Evidence of Phonological Processes in Automatic Recognition of Children’s Speech

Evangelia Fringi, Jill Lehman, Martin Russell

Research output: Contribution to conference (unpublished)Paperpeer-review

Abstract

Automatic speech recognition (ASR) for children’s speech is
more difficult than for adults’ speech. A plausible explanation
is that ASR errors are due to predictable phonological effects
associated with language acquisition. We describe phone recognition
experiments on hand labelled data for children aged between
5 and 9. A comparison of the resulting confusion matrices
with those for adult speech (TIMIT) shows increased phone
substitution rates for children, which correspond to some extent
to established phonological phenomena. However these errors
still only account for a relatively small proportion of the issue.
This suggests that attempts to improve ASR accuracy on children’s
speech by accommodating these phenomena, for example
by changing the pronunciation dictionary, cannot solve the
whole problem.
Original languageEnglish
Number of pages4
Publication statusPublished - 2015
EventInterspeech, 2015 - Dresden, Germany
Duration: 6 Sep 2015 → …

Conference

ConferenceInterspeech, 2015
Country/TerritoryGermany
CityDresden
Period6/09/15 → …

Keywords

  • children’s speech, phonological processes, automatic

Fingerprint

Dive into the research topics of 'Evidence of Phonological Processes in Automatic Recognition of Children’s Speech'. Together they form a unique fingerprint.

Cite this