Events Calendar

Parametric Speech Production Representations for Formant Tracking and Joint Source-filter Modeling

Speaker: Dr. Daryush Mehta, Harvard University & Medical School, Massachusetts General Hospital

Talk Title: Parametric Speech Production Representations for Formant Tracking and Joint Source-filter Modeling

Abstract: We continue to see an urgent need for robust representations of the acoustic speech waveform, especially in speakers with speech and voice impairments. First, I will discuss our approach to the problem of formant and antiformant tracking, in which extended Kalman algorithms take advantage of a linearized mapping from formant frequencies and bandwidths to cepstral coefficients in an autoregressive moving average model. Second, we will explore joint source-filter models for representing sustained vowel phonation that exhibits nonstationary or asymmetric vocal fold vibration. These algorithms hold potential clinical significance for better understanding acoustic-physiological relationships observable with current imaging systems.

Biography: Daryush Mehta is a Research Associate in Electrical Engineering in the School of Engineering and Applied Sciences at Harvard University, an Assistant Biomedical Engineer at the Center for Laryngeal Surgery and Voice Rehabilitation at the Massachusetts General Hospital, and an Instructor in Surgery at Harvard Medical School. Daryush received his PhD in Speech and Hearing Bioscience and Technology from Harvard–MIT (2010), Master's degree in Electrical Engineering and Computer Science from MIT (2006), and Bachelor's degree in Electrical Engineering from University of Florida (2003). 
http://people.seas.harvard.edu/~dmehta/

Host: Prof. Shri Narayanan & Dr. Michael Proctor

Location: Ronald Tutor Hall of Engineering (RTH) - 320

Audiences: Everyone Is Invited

Contact: Mary Francis