Speaker Conditioned Acoustic-to-Articulatory Inversion



Presentation on 'Speaker Conditioned Acoustic-to-Articulatory Inversion Using x-Vectors' at InterSpeech 2020 Shanghai, China.

RESPIN Project



Speech recognition in agriculture and finance for the poor is an initiative to create resources and make them available in the open-source domain to spur research and innovation in speech recognition in nine different Indian languages in the area of agriculture and finance.

Evaluation of Indian English pronunciation



The study involves development of an interactive system which can assess, diagnose and track the Indian English spoken language learners.

Identification of speakers using head gestures in a narration



Head gestures convey intensity of speech and a lot of paralinguistic information. This study contributes to Automatic Identification of speakers using head gestures.

In the words of our alumni