Articles by Rohit Prabhavalkar

Efficiently Train ASR Models that Memorize Less and Perform Better with Per-core Clipping

5 June 2024 by Lun Wang and others

Cryptography and Security, Computation and Language

Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASR

23 April 2024 by Zelin Wu and others at

Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models

27 February 2024 by Rohit Prabhavalkar and others at

How to Estimate Model Transferability of Pre-Trained Speech Models?

6 February 2024 by Zih-Ching Chen and others at

Computation and Language, Neural and Evolutionary Computing

USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models

16 January 2024 by Shaojin Ding and others at

Audio and Speech Processing, Sound

Improved Long-Form Speech Recognition by Jointly Modeling the Primary and Non-primary Speakers

18 December 2023 by Guru Prakash Arumugam and others at

Sound, Artificial Intelligence

The Gift of Feedback: Improving ASR Model Quality by Learning from User Corrections through Federated Learning

30 November 2023 by Lillian Zhou and others at

Computation and Language, Audio and Speech Processing

Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithm

29 September 2023 by Weiran Wang and others

Computation and Language, Audio and Speech Processing

Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages

25 September 2023 by Yu Zhang and others

Massive End-to-end Models for Short Search Queries

22 September 2023 by Weiran Wang and others

Audio and Speech Processing, Sound

Improving Joint Speech-Text Representations Without Alignment

11 August 2023 by Cal Peyser and others

A Comparison of Semi-Supervised Learning Techniques for Streaming ASR at Scale

19 April 2023 by Cal Peyser and others

Lego-Features: Exporting modular encoder features for streaming and deliberation ASR

31 March 2023 by Rami Botros and others

Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition Models

15 March 2023 by Yanzhang He and others

Audio and Speech Processing, Artificial Intelligence

E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model

5 March 2023 by W. Ronny Huang and others at

End-to-End Speech Recognition: A Survey

Computation and Language

3 March 2023 by Rohit Prabhavalkar and others

Audio and Speech Processing, Computation and Language

Modular Hybrid Autoregressive Transducer

17 February 2023 by Zhong Meng and others

JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition

16 February 2023 by Zhong Meng and others

Audio and Speech Processing, Artificial Intelligence

From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition

19 January 2023 by Chao-Han Huck Yang and others

Sound, Artificial Intelligence

Dual Learning for Large Vocabulary On-Device ASR

11 January 2023 by Cal Peyser and others

JOIST: A Joint Speech and Text Streaming Model For ASR

13 October 2022 by Tara Sainath and others

Improving Deliberation by Text-Only and Semi-Supervised Training

29 June 2022 by Ke Hu and others

Improving Rare Word Recognition with LM-aware MWER Training

27 June 2022 by Weiran Wang and others

E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR

15 June 2022 by W. Ronny Huang and others

Sound, Computation and Language

A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes

20 April 2022 by Shaojin Ding and others

Audio and Speech Processing, Machine Learning

Input Length Matters: Improving RNN-T and MWER Training for Long-form Telephony Speech Recognition

1 April 2022 by Zhiyun Lu and others

Audio and Speech Processing, Computation and Language

Neural-FST Class Language Model for End-to-End Speech Recognition

31 January 2022 by Antoine Bruguier and others