Coping imbalanced prosodic unit boundary detection with linguistically-motivated prosodic features

Yi Fen Liu*, Shu Chuan Tseng, J. S.Roger Jang, C. H.Alvin Chen

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Continuous speech input for ASR processing is usually presegmented into speech stretches by pauses. In this paper, we propose that smaller, prosodically defined units can be identified by tackling the problem on imbalanced prosodic unit boundary detection using five machine learning techniques. A parsimonious set of linguistically motivated prosodic features has been proven to be useful to characterize prosodic boundary information. Furthermore, BMPM is prone to have true positive rate on the minority class, i.e. the defined prosodic units. As a whole, the decision tree classifier, C4.5, reaches a more stable performance than the other algorithms.

Original languageEnglish
Title of host publicationProceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010
PublisherInternational Speech Communication Association
Pages1417-1420
Number of pages4
Publication statusPublished - 2010
Externally publishedYes

Publication series

NameProceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

Keywords

  • Biased minimax probability machine
  • Machine learning
  • Prosodic unit

ASJC Scopus subject areas

  • Language and Linguistics
  • Speech and Hearing

Fingerprint

Dive into the research topics of 'Coping imbalanced prosodic unit boundary detection with linguistically-motivated prosodic features'. Together they form a unique fingerprint.

Cite this