Rita Singh works on core algorithmic aspects of computer voice recognition and artificial intelligence applied to voice forensics. Her focus is on the development of technology for automated discovery, measurement, representation, and learning of information encoded in voice signals for optimal voice intelligence. Understanding general audio and the interplay of human voice with contextual significance is a vital part of her research. The ultimate goal of her work is to enable computing machines to recognize the content of human speech and understand and respond to humans by gauging persona, intent, and status solely through voice—an acuity that surpasses that of the human brain. Singh's research represents the intersection of areas in AI and voice forensics. She continues to work toward enhancing voice intelligence algorithms to function effectively in high-noise and complex environments while using minimal external (human-generated) knowledge. Additionally, she engages in the quest for automation, powerful search strategies, and scalable learning algorithms for voice intelligence systems.
Language Technologies Institute, Carnegie Mellon University • Pittsburgh, PA
Conducts research on voice recognition algorithms and artificial intelligence applications in voice forensics.