b'George Saon'

research

∙ 09/19/2023

Semi-Autoregressive Streaming ASR With Label Context

Non-autoregressive (NAR) modeling has gained significant interest in spe...

0 Siddhant Arora, et al. ∙

research

∙ 09/07/2023

Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems

Transferring the knowledge of large language models (LLMs) is a promisin...

0 Takuma Udagawa, et al. ∙

research

∙ 02/27/2023

Diagonal State Space Augmented Transformers for Speech Recognition

We improve on the popular conformer architecture by replacing the depthw...

0 George Saon, et al. ∙

research

∙ 08/03/2022

VQ-T: RNN Transducers using Vector-Quantized Prediction Network States

Beam search, which is the dominant ASR decoding algorithm for end-to-end...

0 Jiatong Shi, et al. ∙

research

∙ 07/28/2022

Extending RNN-T-based speech recognition systems with emotion and language classification

Speech transcription, emotion recognition, and language identification a...

0 Zvi Kons, et al. ∙

research

∙ 06/16/2022

Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization

We report on aggressive quantization strategies that greatly accelerate ...

0 Andrea Fasoli, et al. ∙

research

∙ 04/01/2022

Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems

Large-scale language models (LLMs) such as GPT-2, BERT and RoBERTa have ...

0 Takuma Udagawa, et al. ∙

research

∙ 03/29/2022

Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing

We introduce two techniques, length perturbation and n-best based label ...

0 Xiaodong Cui, et al. ∙

research

∙ 02/26/2022

Towards Reducing the Need for Speech Training Data To Build Spoken Language Understanding Systems

The lack of speech data annotated with labels required for spoken langua...

0 Samuel Thomas, et al. ∙

research

∙ 02/26/2022

Integrating Text Inputs For Training and Adapting RNN Transducer ASR Models

Compared to hybrid automatic speech recognition (ASR) systems that use a...

0 Samuel Thomas, et al. ∙

research

∙ 01/28/2022

Improving End-to-End Models for Set Prediction in Spoken Language Understanding

The goal of spoken language understanding (SLU) systems is to determine ...

0 Hong-Kwang J. Kuo, et al. ∙

research

∙ 10/21/2021

Asynchronous Decentralized Distributed Training of Acoustic Models

Large-scale distributed training of deep acoustic models plays an import...

9 Xiaodong Cui, et al. ∙

research

∙ 10/04/2021

Towards efficient end-to-end speech recognition with biologically-inspired neural networks

Automatic speech recognition (ASR) is a capability which enables a progr...

0 Thomas Bohnstingl, et al. ∙

research

∙ 08/27/2021

4-bit Quantization of LSTM-based Speech Recognition Models

We investigate the impact of aggressive low-precision representations of...

0 Andrea Fasoli, et al. ∙

research

∙ 08/24/2021

Reducing Exposure Bias in Training Recurrent Neural Network Transducers

When recurrent neural network transducers (RNNTs) are trained using the ...

0 Xiaodong Cui, et al. ∙

research

∙ 08/18/2021

Integrating Dialog History into End-to-End Spoken Language Understanding Systems

End-to-end spoken language understanding (SLU) systems that process huma...

13 Jatin Ganhotra, et al. ∙

research

∙ 05/03/2021

On the limit of English conversational speech recognition

In our previous work we demonstrated that a single headed attention enco...

0 Zoltán Tüske, et al. ∙

research

∙ 04/08/2021

RNN Transducer Models For Spoken Language Understanding

We present a comprehensive study on building and adapting RNN transducer...

0 Samuel Thomas, et al. ∙

research

∙ 03/17/2021

Advancing RNN Transducer Technology for Speech Recognition

We investigate a set of techniques for RNN Transducers (RNN-Ts) that wer...

0 George Saon, et al. ∙

research

∙ 02/24/2020

Distributed Training of Deep Neural Network Acoustic Models for Automatic Speech Recognition

The past decade has witnessed great progress in Automatic Speech Recogni...

0 Xiaodong Cui, et al. ∙

research

∙ 02/04/2020

Improving Efficiency in Large-Scale Decentralized Distributed Training

Decentralized Parallel SGD (D-PSGD) and its asynchronous variant Asynchr...

16 Wei Zhang, et al. ∙

research

∙ 01/20/2020

Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard-300

It is generally believed that direct sequence-to-sequence (seq2seq) spee...

0 Zoltán Tüske, et al. ∙

research

∙ 08/09/2019

Challenging the Boundaries of Speech Recognition: The MALACH Corpus

There has been huge progress in speech recognition over the last several...

0 Michael Picheny, et al. ∙

research

∙ 07/10/2019

A Highly Efficient Distributed Deep Learning System For Automatic Speech Recognition

Modern Automatic Speech Recognition (ASR) systems rely on distributed de...

8 Wei Zhang, et al. ∙

research

∙ 04/30/2019

English Broadcast News Speech Recognition by Humans and Machines

With recent advances in deep learning, considerable attention has been g...

0 Samuel Thomas, et al. ∙

research

∙ 04/10/2019

Distributed Deep Learning Strategies For Automatic Speech Recognition

In this paper, we propose and investigate a variety of distributed deep ...

0 Wei Zhang, et al. ∙

research

∙ 12/08/2017

Building competitive direct acoustics-to-word models for English conversational speech recognition

Direct acoustics-to-word (A2W) models in the end-to-end paradigm have re...

0 Kartik Audhkhasi, et al. ∙

research

∙ 10/17/2017

Embedding-Based Speaker Adaptive Training of Deep Neural Networks

An embedding-based speaker adaptive training (SAT) approach is proposed ...

0 Xiaodong Cui, et al. ∙

research

∙ 09/19/2017

Language Modeling with Highway LSTM

Language models (LMs) based on Long Short Term Memory (LSTM) have shown ...

0 Gakuto Kurata, et al. ∙

research

∙ 03/22/2017

Direct Acoustics-to-Word Models for English Conversational Speech Recognition

Recent work on end-to-end automatic speech recognition (ASR) has shown t...

0 Kartik Audhkhasi, et al. ∙

research

∙ 03/06/2017

English Conversational Telephone Speech Recognition by Humans and Machines

One of the most difficult speech recognition tasks is accurate recogniti...

0 George Saon, et al. ∙

research

∙ 04/27/2016

The IBM 2016 English Conversational Telephone Speech Recognition System

We describe a collection of acoustic and language modeling techniques th...

0 George Saon, et al. ∙

research

∙ 09/05/2013

Improvements to deep convolutional neural networks for LVCSR

Deep Convolutional Neural Networks (CNNs) are more powerful than Deep Ne...

0 Tara N. Sainath, et al. ∙

George Saon

Featured Co-authors