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 encoder of the model on a large unlabeled multilingual dataset of 12 million (M) hours spanning over 300 languages, and fine-tuning on a smaller labeled dataset. We use multilingual pre-training with random-projection quantization and speech-text modality matching to achieve state-of-the-art performance on downstream multilingual ASR and speech-to-text translation tasks. We also demonstrate that despite using a labeled training set 1/7-th the size of that used for the Whisper model, our model exhibits comparable or better performance on both in-domain and out-of-domain speech recognition tasks across many languages.
@article{arxiv.2303.01037,
title = {Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages},
author = {Yu Zhang and Wei Han and James Qin and Yongqiang Wang and Ankur Bapna and Zhehuai Chen and Nanxin Chen and Bo Li and Vera Axelrod and Gary Wang and Zhong Meng and Ke Hu and Andrew Rosenberg and Rohit Prabhavalkar and Daniel S. Park and Parisa Haghani and Jason Riesa and Ginger Perng and Hagen Soltau and Trevor Strohman and Bhuvana Ramabhadran and Tara Sainath and Pedro Moreno and Chung-Cheng Chiu and Johan Schalkwyk and Françoise Beaufays and Yonghui Wu},
journal= {arXiv preprint arXiv:2303.01037},
year = {2023}
}