Autosegmental neural nets: Should phones and tones be synchronous or asynchronous?

Research output: Contribution to journalConference articlepeer-review

Abstract

Phones, the segmental units of the International Phonetic Alphabet (IPA), are used for lexical distinctions in most human languages; Tones, the suprasegmental units of the IPA, are used in perhaps 70%. Many previous studies have explored cross-lingual adaptation of automatic speech recognition (ASR) phone models, but few have explored the multilingual and cross-lingual transfer of synchronization between phones and tones. In this paper, we test four Connectionist Temporal Classification (CTC)-based acoustic models, differing in the degree of synchrony they impose between phones and tones. Models are trained and tested multilingually in three languages, then adapted and tested cross-lingually in a fourth. Both synchronous and asynchronous models are effective in both multilingual and cross-lingual settings. Synchronous models achieve lower error rate in the joint phone+tone tier, but asynchronous training results in lower tone error rate.

Original languageEnglish (US)
Pages (from-to)1027-1031
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume2020-October
DOIs
StatePublished - 2020
Externally publishedYes
Event21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020 - Shanghai, China
Duration: Oct 25 2020Oct 29 2020

Keywords

  • Asynchronous training of tones and phones
  • CTC
  • IPA
  • Tones
  • Under-resourced languages

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modeling and Simulation

Fingerprint Dive into the research topics of 'Autosegmental neural nets: Should phones and tones be synchronous or asynchronous?'. Together they form a unique fingerprint.

Cite this