Multi-reference WER for evaluating ASR for languages with no orthographic rules

Ahmed Ali, Walid Magdy, Peter Bell, Steve Renais

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

13 Citations (Scopus)

Abstract

Languages with no standard orthographic representation faces a challenge to evaluate the output from Automatic Speech Recognition (ASR). Since the reference transcription text can vary widely from one user to another. We propose an innovative approach for evaluating speech recognition using Multi-References. For each recognized speech segments, we ask five different users to transcribe the speech. We combine the alignment for the multiple references, and use the combined alignment to report a modified version of Word Error Rate (WER). This approach is in favor of accepting a recognized word if any of the references typed it in the same form. Results are reported using two Dialectal Arabic (DA) as a language with no standard orthographic; Egyptian, and North African speech. The average WER for the five references individually is 71.4%, and 80.1% respectively. When considering all references combined, the Multi-References MR-WER was found to be 39.7%, and 45.9% respectively.

Original languageEnglish
Title of host publication2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages576-580
Number of pages5
ISBN (Electronic)9781479972913
DOIs
Publication statusPublished - 10 Feb 2016
EventIEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015 - Scottsdale, United States
Duration: 13 Dec 201517 Dec 2015

Publication series

Name2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015 - Proceedings

Conference

ConferenceIEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015
Country/TerritoryUnited States
CityScottsdale
Period13/12/1517/12/15

Keywords

  • Under-Resource
  • WER

Fingerprint

Dive into the research topics of 'Multi-reference WER for evaluating ASR for languages with no orthographic rules'. Together they form a unique fingerprint.

Cite this