Paper Info
Title
Advanced Unsupervised Joint Prosody Labeling And Modeling For Mandarin Speech And Its Application To Prosody Generation For Tts
Abstract
Motivated by the success of the unsupervised joint prosody labeling and modeling (UJPLM) method for Mandarin speech on modeling of syllable pitch contour in our previous study, in this paper, the advanced UJPLM (A-UJPLM) method is proposed based on UJPLM to jointly label prosodic tags and model syllable pitch contour, duration and energy level. Experimental results on the Sinica Treebank corpus showed that most prosodic tags labeled were linguistically meaningful and the model parameters estimated were interpretable and generally agreed with other previous study. In virtue of the functions given by the model parameters, an application of A-UJPLM to the prosody generation for Mandarin TTS is proposed. Experimental results showed that the proposed method performed well. Most predicted prosodic features matched well to their original counterparts. This also reconfirmed the effectiveness of the A-UJPLM method.
Year
Venue
Keywords
2009
INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5
prosody modeling, prosody labeling, prosody generation, text-to-speech system
Field
DocType
Citations 
Prosody,Computer science,Speech recognition,Artificial intelligence,Natural language processing,Mandarin Chinese
Conference
2
PageRank 
References 
Authors
0.38
1
3
Name
Order
Citations
PageRank
Chen-Yu Chiang13111.55
Sin-Horng Chen227339.86
Yih-Ru Wang323734.68