arXivDaily arXiv每日学术速递 周一至周五更新
看起来今天可以划水了
arXiv 2106.04897cs.CLcs.SDeess.AS
收藏

无监督自动语音识别研究进展

Unsupervised Automatic Speech Recognition: A Review

UAE University(阿联酋大学);National University of Science & Technology(国家科学技术大学)

Hanan Aldarmaki, Asad Ullah, Nazar Zaki

摘要:

自动语音识别(ASR)系统可以被训练以在给定大量手动转录的语音的情况下实现显著的性能,但是对于所有感兴趣的语言而言,获取大的标记数据集可能是困难的或昂贵的。在本文中,我们回顾了研究文献,以确定可能导致完全无监督ASR的模型和想法,包括语音信号的无监督分割,从语音段到文本的无监督映射,以及具有标称数量的标记示例的半监督模型。这项研究的目的是确定什么可以从语音数据单独学习的局限性,并了解语音识别的最低要求。识别这些限制将有助于优化低资源语言的ASR开发资源和工作。

英文摘要:

Automatic Speech Recognition (ASR) systems can be trained to achieve remarkable performance given large amounts of manually transcribed speech, but large labeled data sets can be difficult or expensive to acquire for all languages of interest. In this paper, we review the research literature to identify models and ideas that could lead to fully unsupervised ASR, including unsupervised segmentation of the speech signal, unsupervised mapping from speech segments to text, and semi-supervised models with nominal amounts of labeled examples. The objective of the study is to identify the limitations of what can be learned from speech data alone and to understand the minimum requirements for speech recognition. Identifying these limitations would help optimize the resources and efforts in ASR development for low-resource languages.

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。

↑