K
Kaustubh Kalgaonkar
Researcher at Facebook
Publications - 35
Citations - 778
Kaustubh Kalgaonkar is an academic researcher from Facebook. The author has contributed to research in topics: Acoustic model & Speech processing. The author has an hindex of 14, co-authored 31 publications receiving 620 citations. Previous affiliations of Kaustubh Kalgaonkar include Georgia Institute of Technology & Microsoft.
Papers
More filters
Posted Content
Transformer-Transducer: End-to-End Speech Recognition with Self-Attention
Ching-Feng Yeh,Jay Mahadeokar,Kaustubh Kalgaonkar,Yongqiang Wang,Duc Le,Mahaveer Jain,Kjell Schubert,Christian Fuegen,Michael L. Seltzer +8 more
TL;DR: The proposed Transformer-Transducer outperforms neural transducer with LSTM/BLSTM networks and achieved word error rates of 6.37 % on the test-clean set and 15.30%) while remaining streamable, compact, and computationally efficient with complexity of O(T), where T is input sequence length.
Proceedings ArticleDOI
One-handed gesture recognition using ultrasonic Doppler sonar
Kaustubh Kalgaonkar,Bhiksha Raj +1 more
TL;DR: A new device based on ultrasonic sensors to recognize one-handed gestures through the Doppler frequency shifts they generate in reflections of an ultrasonic tone emitted by the transmitter is presented.
Proceedings ArticleDOI
Acoustic Doppler sonar for gait recogination
Kaustubh Kalgaonkar,Bhiksha Raj +1 more
TL;DR: It is shown that remarkably good gait recognition is possible with the ADS sensor, a very inexpensive sensor that can be built using off-the-shelf components, for under $20 USD at today's prices.
Journal ArticleDOI
Ultrasonic Doppler Sensing in HCI
TL;DR: Several properties differentiate ultrasonic Doppler sensing from other sensing techniques-high frame rate, low computational overhead, instantaneous velocity readings, and range independence.
Proceedings ArticleDOI
Ultrasonic Doppler sensor for speaker recognition
Kaustubh Kalgaonkar,Bhiksha Raj +1 more
TL;DR: A novel use of an acoustic Doppler sonar for multi-modal speaker identification using reflections from the speaker's face as the speaker talks to extract specific characteristics that can be used to identify the speaker.