Performance Improvement of Probabilistic Transcriptions with Language-specific Constraints

Xiang Kong, Preethi Jyothi, Mark Allan Hasegawa-Johnson

Research output: Contribution to journalConference article

Abstract

This article describes a method for reducing the error rate of probabilistic phone-based transcriptions resulting from mismatched crowdsourcing by using language-specific constraints to post-process the phone sequence. In the scenario under consideration, there are no native-language transcriptions or pronunciation dictionary available in the test language; instead, available resources include non-native transcriptions, a rudimentary rule-based G2P, and a list of orthographic word forms mined from the internet. The proposed solution post-processes non-native transcriptions by converting them to test-language orthography, composing with testlanguage word forms, then converting back to a phone string. Experiments demonstrate that the phone error rate of the transcription is reduced, using this method, by 22% on an independent evaluation-test dataset.

Original languageEnglish (US)
Pages (from-to)30-36
Number of pages7
JournalProcedia Computer Science
Volume81
DOIs
StatePublished - Jan 1 2016
Event5th Workshop on Spoken Language Technologies for Under-resourced languages, SLTU 2016 - Yogyakarta, Indonesia
Duration: May 9 2016May 12 2016

    Fingerprint

Keywords

  • G2P
  • automatic speech recognition resources
  • mismatched crowdsourcing
  • probabilistic transcription

ASJC Scopus subject areas

  • Computer Science(all)

Cite this