arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.09676eess.AScs.CL
收藏

面向端到端语音识别的字节级表示优化

Optimizing Byte-level Representation for End-to-end ASR

Apple(苹果公司)

Roger Hsiao, Liuhui Deng, Erik McDermott, Ruchir Travadi, Xiaodan Zhuang

AI总结:

本文提出利用自编码器与向量量化优化字节级表示,以提升端到端多语言ASR的准确率,并在英中听写任务中比UTF-8相对降低5%错误率。

摘要:

我们提出了一种优化字节级表示以用于端到端自动语音识别(ASR)的新方法。当所支持语言的字符集很大时,大规模多语言ASR系统通常使用字节级表示。字节级表示的紧凑性和通用性使ASR模型能够使用更小的输出词汇表,从而提供更大的灵活性。UTF-8是多语言ASR中常用的字节级表示,但它并非为直接优化机器学习任务而设计。通过使用自编码器和向量量化,我们表明可以针对ASR优化字节级表示并获得更高的准确率。我们提出的框架能够融合来自不同模态的信息,并提供一种纠错机制。在一项英语/普通话听写任务中,我们展示了使用该方法构建的双语ASR模型在错误率上可比UTF-8表示相对降低5%。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑