An HPM-based prosodic analysis of disfluencies for spontaneous mandarin speech

Cheng Hsien Lin, Chung Long You, Chen Yu Chiang, Yih-Ru Wang, Sin-Horng Chen

Research output: Contribution to journalConference articlepeer-review

1 Scopus citations


This paper presents a prosodic analysis of speech disfluencies on MCDC corpus labelled with two types of prosody tags, syllable-juncture break and syllable prosodic state, by a hierarchical prosodic modeling (HPM) approach proposed previously. The prosodic properties of two major types of speech disfluency, repetition and repair, are explored via examining the prosodic tags labelled on all MCDC utterances. The prosodic phrase structure of a disfluency is analyzed by examining the contextual break types. The prosodic state patterns of prosodic phrases in disfluency are also examined. Lastly, the relation between prosodic properties of disfluencies and their pragmatic functions are discussed.

Original languageEnglish
Pages (from-to)626-630
Number of pages5
JournalProceedings of the International Conference on Speech Prosody
StatePublished - 1 Jan 2018
Event9th International Conference on Speech Prosody, SP 2018 - Poznan, Poland
Duration: 13 Jun 201816 Jun 2018


Dive into the research topics of 'An HPM-based prosodic analysis of disfluencies for spontaneous mandarin speech'. Together they form a unique fingerprint.

Cite this