of years at least, as we rapidly respond to the challenges posed by real crimes by creating technology that is immediately applied to the problem at hand.

  2. General audio analysis, microphone array processing, denoising, dereverberation, signal restoration    Papers
    General theme: Our approach is that of modeling the effect of highly-nonstationary noise and reverberation as compositional phenomena. Clean signals can then be recomposed from the bases of the composition. This approach differs from ones that model audio phenomena using dynamic generative models.

  3. Semi-supervised learning, structure discovery, statistical pattern recognition, classification    Papers
    These papers cover diferent topics such as learning basic units of sound from data, discovering pronunciations for words in terms of these units, selecting better classifiers using weaker classifiers iteratively in a gradient ascent solution to training good acoustic models from completely untranscribed data etc.. They also include general developments in classification techniques.

  4. Acoustic modeling, decoding, speech processing, speech recognition, adaptation, keyword spotting    Papers
    These papers relate to core and peripheral issues in speech recognition and processing for HMM-based ASR systems.

  5. Systems, applications, projects    Papers
    These papers describe systems developed or deployed for specific tasks. Also include papers from short-term student projects, technical reports and other writeups

  6. Miscellaneous    Papers
    Patents, papers on other topics such as chaos theory, radar signal design, geodynamics. From 1993-1998 I worked on these topics. Chaos and complexity theory remain my favorite hobby subjects.

Other activities

  • Associate Editor, IEEE Signal Processing Letters
  • Sphinx-4

Tracking weather

Home   Funded.Projects   Where.I.worked   Other.ongoing.work   Personal.pages   My.old.homepage