Search Results for author:
Found 33 papers, 6 papers with code
Extending Multilingual Speech Synthesis to 100+ Languages without Transcribed Data
Without any transcribed speech in a new language, this TTS model can generate intelligible speech in >30 unseen languages (CER difference of <10% to ground truth).
Improving Speech Recognition for African American English With Audio Classification
By combining the classifier output with coarse geographic information, we can select a subset of utterances from a large corpus of untranscribed short-form queries for semi-supervised learning at scale.
Lego-Features: Exporting modular encoder features for streaming and deliberation ASR
Overall, they present a modular, powerful and cheap alternative to the standard encoder output, as well as the N-best hypotheses.
Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
We introduce the Universal Speech Model (USM), a single large model that performs automatic speech recognition (ASR) across 100+ languages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Federated Pruning: Improving Neural Network Efficiency with Federated Learning
Automatic Speech Recognition models require large amount of speech data for training, and the collection of such data often leads to privacy concerns.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Online Model Compression for Federated Learning with Large Models
This paper addresses the challenges of training large neural network models under federated learning settings: high on-device memory usage and communication cost.
Extracting Targeted Training Data from ASR Models, and How to Mitigate It
We design Noise Masking, a fill-in-the-blank style method for extracting targeted parts of training data from trained ASR models.
Production federated keyword spotting via distillation, filtering, and joint federated-centralized training
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.
Handling Compounding in Mobile Keyboard Input
This paper proposes a framework to improve the typing experience of mobile users in morphologically rich languages.
Revealing and Protecting Labels in Distributed Training
Prior works have demonstrated that labels can be revealed analytically from the last layer of certain models (e. g., ResNet), or they can be reconstructed jointly with model inputs by using Gradients Matching [Zhu et al'19] with additional knowledge about the current state of the model.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Partial Variable Training for Efficient On-Device Federated Learning
This paper aims to address the major challenges of Federated Learning (FL) on edge devices: limited memory and expensive communication.
Exploring Heterogeneous Characteristics of Layers in ASR Models for More Efficient Training
Transformer-based architectures have been the subject of research aimed at understanding their overparameterization and the non-uniform importance of their layers.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition
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 yield an even better recognition result.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Incremental Layer-wise Self-Supervised Learning for Efficient Speech Domain Adaptation On Device
These models are typically trained on the server using transcribed speech data.
Large-scale ASR Domain Adaptation using Self- and Semi-supervised Learning
Self- and semi-supervised learning methods have been actively investigated to reduce labeled training data or enhance the model performance.
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 speech recognition (ASR) models pre-trained using large, diverse unlabeled datasets containing approximately a million hours of audio.
Ranked #1 on
Speech Recognition
on Common Voice
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
On-Device Personalization of Automatic Speech Recognition Models for Disordered Speech
While current state-of-the-art Automatic Speech Recognition (ASR) systems achieve high accuracy on typical speech, they suffer from significant performance degradation on disordered speech and other atypical speech patterns.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
A Method to Reveal Speaker Identity in Distributed ASR Training, and How to Counter It
We show that a dropout rate of 0. 2 can reduce the speaker identity accuracy to 0% top-1 (0. 5% top-5).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Training Production Language Models without Memorizing User Data
This paper presents the first consumer-scale next-word prediction (NWP) model trained with Federated Learning (FL) while leveraging the Differentially Private Federated Averaging (DP-FedAvg) technique.
Understanding Unintended Memorization in Federated Learning
In this paper, we initiate a formal study to understand the effect of different components of canonical FL on unintended memorization in trained models, comparing with the central learning setting.
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 improving both privacy and accuracy of the models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entities
With speech input, if the user corrects only the names, the name recall rate improves to 64. 4%.
Writing Across the World's Languages: Deep Internationalization for Gboard, the Google Keyboard
Today, Gboard supports 900+ language varieties across 70+ writing systems, and this report describes how and why we have been adding support for hundreds of language varieties from around the globe.
Federated Evaluation of On-device Personalization
Federated learning is a distributed, on-device computation framework that enables training global models without exporting sensitive user data to servers.
Federated Learning of N-gram Language Models
The n-gram language models trained with federated learning are compared to n-grams trained with traditional server-based algorithms using A/B tests on tens of millions of users of virtual keyboard.
An Investigation Into On-device Personalization of End-to-end Automatic Speech Recognition Models
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.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Federated Learning for Emoji Prediction in a Mobile Keyboard
We show that a word-level recurrent neural network can predict emoji from text typed on a mobile keyboard.
Federated Learning Of Out-Of-Vocabulary Words
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 vocabulary of a virtual keyboard for smartphones without exporting sensitive text to servers.
Applied Federated Learning: Improving Google Keyboard Query Suggestions
Federated learning is a distributed form of machine learning where both the training data and model training are decentralized.
Federated Learning for Mobile Keyboard Prediction
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 keyboard for smartphones.
Mobile Keyboard Input Decoding with Finite-State Transducers
We describe the general framework of what we call for short the keyboard "FST decoder" as well as the implementation details that are new compared to a speech FST decoder.
Fast and Accurate Recurrent Neural Network Acoustic Models for Speech Recognition
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 recognition.
Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition
However, in contrast to the deep neural networks, the use of RNNs in speech recognition has been limited to phone recognition in small scale tasks.
