Search Results for author:
Found 17 papers, 1 papers with code
Pseudo Label Is Better Than Human Label
State-of-the-art automatic speech recognition (ASR) systems are trained with tens of thousands of hours of labeled speech data.
Joint Unsupervised and Supervised Training for Multilingual ASR
Our average WER of all languages outperforms average monolingual baseline by 33. 3%, and the state-of-the-art 2-stage XLSR by 32%.
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.
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.
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.
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.
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%.
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.
Streaming End-to-end Speech Recognition For Mobile Devices
End-to-end (E2E) models, which directly predict output character sequences given input speech, are good candidates for on-device speech recognition.
Toward domain-invariant speech recognition via large scale training
More importantly, such models generalize better to unseen conditions and allow for rapid adaptation -- we show that by using as little as 10 hours of data from a new domain, an adapted domain-invariant model can match performance of a domain-specific model trained from scratch using 70 times as much data.
Understanding Recurrent Neural State Using Memory Signatures
We demonstrate this method's usefulness in revealing information divergence in the bases of recurrent factorized kernels, visualizing the character-level differences between the memory of n-gram and recurrent language models, and extracting knowledge of history encoded in the layers of grapheme-based end-to-end ASR networks.
Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Model
Sequence-to-sequence models provide a simple and elegant solution for building speech recognition systems by folding separate components of a typical system, namely acoustic (AM), pronunciation (PM) and language (LM) models into a single neural network.
