164 citations · 339 across the 12 of their papers we have counts for
12 papers
Lego-Features: Exporting modular encoder features for streaming and deliberation ASR
Rami Botros, Rohit Prabhavalkar, Johan Schalkwyk +3
In end-to-end (E2E) speech recognition models, a representational tight-coupling inevitably emerges between the encoder and the decoder. We build upon recent work that has begun to…
Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
Yu Zhang, Wei Han, James Qin +24
We introduce the Universal Speech Model (USM), a single large model that performs automatic speech recognition (ASR) across 100+ languages. This is achieved by pre-training the enc…
Federated Pruning: Improving Neural Network Efficiency with Federated Learning
Rongmei Lin, Yonghui Xiao, Tien-Ju Yang +4
Automatic Speech Recognition models require large amount of speech data for training, and the collection of such data often leads to privacy concerns. Federated learning has been w…
Extracting Targeted Training Data from ASR Models, and How to Mitigate It
Ehsan Amid, Om Thakkar, Arun Narayanan +2
Recent work has designed methods to demonstrate that model updates in ASR training can leak potentially sensitive attributes of the utterances used in computing the updates. In thi…
Handling Compounding in Mobile Keyboard Input
Andreas Kabel, Keith Hall, Tom Ouyang +3
This paper proposes a framework to improve the typing experience of mobile users in morphologically rich languages. Smartphone keyboards typically support features such as input de…
Revealing and Protecting Labels in Distributed Training
Trung Dang, Om Thakkar, Swaroop Ramaswamy +3
Distributed learning paradigms such as federated learning often involve transmission of model updates, or gradients, over a network, thereby avoiding transmission of private data.…
Incremental Layer-wise Self-Supervised Learning for Efficient Speech Domain Adaptation On Device
Zhouyuan Huo, Dongseong Hwang, Khe Chai Sim +5
Streaming end-to-end speech recognition models have been widely applied to mobile devices and show significant improvement in efficiency. These models are typically trained on the…
On-Device Personalization of Automatic Speech Recognition Models for Disordered Speech
Katrin Tomanek, Françoise Beaufays, Julie Cattiau +2
While current state-of-the-art Automatic Speech Recognition (ASR) systems achieve high accuracy on typical speech, they suffer from significant performance degradation on disordere…
A Method to Reveal Speaker Identity in Distributed ASR Training, and How to Counter It
Trung Dang, Om Thakkar, Swaroop Ramaswamy +3
End-to-end Automatic Speech Recognition (ASR) models are commonly trained over spoken utterances using optimization methods like Stochastic Gradient Descent (SGD). In distributed s…
Training Production Language Models without Memorizing User Data
Swaroop Ramaswamy, Om Thakkar, Rajiv Mathews +3
This paper presents the first consumer-scale next-word prediction (NWP) model trained with Federated Learning (FL) while leveraging the Differentially Private Federated Averaging (…
Understanding Unintended Memorization in Federated Learning
Om Thakkar, Swaroop Ramaswamy, Rajiv Mathews +1
Recent works have shown that generative sequence models (e.g., language models) have a tendency to memorize rare or unique sequences in the training data. Since useful models are o…
Federated Learning for Emoji Prediction in a Mobile Keyboard
Swaroop Ramaswamy, Rajiv Mathews, Kanishka Rao +1
We show that a word-level recurrent neural network can predict emoji from text typed on a mobile keyboard. We demonstrate the usefulness of transfer learning for predicting emoji b…