Incremental Lattice Determinization for WFST Decoders

Zhehuai Chen, Mahsa Yarmohammadi, Hainan Xu, Hang Lv, Lei Xie, Daniel Povey, Sanjeev Khudanpur

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

We introduce a lattice determinization algorithm that can operate incrementally. That is, a word-level lattice can be generated for a partial utterance and then, once we have processed more audio, we can obtain a word-level lattice for the extended utterance without redoing all the work of lattice determinization. This is relevant for ASR decoders such as those used in Kaldi, which first generate a state-level lattice and then convert it to a word-level lattice using a determinization algorithm in a special semiring. Our incremental determinization algorithm is useful when word-level lattices are needed prior to the end of the utterance, and also reduces the latency due to determinization at the end of the utterance.

源语言英语
主期刊名2019 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019 - Proceedings
出版商Institute of Electrical and Electronics Engineers Inc.
1-7
页数7
ISBN(电子版)9781728103068
DOI
出版状态已出版 - 12月 2019
活动2019 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019 - Singapore, 新加坡
期限: 15 12月 201918 12月 2019

出版系列

姓名2019 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019 - Proceedings

会议

会议2019 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019
国家/地区新加坡
Singapore
时期15/12/1918/12/19

指纹

探究 'Incremental Lattice Determinization for WFST Decoders' 的科研主题。它们共同构成独一无二的指纹。

引用此