Generative Voice: Applications and Implications

Abstract

Recent advances in machine learning have transformed speech and language processing. In particular, generative voice models can now emulate a speaker’s articulation, cadence, intonation and conversational style to uncanny levels. When combined with large language models the line between human – machine conversation has not only blurred but evolved. This talk demonstrates how an assistive technology application of personalized voices is now fueling mainstream use cases in media and entertainment, customer service, education, health care and more. The discussion also includes the impact of this technology on social, economic, security and ethical considerations.

Biography

Rupal Patel is a tenured professor at Northeastern University with joint appointments in Bouve College of Health Science and Khoury College of Computer Science. Rupal is also a Core Faculty member at the Institute for Experiential AI. Her research focuses on speech motor control in healthy talkers and those with neuromotor speech impairment; this empirical evidence is then applied to the design of technologies that enable, enrich and enhance communication. Rupal is also an entrepreneur who founded and led VocaliD, a synthetic media company that was recently acquired by Veritone Inc, an enterprise AI solutions company. Rupal is currently on leave from the University to integrate VocaliD within Veritone where she leads strategy and innovation as VP of Voice and Accessibility. Rupal’s work has been featured on TED and NPR and in leading news and technology outlets such as The Wall Street Journal, Wired, Bloomberg, BuzzFeed and FastCompany. She is a member of the Aspen Global Leadership Network, serves on several non-profit boards and is a fierce advocate for accessible and inclusive technology that benefits all.