research
∙
05/25/2023
Mixture-of-Expert Conformer for Streaming Multilingual ASR
End-to-end models with large capacity have significantly improved multil...
share
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-...
research
∙
03/02/2023
Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
We introduce the Universal Speech Model (USM), a single large model that...
research
∙
09/14/2022
Federated Pruning: Improving Neural Network Efficiency with Federated Learning
Automatic Speech Recognition models require large amount of speech data ...
research
∙
05/06/2022
Online Model Compression for Federated Learning with Large Models
This paper addresses the challenges of training large neural network mod...
research
∙
04/18/2022
Extracting Targeted Training Data from ASR Models, and How to Mitigate It
Recent work has designed methods to demonstrate that model updates in AS...
research
∙
04/11/2022
Production federated keyword spotting via distillation, filtering, and joint federated-centralized training
We trained a keyword spotting model using federated learning on real use...
research
∙
01/17/2022
Handling Compounding in Mobile Keyboard Input
This paper proposes a framework to improve the typing experience of mobi...
research
∙
10/31/2021
Revealing and Protecting Labels in Distributed Training
Distributed learning paradigms such as federated learning often involve ...
research
∙
10/11/2021
Partial Variable Training for Efficient On-Device Federated Learning
This paper aims to address the major challenges of Federated Learning (F...
research
∙
10/08/2021
Exploring Heterogeneous Characteristics of Layers in ASR Models for More Efficient Training
Transformer-based architectures have been the subject of research aimed ...
research
∙
10/07/2021
Enabling On-Device Training of Speech Recognition Models with Federated Dropout
Federated learning can be used to train machine learning models on the e...
research
∙
10/05/2021
Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition
Fast contextual adaptation has shown to be effective in improving Automa...
research
∙
10/01/2021
Large-scale ASR Domain Adaptation using Self- and Semi-supervised Learning
Self- and semi-supervised learning methods have been actively investigat...
research
∙
10/01/2021
Incremental Layer-wise Self-Supervised Learning for Efficient Speech Domain Adaptation On Device
Streaming end-to-end speech recognition models have been widely applied ...
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...
research
∙
06/18/2021
On-Device Personalization of Automatic Speech Recognition Models for Disordered Speech
While current state-of-the-art Automatic Speech Recognition (ASR) system...
research
∙
04/15/2021
A Method to Reveal Speaker Identity in Distributed ASR Training, and How to Counter It
End-to-end Automatic Speech Recognition (ASR) models are commonly traine...
research
∙
10/29/2020
Training Speech Recognition Models with Federated Learning: A Quality/Cost Framework
We propose using federated learning, a decentralized on-device learning ...
research
∙
09/21/2020
Training Production Language Models without Memorizing User Data
This paper presents the first consumer-scale next-word prediction (NWP) ...
research
∙
06/12/2020
Understanding Unintended Memorization in Federated Learning
Recent works have shown that generative sequence models (e.g., language ...
research
∙
06/02/2020
Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer
The demand for fast and accurate incremental speech recognition increase...
research
∙
01/24/2020
Low-rank Gradient Approximation For Memory-Efficient On-device Training of Deep Neural Network
Training machine learning models on mobile devices has the potential of ...
research
∙
12/14/2019
Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entities
We study the effectiveness of several techniques to personalize end-to-e...
research
∙
12/03/2019
Writing Across the World's Languages: Deep Internationalization for Gboard, the Google Keyboard
This technical report describes our deep internationalization program fo...
research
∙
10/22/2019
Federated Evaluation of On-device Personalization
Federated learning is a distributed, on-device computation framework tha...
research
∙
10/08/2019
Federated Learning of N-gram Language Models
We propose algorithms to train production-quality n-gram language models...
research
∙
09/14/2019
An Investigation Into On-device Personalization of End-to-end Automatic Speech Recognition Models
Speaker-independent speech recognition systems trained with data from ma...
research
∙
06/11/2019
Federated Learning for Emoji Prediction in a Mobile Keyboard
We show that a word-level recurrent neural network can predict emoji fro...
research
∙
03/26/2019
Federated Learning Of Out-Of-Vocabulary Words
We demonstrate that a character-level recurrent neural network is able t...
research
∙
12/07/2018
Applied Federated Learning: Improving Google Keyboard Query Suggestions
Federated learning is a distributed form of machine learning where both ...
research
∙
11/08/2018
Federated Learning for Mobile Keyboard Prediction
We train a recurrent neural network language model using a distributed, ...
research
∙
04/13/2017
Mobile Keyboard Input Decoding with Finite-State Transducers
We propose a finite-state transducer (FST) representation for the models...
research
∙
03/10/2016
Personalized Speech recognition on mobile devices
We describe a large vocabulary speech recognition system that is accurat...
research
∙
07/24/2015
Fast and Accurate Recurrent Neural Network Acoustic Models for Speech Recognition
We have recently shown that deep Long Short-Term Memory (LSTM) recurrent...
research
∙
02/05/2014