Rupal Patel, founder of VocaliD, describes how she is developing a technology that creates personalized, enhanced voices for the speech impaired.
Looking for ways to give voice to the voiceless, Rupal Patel founded VocaliD, a company that creates customized synthetic voices by combining the speaker’s residual voice with an anatomically similar voice selected from a donor database. The result is a reverse engineered voice that approximates how a person may sound if not limited by a speech impairment. Rupal is a Professor at Northeastern University, where she directs the Communication Analysis and Design Laboratory, an interdisciplinary research group she founded that focuses on the study of speech communication in typically developing talkers and individuals with neuromotor speech impairments. Rupal also holds appointments at Harvard, MIT, University of Massachusetts, and Yale University. She recently launched the Human Voicebank Initiative, an effort to collect a million voice samples from English speakers worldwide.
LEARN MORESpeaking up for the voiceless: Q&A with Rupal Patel
Park Play: A picture description task for assessing childhood motor speech disorders
Patel R, et al. International Journal of Speech-Language Pathology. 2014:16(4), 337-343.
The Caterpillar: A Novel Reading Passage for Assessment of Motor Speech Disorders
Patel R, et al. American Journal of Speech Language Pathology. 2013:22, 1-9.
Talk ReferencesTowards Personalized Speech Synthesis for Augmentative and Assistive Communication
Mills T, Bunnell TH, Patel R. Augmentative and Alternative Communication. 2014:30(3), 226-236.
Unsupervised Vocal-tract Length Estimation Through Model-based Acoustic-to-Articulatory Inversion
Cai S, Bunnell TH, Patel R. 2013: 1712–1716.
Prosodic Adaptations to Pitch Perturbation in Running Speech
Patel R, Niziolek C, Reilly K, Guenther FH. Journal of Speech, Language, and Hearing Research. 2011:54, 1051-1059.
ReadN’Karaoke: visualizing prosody in children's books for expressive oral reading
Patel R, Furr W. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. 2011:3203-3206.