Tara N. Sainath

Google (United States) — United States

Computer Science · Physical Sciences

60h-index29.3kcitations300works16.92yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech Recognition and Synthesis(249), Speech and Audio Processing(166), Music and Audio Processing(146), Natural Language Processing Techniques(80), Topic Modeling(57)

Publications298 total

Text Injection for Neural Contextual Biasing
2024· 3 cited
Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithm
2024· 1 cited
Text Injection for Neural Contextual Biasing
arXiv (Cornell University)·2024Open Access
Hierarchical Recurrent Adapters for Efficient Multi-Task Adaptation of Large Speech Models
arXiv (Cornell University)·2024Open Access
A Comparison of Parameter-Efficient ASR Domain Adaptation Methods for Universal Speech and Language Models
2024· 6 cited
Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study
2024· 5 cited
Efficient Adapter Finetuning for Tail Languages in Streaming Multilingual ASR
2024· 4 cited
USM-Lite: Quantization and Sparsity Aware Fine-Tuning for Speech Recognition with Universal Speech Models
2024· 2 cited
Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models
2024· 5 cited
Augmenting Conformers With Structured State-Space Sequence Models For Online Speech Recognition
2024· 3 cited
Improving Speech Recognition for African American English with Audio Classification
2024· 2 cited
Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models
arXiv (Cornell University)·2024Open Access
Handling Ambiguity in Emotion: From Out-of-Domain Detection to Distribution Estimation
arXiv (Cornell University)·2024Open Access
Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study
arXiv (Cornell University)·2024· 1 citedOpen Access
Efficient Adapter Finetuning for Tail Languages in Streaming Multilingual ASR
arXiv (Cornell University)·2024Open Access
Handling Ambiguity in Emotion: From Out-of-Domain Detection to Distribution Estimation
2024· 2 citedOpen Access
Massive End-to-end Speech Recognition Models with Time Reduction
2024· 1 citedOpen Access
Improved Long-Form Speech Recognition by Jointly Modeling the Primary and Non-primary Speakers
arXiv (Cornell University)·2023Open Access
Efficient Cascaded Streaming ASR System Via Frame Rate Reduction
2023· 2 cited
Improving Multilingual and Code-Switching ASR Using Large Language Model Generated Text
2023· 4 cited
page 1 of 15Next →

Frequent Co-authors

Bhuvana Ramabhadran(12), Brian Kingsbury(10), Rohit Prabhavalkar(10), Yonghui Wu(10), Bo Li(8), Ruoming Pang(8), Michiel Bacchiani(8), Abdelrahman Mohamed(7), Anjuli Kannan(7), Golan Pundak(7), Kanishka Rao(7), Ron J. Weiss(7), Chung‐Cheng Chiu(7), Shuo-Yiin Chang(6), Arun Narayanan(6), Zhifeng Chen(6), George E. Dahl(5), Navdeep Jaitly(5), Andrew Senior(5), Patrick Nguyen(5)