Tara N. Sainath

research

∙ 08/11/2023

Improving Joint Speech-Text Representations Without Alignment

The last year has seen astonishing progress in text-prompted image gener...

0 Cal Peyser, et al. ∙

research

∙ 06/01/2023

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

In this work, we introduce a “score-based assessment” framework for esti...

0 Zih-Ching Chen, et al. ∙

research

∙ 05/25/2023

Mixture-of-Expert Conformer for Streaming Multilingual ASR

End-to-end models with large capacity have significantly improved multil...

0 Ke Hu, et al. ∙

research

∙ 03/31/2023

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

In end-to-end (E2E) speech recognition models, a representational tight-...

0 Rami Botros, et al. ∙

research

∙ 03/31/2023

Practical Conformer: Optimizing size, speed and flops of Conformer for on-Device and cloud ASR

Conformer models maintain a large number of internal states, the vast ma...

0 Rami Botros, et al. ∙

research

∙ 03/23/2023

A Deliberation-based Joint Acoustic and Text Decoder

We propose a new two-pass E2E speech recognition model that improves ASR...

0 Sepand Mavandadi, et al. ∙

research

∙ 03/15/2023

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

Continued improvements in machine learning techniques offer exciting new...

0 Steven M. Hernandez, et al. ∙

research

∙ 03/03/2023

End-to-End Speech Recognition: A Survey

In the last decade of automatic speech recognition (ASR) research, the i...

0 Rohit Prabhavalkar, et al. ∙

research

∙ 02/22/2023

UML: A Universal Monolingual Output Layer for Multilingual ASR

Word-piece models (WPMs) are commonly used subword units in state-of-the...

0 Chao Zhang, et al. ∙

research

∙ 02/17/2023

Massively Multilingual Shallow Fusion with Large Language Models

While large language models (LLM) have made impressive progress in natur...

0 Ke Hu, et al. ∙

research

∙ 02/16/2023

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

We propose JEIT, a joint end-to-end (E2E) model and internal language mo...

0 Zhong Meng, et al. ∙

research

∙ 01/19/2023

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

In this work, we propose a new parameter-efficient learning framework ba...

0 Chao-Han Huck Yang, et al. ∙

research

∙ 11/28/2022

E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model

We explore unifying a neural segmenter with two-pass cascaded encoder AS...

0 W. Ronny Huang, et al. ∙

research

∙ 11/02/2022

A Quantum Kernel Learning Approach to Acoustic Modeling for Spoken Command Recognition

We propose a quantum kernel learning (QKL) framework to address the inhe...

0 Chao-Han Huck Yang, et al. ∙

research

∙ 10/13/2022

JOIST: A Joint Speech and Text Streaming Model For ASR

We present JOIST, an algorithm to train a streaming, cascaded, encoder e...

0 Tara N. Sainath, et al. ∙

research

∙ 10/11/2022

Scaling Up Deliberation for Multilingual ASR

Multilingual end-to-end automatic speech recognition models are attracti...

0 Ke Hu, et al. ∙

research

∙ 08/29/2022

A Language Agnostic Multilingual Streaming On-Device ASR System

On-device end-to-end (E2E) models have shown improvements over a convent...

1 Bo Li, et al. ∙

research

∙ 08/29/2022

Streaming Intended Query Detection using E2E Modeling for Continued Conversation

In voice-enabled applications, a predetermined hotword isusually used to...

0 Shuo-yiin Chang, et al. ∙

research

∙ 08/29/2022

Turn-Taking Prediction for Natural Conversational Speech

While a streaming voice assistant system has been used in many applicati...

0 Shuo-yiin Chang, et al. ∙

research

∙ 06/29/2022

Improving Deliberation by Text-Only and Semi-Supervised Training

Text-only and semi-supervised training based on audio-only data has gain...

0 Ke Hu, et al. ∙

research

∙ 05/21/2022

Self-Supervised Speech Representation Learning: A Review

Although supervised deep learning has revolutionized speech and audio pr...

0 Abdelrahman Mohamed, et al. ∙

research

∙ 04/22/2022

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

Improving the performance of end-to-end ASR models on long utterances ra...

0 W. Ronny Huang, et al. ∙

research

∙ 04/15/2022

Streaming Align-Refine for Non-autoregressive Deliberation

We propose a streaming non-autoregressive (non-AR) decoding algorithm to...

0 Weiran Wang, et al. ∙

research

∙ 04/15/2022

Improving Rare Word Recognition with LM-aware MWER Training

Language models (LMs) significantly improve the recognition accuracy of ...

0 Weiran Wang, et al. ∙

research

∙ 04/13/2022

A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes

In this paper, we propose a dynamic cascaded encoder Automatic Speech Re...

0 Shaojin Ding, et al. ∙

research

∙ 03/09/2022

Sentence-Select: Large-Scale Language Model Data Selection for Rare-Word Speech Recognition

Language model fusion helps smart assistants recognize words which are r...

5 W. Ronny Huang, et al. ∙

research

∙ 01/25/2022

Improving the fusion of acoustic and text representations in RNN-T

The recurrent neural network transducer (RNN-T) has recently become the ...

1 Chao Zhang, et al. ∙

research

∙ 11/15/2021

Joint Unsupervised and Supervised Training for Multilingual ASR

Self-supervised training has shown promising gains in pretraining models...

0 Junwen Bai, et al. ∙

research

∙ 09/27/2021

BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition

We summarize the results of a host of efforts using giant automatic spee...

1 Yu Zhang, et al. ∙

research

∙ 09/15/2021

Tied Reduced RNN-T Decoder

Previous works on the Recurrent Neural Network-Transducer (RNN-T) models...

0 Rami Botros, et al. ∙

research

∙ 04/30/2021

Scaling End-to-End Models for Large-Scale Multilingual ASR

Building ASR models across many language families is a challenging multi...

14 Bo Li, et al. ∙

research

∙ 04/09/2021

Lookup-Table Recurrent Language Models for Long Tail Speech Recognition

We introduce Lookup-Table Language Models (LookupLM), a method for scali...

0 W. Ronny Huang, et al. ∙

research

∙ 03/11/2021

Learning Word-Level Confidence For Subword End-to-End ASR

We study the problem of word-level confidence estimation in subword-base...

0 David Qiu, et al. ∙

research

∙ 01/27/2021

Transformer Based Deliberation for Two-Pass Speech Recognition

Interactive speech recognition systems must generate words quickly while...

0 Ke Hu, et al. ∙

research

∙ 12/12/2020

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

End-to-end models that condition the output label sequence on all previo...

5 Rohit Prabhavalkar, et al. ∙

research

∙ 11/21/2020

A Better and Faster End-to-End Model for Streaming ASR

End-to-end (E2E) models have shown to outperform state-of-the-art conven...

0 Bo Li, et al. ∙

research

∙ 10/27/2020

Cascaded encoders for unifying streaming and non-streaming ASR

End-to-end (E2E) automatic speech recognition (ASR) models, by now, have...

0 Arun Narayanan, et al. ∙

research

∙ 10/27/2020

Multitask Training with Text Data for End-to-End Speech Recognition

We propose a multitask training method for attention-based end-to-end sp...

0 Peidong Wang, et al. ∙

research

∙ 10/21/2020

FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization

Streaming automatic speech recognition (ASR) aims to emit each hypothesi...

5 Jiahui Yu, et al. ∙

research

∙ 10/12/2020

Universal ASR: Unify and Improve Streaming ASR with Full-context Modeling

Streaming automatic speech recognition (ASR) aims to emit each hypothesi...

8 Jiahui Yu, et al. ∙

research

∙ 08/24/2020

Improving Tail Performance of a Deliberation E2E ASR Model Using a Large Text Corpus

End-to-end (E2E) automatic speech recognition (ASR) systems lack the dis...

0 Cal Peyser, et al. ∙

research

∙ 05/19/2020

Improving Proper Noun Recognition in End-to-End ASR By Customization of the MWER Loss Criterion

Proper nouns present a challenge for end-to-end (E2E) automatic speech r...

0 Cal Peyser, et al. ∙

research

∙ 05/07/2020

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

In recent years, all-neural end-to-end approaches have obtained state-of...

0 Chung-Cheng Chiu, et al. ∙

research

∙ 03/28/2020

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

Thus far, end-to-end (E2E) models have not been shown to outperform stat...

0 Tara N. Sainath, et al. ∙

research

∙ 03/17/2020

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

End-to-end (E2E) models have made rapid progress in automatic speech rec...

0 Ke Hu, et al. ∙

research

∙ 10/24/2019

Recognizing long-form speech using streaming end-to-end models

All-neural end-to-end (E2E) automatic speech recognition (ASR) systems t...

0 Arun Narayanan, et al. ∙

research

∙ 09/11/2019

Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model

Multilingual end-to-end (E2E) models have shown great promise in expansi...

26 Anjuli Kannan, et al. ∙

research

∙ 08/29/2019

Two-Pass End-to-End Speech Recognition

The requirements for many applications of state-of-the-art speech recogn...

0 Tara N. Sainath, et al. ∙

research

∙ 07/01/2019

Improving Performance of End-to-End ASR on Numeric Sequences

Recognizing written domain numeric utterances (e.g. I need 1.25.) can be...

2 Cal Peyser, et al. ∙

research

∙ 06/21/2019

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

Contextual automatic speech recognition, i.e., biasing recognition towar...

0 Ke Hu, et al. ∙

Tara N. Sainath

Featured Co-authors