We propose a novel approach to optimizing a byte-level representation for end-to-end automatic speech recognition (ASR). Byte-level representation is often used by large scale multilingual ASR systems when the character set of the supported languages is large. The compactness and universality of byte-level representation allow the ASR models to use smaller output vocabularies and therefore, provide more flexibility. UTF-8 is a commonly used byte-level representation for multilingual ASR, but it is not designed to optimize machine learning tasks directly. By using auto-encoder and vector quantization, we show that we can optimize a byte-level representation for ASR and achieve better accuracy. Our proposed framework can incorporate information from different modalities, and provides an error correction mechanism. In an English/Mandarin dictation task, we show that a bilingual ASR model built with this approach can outperform UTF-8 representation by 5% relative in error rate.
@article{arxiv.2406.09676,
title = {Optimizing Byte-level Representation for End-to-end ASR},
author = {Roger Hsiao and Liuhui Deng and Erik McDermott and Ruchir Travadi and Xiaodan Zhuang},
journal= {arXiv preprint arXiv:2406.09676},
year = {2024}
}