Rohit Prabhavalkar

Orcid: 0000-0001-5331-6058

According to our database¹, Rohit Prabhavalkar authored at least 80 papers between 2009 and 2024.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of three.

Timeline

Legend:

Book

In proceedings

Article

PhD thesis

Dataset

Other

Bibliography

2024

End-to-End Speech Recognition: A Survey.

[BibT_eX]

[DOI]

IEEE ACM Trans. Audio Speech Lang. Process., 2024

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

[BibT_eX]

[DOI]

CoRR, 2024

2023

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

[BibT_eX]

[DOI]

CoRR, 2023

Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithm.

[BibT_eX]

[DOI]

Weiran Wang

Zelin Wu

Diamantino Caseiro

Tsendsuren Munkhdalai

Pedro Moreno Mengibar

CoRR, 2023

Massive End-to-end Models for Short Search Queries.

[BibT_eX]

[DOI]

Pedro Moreno Mengibar

CoRR, 2023

Improving Joint Speech-Text Representations Without Alignment.

[BibT_eX]

[DOI]

CoRR, 2023

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

[BibT_eX]

[DOI]

CoRR, 2023

Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages.

[BibT_eX]

[DOI]

CoRR, 2023

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

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

Improving Contextual Biasing with Text Injection.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

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

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

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

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

Cross-Training: A Semi-Supervised Training Scheme for Speech Recognition.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

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

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

Lego-Features: Exporting Modular Encoder Features for Streaming and Deliberation ASR.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

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

[BibT_eX]

[DOI]

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023

Efficient Cascaded Streaming ASR System Via Frame Rate Reduction.

[BibT_eX]

[DOI]

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023

Improved Long-Form Speech Recognition By Jointly Modeling The Primary And Non-Primary Speakers.

[BibT_eX]

[DOI]

Guru Prakash Arumugam

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023

2022

JOIST: A Joint Speech and Text Streaming Model for ASR.

[BibT_eX]

[DOI]

Proceedings of the IEEE Spoken Language Technology Workshop, 2022

Dual Learning for Large Vocabulary On-Device ASR.

[BibT_eX]

[DOI]

Proceedings of the IEEE Spoken Language Technology Workshop, 2022

Modular Hybrid Autoregressive Transducer.

[BibT_eX]

[DOI]

Proceedings of the IEEE Spoken Language Technology Workshop, 2022

Improving Rare Word Recognition with LM-aware MWER Training.

[BibT_eX]

[DOI]

Proceedings of the Interspeech 2022, 2022

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

[BibT_eX]

[DOI]

Proceedings of the Interspeech 2022, 2022

Improving Deliberation by Text-Only and Semi-Supervised Training.

[BibT_eX]

[DOI]

Proceedings of the Interspeech 2022, 2022

A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes.

[BibT_eX]

[DOI]

Proceedings of the Interspeech 2022, 2022

Improving The Latency And Quality Of Cascaded Encoders.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2022

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

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2022

2021

Input Length Matters: An Empirical Study Of RNN-T And MWER Training For Long-form Telephony Speech Recognition.

[BibT_eX]

[DOI]

CoRR, 2021

RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions.

[BibT_eX]

[DOI]

Proceedings of the IEEE Spoken Language Technology Workshop, 2021

Dynamic Encoder Transducer: A Flexible Solution for Trading Off Accuracy for Latency.

[BibT_eX]

[DOI]

Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

Dissecting User-Perceived Latency of On-Device E2E Speech Recognition.

[BibT_eX]

[DOI]

Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

Replacing Human Audio with Synthetic Audio for on-Device Unspoken Punctuation Prediction.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2021

Learning Word-Level Confidence for Subword End-To-End ASR.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2021

Less is More: Improved RNN-T Decoding Using Limited Label Context and Path Merging.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2021

Cascaded Encoders for Unifying Streaming and Non-Streaming ASR.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2021

A Neural Acoustic Echo Canceller Optimized Using An Automatic Speech Recognizer and Large Scale Synthetic Data.

[BibT_eX]

[DOI]

Nathan Howard

Alex Park

Turaj Zakizadeh Shabestary

Alexander Gruenstein

Rohit Prabhavalkar

Proceedings of the IEEE International Conference on Acoustics, 2021

2020

A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency.

[BibT_eX]

[DOI]

CoRR, 2020

Anti-Aliasing Regularization in Stacking Layers.

[BibT_eX]

[DOI]

Proceedings of the Interspeech 2020, 2020

A Streaming On-Device End-To-End Model Surpassing Server-Side Conventional Model Quality and Latency.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

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

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019

Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling.

[BibT_eX]

[DOI]

CoRR, 2019

Model Unit Exploration for Sequence-to-Sequence Speech Recognition.

[BibT_eX]

[DOI]

CoRR, 2019

Two-Pass End-to-End Speech Recognition.

[BibT_eX]

[DOI]

Proceedings of the Interspeech 2019, 2019

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

[BibT_eX]

[DOI]

Proceedings of the Interspeech 2019, 2019

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

[BibT_eX]

[DOI]

Proceedings of the Interspeech 2019, 2019

Streaming End-to-end Speech Recognition for Mobile Devices.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2019

Joint Endpointing and Decoding with End-to-end Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2019

Phoebe: Pronunciation-aware Contextualization for End-to-end Speech Recognition.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2019

Recognizing Long-Form Speech Using Streaming End-to-End Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2019

A Comparison of End-to-End Models for Long-Form Speech Recognition.

[BibT_eX]

[DOI]

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2019

2018

Deep Context: End-to-end Contextual Speech Recognition.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018

From Audio to Semantics: Approaches to End-to-End Spoken Language Understanding.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018

Compression of End-to-End Models.

[BibT_eX]

[DOI]

Proceedings of the Interspeech 2018, 2018

No Need for a Lexicon? Evaluating the Value of the Pronunciation Lexica in End-to-End Models.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Improving the Performance of Online Neural Transducer Models.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Minimum Word Error Rate Training for Attention-Based Sequence-to-Sequence Models.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

An Analysis of Incorporating an External Language Model into a Sequence-to-Sequence Model.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition.

[BibT_eX]

[DOI]

Chris Donahue

Bo Li

Rohit Prabhavalkar

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

State-of-the-Art Speech Recognition with Sequence-to-Sequence Models.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017

An Analysis of "Attention" in Sequence-to-Sequence Models.

[BibT_eX]

[DOI]

Proceedings of the Interspeech 2017, 2017

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

[BibT_eX]

[DOI]

Proceedings of the Interspeech 2017, 2017

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

[BibT_eX]

[DOI]

Kanishka Rao

Hasim Sak

Rohit Prabhavalkar

Proceedings of the 2017 IEEE Automatic Speech Recognition and Understanding Workshop, 2017

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

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE Automatic Speech Recognition and Understanding Workshop, 2017

2016

On the Efficient Representation and Execution of Deep Acoustic Models.

[BibT_eX]

[DOI]

Raziel Alvarez

Rohit Prabhavalkar

Anton Bakhtin

Proceedings of the Interspeech 2016, 2016

On the compression of recurrent neural networks with an application to LVCSR acoustic modeling for embedded speech recognition.

[BibT_eX]

[DOI]

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Personalized speech recognition on mobile devices.

[BibT_eX]

[DOI]

Ian McGraw

Rohit Prabhavalkar

Raziel Alvarez

Montse Gonzalez Arenas

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2015

Compressing deep neural networks using a rank-constrained topology.

[BibT_eX]

[DOI]

Proceedings of the INTERSPEECH 2015, 2015

Automatic gain control and multi-style training for robust small-footprint keyword spotting with deep neural networks.

[BibT_eX]

[DOI]

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

2013

Conditional Random Fields in Speech, Audio, and Language Processing.

[BibT_eX]

[DOI]

Proc. IEEE, 2013

An evaluation of posterior modeling techniques for phonetic recognition.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2013

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

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2013

2012

Discriminative spoken term detection with limited data.

[BibT_eX]

[DOI]

Proceedings of the 2012 Symposium on Machine Learning in Speech and Language Processing, 2012

A chunk-based phonetic score for mobile voice search.

[BibT_eX]

[DOI]

Rohit Prabhavalkar

Jasha Droppo

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

2011

Articulatory Feature Classification Using Nearest Neighbors.

[BibT_eX]

[DOI]

Arild Brandrud Næss

Karen Livescu

Rohit Prabhavalkar

Proceedings of the INTERSPEECH 2011, 2011

A factored conditional random field model for articulatory feature forced transcription.

[BibT_eX]

[DOI]

Rohit Prabhavalkar

Eric Fosler-Lussier

Karen Livescu

Proceedings of the 2011 IEEE Workshop on Automatic Speech Recognition & Understanding, 2011

2010

Investigations into the Crandem Approach to Word Recognition.

[BibT_eX]

[DOI]

Proceedings of the Human Language Technologies: Conference of the North American Chapter of the Association of Computational Linguistics, 2010

Combining monaural and binaural evidence for reverberant speech segregation.

[BibT_eX]

[DOI]

Proceedings of the INTERSPEECH 2010, 2010

Backpropagation training for multilayer conditional random field based phone recognition.

[BibT_eX]

[DOI]

Rohit Prabhavalkar

Eric Fosler-Lussier

Proceedings of the IEEE International Conference on Acoustics, 2010

2009

Monaural segregation of voiced speech using discriminative random fields.

[BibT_eX]

[DOI]

Rohit Prabhavalkar

Zhaozhang Jin

Eric Fosler-Lussier

Proceedings of the INTERSPEECH 2009, 2009

Rohit Prabhavalkar

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...