Personal information

No personal information available

Activities

Employment (1)

Google LLC: Mountain View, CA, US

Employment
Source: Self-asserted source
Rohit Prabhavalkar

Works (25)

End-to-End Speech Recognition: A Survey

IEEE/ACM Transactions on Audio, Speech, and Language Processing
2024 | Journal article
Contributors: Rohit Prabhavalkar; Takaaki Hori; Tara N. Sainath; Ralf Schlüter; Shinji Watanabe
Source: check_circle
Crossref

Dual Learning for Large Vocabulary On-Device ASR

2022 IEEE Spoken Language Technology Workshop (SLT)
2023-01-09 | Other
Contributors: Cal Peyser; Ronny Huang; Tara Sainath; Rohit Prabhavalkar; Michael Picheny; Kyunghyun Cho
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

Improving Deliberation by Text-Only and Semi-Supervised Training

Interspeech 2022
2022-09 | Other
Contributors: Ke Hu; Tara Sainath; Yanzhang He; Rohit Prabhavalkar; Trevor Strohman; Sepand Mavandadi; Weiran Wang
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

Anti-Aliasing Regularization in Stacking Layers

Interspeech 2020
2020-10 | Other
Contributors: Antoine Bruguier; Ananya Misra; Arun Narayanan; Rohit Prabhavalkar
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

Deliberation Model Based Two-Pass End-To-End Speech Recognition

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2020-05 | Other
Contributors: Ke Hu; Tara N. Sainath; Ruoming Pang; Rohit Prabhavalkar
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition

Interspeech 2019
2019-09 | Other
Contributors: Kazuki Irie; Rohit Prabhavalkar; Anjuli Kannan; Antoine Bruguier; David Rybach; Patrick Nguyen
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models

Interspeech 2019
2019-09 | Other
Contributors: Ke Hu; Antoine Bruguier; Tara N. Sainath; Rohit Prabhavalkar; Golan Pundak
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

Deep Context: End-to-end Contextual Speech Recognition

2018 IEEE Spoken Language Technology Workshop (SLT)
2018 | Other
Contributors: Golan Pundak; Tara N. Sainath; Rohit Prabhavalkar; Anjuli Kannan; Ding Zhao
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

Compression of End-to-End Models

Interspeech 2018
2018-09-02 | Other
Contributors: Ruoming Pang; Tara Sainath; Rohit Prabhavalkar; Suyog Gupta; Yonghui Wu; Shuyuan Zhang; Chung-Cheng Chiu
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2018-04 | Other
Contributors: Chris Donahue; Bo Li; Rohit Prabhavalkar
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

Improving the Performance of Online Neural Transducer Models

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2018-04 | Other
Contributors: Tara N. Sainath; Chung-Cheng Chiu; Rohit Prabhavalkar; Anjuli Kannan; Yonghui Wu; Patrick Nguyen; ZhiJeng Chen
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

Exploring architectures, data and units for streaming end-to-end speech recognition with RNN-transducer

2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
2017 | Other
Contributors: Kanishka Rao; Hasim Sak; Rohit Prabhavalkar
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

Streaming small-footprint keyword spotting using sequence-to-sequence models

2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
2017 | Other
Contributors: Yanzhang He; Rohit Prabhavalkar; Kanishka Rao; Wei Li; Anton Bakhtin; Ian McGraw
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

A Comparison of Sequence-to-Sequence Models for Speech Recognition

Interspeech 2017
2017-08 | Other
Contributors: Rohit Prabhavalkar; Kanishka Rao; Tara N. Sainath; Bo Li; Leif Johnson; Navdeep Jaitly
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

An Analysis of “Attention” in Sequence-to-Sequence Models

Interspeech 2017
2017-08 | Other
Contributors: Rohit Prabhavalkar; Tara N. Sainath; Bo Li; Kanishka Rao; Navdeep Jaitly
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

On the Efficient Representation and Execution of Deep Acoustic Models

Interspeech 2016
2016-09-08 | Other
Contributors: Raziel Alvarez; Rohit Prabhavalkar; Anton Bakhtin
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

Compressing deep neural networks using a rank-constrained topology

Interspeech 2015
2015-09-06 | Other
Contributors: Preetum Nakkiran; Raziel Alvarez; Rohit Prabhavalkar; Carolina Parada
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

An evaluation of posterior modeling techniques for phonetic recognition

2013 IEEE International Conference on Acoustics, Speech and Signal Processing
2013-05 | Other
Contributors: Rohit Prabhavalkar; Tara N. Sainath; David Nahamoo; Bhuvana Ramabhadran; Dimitri Kanevsky
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

Discriminative articulatory models for spoken term detection in low-resource conversational settings

2013 IEEE International Conference on Acoustics, Speech and Signal Processing
2013-05 | Other
Contributors: Rohit Prabhavalkar; Karen Livescu; Eric Fosler-Lussier; Joseph Keshet
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

Conditional Random Fields in Speech, Audio, and Language Processing

Proceedings of the IEEE
2013-04 | Journal article
Part of ISSN: 0018-9219
Contributors: Eric Fosler-Lussier; Yanzhang He; Preethi Jyothi; Rohit Prabhavalkar
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

A chunk-based phonetic score for mobile voice search

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2012-03 | Other
Contributors: Rohit Prabhavalkar; Jasha Droppo
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

A factored conditional random field model for articulatory feature forced transcription

2011 IEEE Workshop on Automatic Speech Recognition & Understanding
2011 | Other
Contributors: Rohit Prabhavalkar; Eric Fosler-Lussier; Karen Livescu
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

Articulatory feature classification using nearest neighbors

Interspeech 2011
2011-08 | Other
Contributors: Arild Brandrud Næss; Karen Livescu; Rohit Prabhavalkar
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

Combining monaural and binaural evidence for reverberant speech segregation

Interspeech 2010
2010-09 | Other
Contributors: John Woodruff; Rohit Prabhavalkar; Eric Fosler-Lussier; DeLiang Wang
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search

Monaural segregation of voiced speech using discriminative random fields

Interspeech 2009
2009-09-06 | Other
Contributors: Rohit Prabhavalkar; Zhaozhang Jin; Eric Fosler-Lussier
Source: Self-asserted source
Rohit Prabhavalkar via Crossref Metadata Search