AIConfPaper
← Search

Antoine Bruguier

7 accepted papers

2023

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

Steven M. Hernandez, Ding Zhao, Shaojin Ding, Antoine Bruguier, Rohit Prabhavalkar, Tara N. Sainath +2
ICASSP 2023accepted

Continued improvements in machine learning techniques offer exciting new opportunities through the use of larger models and larger training datasets. However, there is a growing need to offer these new capabilities on-board low-powered devices such as smart-phones, wearables and other embedded envir…

Cited by 13Source ↗Scholar ↗
2022

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

Antoine Bruguier, Duc Le, Rohit Prabhavalkar, Dangna Li, Zhe Liu, Bo Wang +4
ICASSP 2022accepted

We propose Neural-FST Class Language Model (NFCLM) for end-to-end speech recognition, a novel method that combines neural network language models (NNLMs) and finite state transducers (FSTs) in a mathematically consistent framework. Our method utilizes a background NNLM which models generic backgroun…

Cited by 0Source ↗Scholar ↗
2021

Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer

Suyoun Kim, Yuan Shangguan, Jay Mahadeokar, Antoine Bruguier, Christian Fuegen, Michael L. Seltzer +1
ICASSP 2021accepted

Recurrent Neural Network Transducer (RNN-T), like most end-to-end speech recognition model architectures, has an implicit neural network language model (NNLM) and cannot easily leverage unpaired text data during training. Previous work has proposed various fusion methods to incorporate external NNLM…

Cited by 0Source ↗Scholar ↗
2020

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

Tara N. Sainath, Yanzhang He, Bo Li, Arun Narayanan, Ruoming Pang, Antoine Bruguier +22
ICASSP 2020accepted

Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art conventional models with respect to both quality, i.e., word error rate (WER), and latency, i.e., the time the hypothesis is finalized after the user stops speaking. In this paper, we develop a first-pass Recurrent…

Cited by 0Source ↗Scholar ↗
2020

Algorithmic Exploration of American English Dialects

Alëna Aksënova, Antoine Bruguier, Amanda Ritchart-Scott, Uri Mendlovic
ICASSP 2020accepted

In this paper, we use a novel algorithmic approach to explore dialectal variation in American English speech. Without the need for human phonemic annotations, we are able to use an existing corpus transcribed in text form only. Our results show that, in general, American English dialects can be divi…

Cited by 6Source ↗Scholar ↗
2019

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

Antoine Bruguier, Rohit Prabhavalkar, Golan Pundak, Tara N. Sainath
ICASSP 2019accepted

End-to-End (E2E) automatic speech recognition (ASR) systems learn word spellings directly from text-audio pairs, in contrast to traditional ASR systems which incorporate a separate pronunciation lexicon. The lexicon allows a traditional system to correctly spell rare words observed only in LM traini…

Cited by 0Source ↗Scholar ↗
2016

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

Rohit Prabhavalkar, Ouais Alsharif, Antoine Bruguier, Ian McGraw
ICASSP 2016accepted

We study the problem of compressing recurrent neural networks (RNNs). In particular, we focus on the compression of RNN acoustic models, which are motivated by the goal of building compact and accurate speech recognition systems which can be run efficiently on mobile devices. In this work, we presen…

Cited by 0Source ↗Scholar ↗