In this work, to measure the accuracy and efficiency for a latency-controlled streaming automatic speech recognition (ASR) application, we perform comprehensive evaluations on three popular training criteria: LF-MMI, CTC and RNN-T. In transcribing social media videos of 7 languages with training data 3K-14K hours, we conduct large-scale controlled experimentation across each criterion using identical datasets and encoder model architecture. We find that RNN-T has consistent wins in ASR accuracy, while CTC models excel at inference efficiency. Moreover, we selectively examine various modeling strategies for different training criteria, including modeling units, encoder architectures, pre-training, etc. Given such large-scale real-world streaming ASR application, to our best knowledge, we present the first comprehensive benchmark on these three widely used training criteria across a great many languages.
@article{arxiv.2011.04785,
title = {Benchmarking LF-MMI, CTC and RNN-T Criteria for Streaming ASR},
author = {Xiaohui Zhang and Frank Zhang and Chunxi Liu and Kjell Schubert and Julian Chan and Pradyot Prakash and Jun Liu and Ching-Feng Yeh and Fuchun Peng and Yatharth Saraf and Geoffrey Zweig},
journal= {arXiv preprint arXiv:2011.04785},
year = {2020}
}
Comments
Accepted for publication at IEEE Spoken Language Technology Workshop (SLT), 2021