Minimum Bayes Risk Training for End-to-End Speaker-Attributed ASR

Clicks: 125
ID: 282327
2020
Free PDF
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This article has not been analysed, so there is no overall score — reader engagement is measured and shown alongside.
AI Quality Assessment
Not analyzed
Readership in this journal
Steady

Ranked #32 of 803 articles by views in arXiv

Most read Least read

Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 803 in total.

Mint this article as an NFT
Not yet minted

Create a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.

5 SUSD one-off · no wallet required
Sign in to mint
Abstract
Recently, an end-to-end speaker-attributed automatic speech recognition (E2E SA-ASR) model was proposed as a joint model of speaker counting, speech recognition and speaker identification for monaural overlapped speech. In the previous study, the model parameters were trained based on the speaker-attributed maximum mutual information (SA-MMI) criterion, with which the joint posterior probability for multi-talker transcription and speaker identification are maximized over training data. Although SA-MMI training showed promising results for overlapped speech consisting of various numbers of speakers, the training criterion was not directly linked to the final evaluation metric, i.e., speaker-attributed word error rate (SA-WER). In this paper, we propose a speaker-attributed minimum Bayes risk (SA-MBR) training method where the parameters are trained to directly minimize the expected SA-WER over the training data. Experiments using the LibriSpeech corpus show that the proposed SA-MBR training reduces the SA-WER by 9.0 % relative compared with the SA-MMI-trained model.
Reference Key
yoshioka2020minimum Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Naoyuki Kanda; Zhong Meng; Liang Lu; Yashesh Gaur; Xiaofei Wang; Zhuo Chen; Takuya Yoshioka
Journal arXiv
Year 2020
DOI
DOI not found
URL
http://arxiv.org/abs/2011.02921v1
Keywords
cs.cl eess.as cs.sd

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.