Tara N. Sainath
Papers
1
Total Citations
66
H-Index
1
About
Tara N. Sainath is a leading researcher in speech and audio processing, with a focus on deep learning for automatic speech recognition (ASR). Her major contributions include pioneering work on convolutional, recurrent, and attention-based neural network architectures for ASR, which have significantly advanced the state of the art. She is perhaps best known for her influential research on Listen, Attend and Spell (LAS) models and sequence-to-sequence learning for end-to-end speech recognition, which has been widely adopted in both academia and industry. Her work has garnered over 20,000 citations, reflecting its profound impact on the field. At Google, she has led efforts to integrate these models into production systems, notably improving voice search and assistant capabilities. Earlier in her career, she also contributed to robotics, co-authoring a paper on a voice-commandable robotic forklift for human-robot collaboration. A recipient of multiple best paper awards, Sainath continues to shape the future of speech technology through her innovative research and leadership.
Research Focus
Key Achievements
Top Papers
- 1