C4.5: programs for machine learning
C4.5: programs for machine learning
Prosody-based automatic segmentation of speech into sentences and topics
Speech Communication - Special issue on accessing information in spoken audio
Integrating prosodic and lexical cues for automatic topic segmentation
Computational Linguistics
Prosody-based topic segmentation for Mandarin broadcast news
HLT-NAACL-Short '04 Proceedings of HLT-NAACL 2004: Short Papers
A Heuristic Approach to Caption Enhancement for Effective Video OCR
ICIC '08 Proceedings of the 4th international conference on Intelligent Computing: Advanced Intelligent Computing Theories and Applications - with Aspects of Theoretical and Methodological Issues
Subword Lexical Chaining for Automatic Story Segmentation in Chinese Broadcast News
PCM '08 Proceedings of the 9th Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
A Subword Normalized Cut Approach to Automatic Story Segmentation of Chinese Broadcast News
AIRS '09 Proceedings of the 5th Asia Information Retrieval Symposium on Information Retrieval Technology
Multi-scale TextTiling for automatic story segmentation in Chinese broadcast news
AIRS'08 Proceedings of the 4th Asia information retrieval conference on Information retrieval technology
Information Sciences: an International Journal
Hi-index | 0.00 |
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 tone-normalized 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.