1.1k citations · 2.8k across the 23 of their papers we have counts for
24 papers
Mixture-of-Expert Conformer for Streaming Multilingual ASR
Ke Hu, Bo Li, Tara N. Sainath +2
End-to-end models with large capacity have significantly improved multilingual automatic speech recognition, but their computation cost poses challenges for on-device applications.…
Efficient Domain Adaptation for Speech Foundation Models
Bo Li, Dongseong Hwang, Zhouyuan Huo +8
Foundation models (FMs), that are trained on broad data at scale and are adaptable to a wide range of downstream tasks, have brought large interest in the research community. Benef…
Online Model Compression for Federated Learning with Large Models
Tien-Ju Yang, Yonghui Xiao, Giovanni Motta +3
This paper addresses the challenges of training large neural network models under federated learning settings: high on-device memory usage and communication cost. The proposed Onli…
Production federated keyword spotting via distillation, filtering, and joint federated-centralized training
Andrew Hard, Kurt Partridge, Neng Chen +9
We trained a keyword spotting model using federated learning on real user devices and observed significant improvements when the model was deployed for inference on phones. To comp…
Partial Variable Training for Efficient On-Device Federated Learning
Tien-Ju Yang, Dhruv Guliani, Françoise Beaufays +1
This paper aims to address the major challenges of Federated Learning (FL) on edge devices: limited memory and expensive communication. We propose a novel method, called Partial Va…
Enabling On-Device Training of Speech Recognition Models with Federated Dropout
Dhruv Guliani, Lillian Zhou, Changwan Ryu +5
Federated learning can be used to train machine learning models on the edge on local data that never leave devices, providing privacy by default. This presents a challenge pertaini…
Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition
Tsendsuren Munkhdalai, Khe Chai Sim, Angad Chandorkar +4
Fast contextual adaptation has shown to be effective in improving Automatic Speech Recognition (ASR) of rare words and when combined with an on-device personalized training, it can…
Exploring Heterogeneous Characteristics of Layers in ASR Models for More Efficient Training
Lillian Zhou, Dhruv Guliani, Andreas Kabel +2
Transformer-based architectures have been the subject of research aimed at understanding their overparameterization and the non-uniform importance of their layers. Applying these a…
Large-scale ASR Domain Adaptation using Self- and Semi-supervised Learning
Dongseong Hwang, Ananya Misra, Zhouyuan Huo +7
Self- and semi-supervised learning methods have been actively investigated to reduce labeled training data or enhance the model performance. However, the approach mostly focus on i…
Training Speech Recognition Models with Federated Learning: A Quality/Cost Framework
Dhruv Guliani, Francoise Beaufays, Giovanni Motta
We propose using federated learning, a decentralized on-device learning paradigm, to train speech recognition models. By performing epochs of training on a per-user basis, federate…
Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer
Yuan Shangguan, Kate Knister, Yanzhang He +2
The demand for fast and accurate incremental speech recognition increases as the applications of automatic speech recognition (ASR) proliferate. Incremental speech recognizers outp…
Low-rank Gradient Approximation For Memory-Efficient On-device Training of Deep Neural Network
Mary Gooneratne, Khe Chai Sim, Petr Zadrazil +3
Training machine learning models on mobile devices has the potential of improving both privacy and accuracy of the models. However, one of the major obstacles to achieving this goa…
Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entities
Khe Chai Sim, Françoise Beaufays, Arnaud Benard +9
We study the effectiveness of several techniques to personalize end-to-end speech models and improve the recognition of proper names relevant to the user. These techniques differ i…
Writing Across the World's Languages: Deep Internationalization for Gboard, the Google Keyboard
Daan van Esch, Elnaz Sarbar, Tamar Lucassen +6
This technical report describes our deep internationalization program for Gboard, the Google Keyboard. Today, Gboard supports 900+ language varieties across 70+ writing systems, an…
Federated Evaluation of On-device Personalization
Kangkang Wang, Rajiv Mathews, Chloé Kiddon +3
Federated learning is a distributed, on-device computation framework that enables training global models without exporting sensitive user data to servers. In this work, we describe…
Federated Learning of N-gram Language Models
Mingqing Chen, Ananda Theertha Suresh, Rajiv Mathews +4
We propose algorithms to train production-quality n-gram language models using federated learning. Federated learning is a distributed computation platform that can be used to trai…
An Investigation Into On-device Personalization of End-to-end Automatic Speech Recognition Models
Khe Chai Sim, Petr Zadrazil, Françoise Beaufays
Speaker-independent speech recognition systems trained with data from many users are generally robust against speaker variability and work well for a large population of speakers.…
Federated Learning Of Out-Of-Vocabulary Words
Mingqing Chen, Rajiv Mathews, Tom Ouyang +1
We demonstrate that a character-level recurrent neural network is able to learn out-of-vocabulary (OOV) words under federated learning settings, for the purpose of expanding the vo…
Applied Federated Learning: Improving Google Keyboard Query Suggestions
Timothy Yang, Galen Andrew, Hubert Eichner +5
Federated learning is a distributed form of machine learning where both the training data and model training are decentralized. In this paper, we use federated learning in a commer…
Federated Learning for Mobile Keyboard Prediction
Andrew Hard, Kanishka Rao, Rajiv Mathews +6
We train a recurrent neural network language model using a distributed, on-device learning framework called federated learning for the purpose of next-word prediction in a virtual…
Mobile Keyboard Input Decoding with Finite-State Transducers
Tom Ouyang, David Rybach, Françoise Beaufays +1
We propose a finite-state transducer (FST) representation for the models used to decode keyboard inputs on mobile devices. Drawing from learnings from the field of speech recogniti…
Personalized Speech recognition on mobile devices
Ian McGraw, Rohit Prabhavalkar, Raziel Alvarez +8
We describe a large vocabulary speech recognition system that is accurate, has low latency, and yet has a small enough memory and computational footprint to run faster than real-ti…
Fast and Accurate Recurrent Neural Network Acoustic Models for Speech Recognition
Haşim Sak, Andrew Senior, Kanishka Rao +1
We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech re…
Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition
Haşim Sak, Andrew Senior, Françoise Beaufays
Long Short-Term Memory (LSTM) is a recurrent neural network (RNN) architecture that has been designed to address the vanishing and exploding gradient problems of conventional RNNs.…