Combined use of speaker-and tone-normalized pitch reset with pause duration for automatic story segmentation in Mandarin broadcast news

Lei Xie, Chuan Liu, Helen Meng

Research output: Contribution to conferencePaperpeer-review

13 Scopus citations

Abstract

This paper investigates the combined use of pause duration and pitch reset for automatic story segmentation in Mandarin broadcast news. Analysis shows that story boundaries cannot be clearly discriminated from utterance boundaries by speaker-normalized pitch reset due to its large variations across different syllable tone pairs. Instead, speaker- and tonenormalized pitch reset can provide a clear separation between utterance and story boundaries. Experiments using decision trees for story boundary detection reinforce that raw and speaker-normalized pitch resets are not effective for Mandarin Chinese story segmentation. Speaker- and tone-normalized pitch reset is a good story boundary indicator. When it is combined with pause duration, a high F-measure of 86.7% is achieved. Analysis of the decision tree uncovered four major heuristics that show how speakers jointly utilize pause duration and pitch reset to separate speech into stories.

Original languageEnglish
Pages193-196
Number of pages4
StatePublished - 2007
Externally publishedYes
Event2007 Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, NAACL-HLT 2007 - Rochester, United States
Duration: 22 Apr 200727 Apr 2007

Conference

Conference2007 Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, NAACL-HLT 2007
Country/TerritoryUnited States
CityRochester
Period22/04/0727/04/07

Fingerprint

Dive into the research topics of 'Combined use of speaker-and tone-normalized pitch reset with pause duration for automatic story segmentation in Mandarin broadcast news'. Together they form a unique fingerprint.

Cite this