Ensemble And Re-Ranking Based On Language Models To Improve ASR

Shu Fen Tsai*, Shih Chan Kuo, Ren Yuan Lyu, Jyh Shing Roger Jang*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We propose a strategy to improve speech recognition by selecting appropriate words to form new sentences using ensemble learning. Use traditional speech recognition methods first, and then rescore using different neural language models. Second, the decoding results of five different rescoring models were selected to select words. The choice of words is based on the importance of each word and whether the position of the word is correct. In the selection of word importance, the judgment method is majority weight and cumulative weight, and shift alignment and longest common subsequence alignment are used to determine word positions. And then the selected word representatives are reorganized to create new sentences. We compare the results of sentence ensemble and rescoring. As shown in the Aishell-1 test data, an error reduction rate of 7.30% can be achieved, verifying the effectiveness of the proposed method.

Original languageEnglish
Title of host publication2022 13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022
EditorsKong Aik Lee, Hung-yi Lee, Yanfeng Lu, Minghui Dong
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages185-189
Number of pages5
ISBN (Electronic)9798350397963
DOIs
StatePublished - 2022
Event13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022 - Singapore, Singapore
Duration: 11 12 202214 12 2022

Publication series

Name2022 13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022

Conference

Conference13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022
Country/TerritorySingapore
CitySingapore
Period11/12/2214/12/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

  • automatic speech recognition
  • lattice rescoring
  • neural language models
  • re-ranking
  • sentence ensemble

Fingerprint

Dive into the research topics of 'Ensemble And Re-Ranking Based On Language Models To Improve ASR'. Together they form a unique fingerprint.

Cite this