Personalization of speech models on mobile devices (on-device personalization) is an active area of research, but more often than not, mobile devices have more text-only data than paired audio-text data. We explore training a personalized language model on text-only data, used during inference to improve speech recognition performance for that user. We experiment on a user-clustered LibriSpeech corpus, supplemented with personalized text-only data for each user from Project Gutenberg. We release this User-Specific LibriSpeech (UserLibri) dataset to aid future personalization research. LibriSpeech audio-transcript pairs are grouped into 55 users from the test-clean dataset and 52 users from test-other. We are able to lower the average word error rate per user across both sets in streaming and nonstreaming models, including an improvement of 2.5 for the harder set of test-other users when streaming.
Cite
@article{arxiv.2207.00706,
title = {UserLibri: A Dataset for ASR Personalization Using Only Text},
author = {Theresa Breiner and Swaroop Ramaswamy and Ehsan Variani and Shefali Garg and Rajiv Mathews and Khe Chai Sim and Kilol Gupta and Mingqing Chen and Lara McConnaughey},
journal= {arXiv preprint arXiv:2207.00706},
year = {2022}
}
Comments
Accepted for publication in Interspeech 2022. 9 total pages with appendix, 9 total tables, 5 total figures