arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.00851cs.CL
收藏

一种基于语言分值的多语种语音识别输出选择方法

A language score based output selection method for multilingual speech recognition

Vingroup Big Data Institute(Vingroup大数据研究院)

Van Huy Nguyen, Thi Quynh Khanh Dinh, Truong Thinh Nguyen, Dang Khoa Mac

摘要:

如果输入语言是指定的,则多语言语音识别系统的质量可以通过自适应方法来改善。对于可以接受多语言输入的系统,流行的方法是将语言标识符应用于输入,然后在下一步中切换或配置解码器,或者使用多一个子序列模型从一组候选中选择输出。为了减少实时应用的延迟,本文首先采用语言模型重评分方法产生所有可能的目标语言候选,然后提出一种简单的评分方法来自动选择输出,而不需要输入语言的任何标识符模型或语言规范。主要的一点是,这个分数可以简单和自动估计的飞行,使整个解码流水线更简单和紧凑。实验结果表明,该方法可以达到与指定输入语言相同的质量。此外,我们提出了设计一个英语和越南语端到端模型,以处理不仅跨语言的扬声器的问题,但也作为一种解决方案,以提高英语在越南语中的借用词的准确性。

英文摘要:

The quality of a multilingual speech recognition system can be improved by adaptation methods if the input language is specified. For systems that can accept multilingual inputs, the popular approach is to apply a language identifier to the input then switch or configure decoders in the next step, or use one more subsequence model to select the output from a set of candidates. Motivated by the goal of reducing the latency for real-time applications, in this paper, a language model rescoring method is firstly applied to produce all possible candidates for target languages, then a simple score is proposed to automatically select the output without any identifier model or language specification of the input language. The main point is that this score can be simply and automatically estimated on-the-fly so that the whole decoding pipeline is more simple and compact. Experimental results showed that this method can achieve the same quality as when the input language is specified. In addition, we present to design an English and Vietnamese End-to-End model to deal with not only the problem of cross-lingual speakers but also as a solution to improve the accuracy of borrowed words of English in Vietnamese.

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。

↑