Title :
An investigation on the Mandarin prosody of a parallel multi-speaking rate speech corpus
Author :
Chiang, Chen-Yu ; Tang, Cheng-Chang ; Yu, Hsiu-Min ; Wang, Yih-Ru ; Chen, Sin-Horng
Author_Institution :
Dept. of Commun. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan
Abstract :
In this paper, the prosody of a parallel multispeaking rate Mandarin read speech corpus is investigated. The corpus contains four parallel speech datasets uttered by a female professional announcer with various speech rates (SRs) of 4.40 (fast), 3.82 (normal), 2.97 (median) and 2.45 (slow) syllables/second. By using the unsupervised joint prosody labeling and modeling (PLM) method proposed previously, the relationship between SR and various prosodic features, including pause duration, patterns of three high level prosodic constituents, and the break labels, are investigated. The analyses reported in this study could be very informative in developing prosody generation mechanism for text-to-speech and prosody modeling for automatic speech recognition in various SRs.
Keywords :
hidden Markov models; speech processing; speech synthesis; Mandarin prosody investigation; PLM method; automatic speech recognition; break label; female professional announcer; high level prosodic constituents pattern; parallel multispeaking rate Mandarin read speech corpus; parallel speech dataset; pause duration; prosody generation mechanism; text-to-speech modelling; unsupervised joint prosody modeling; varying speech rate; Automatic speech recognition; Databases; Hidden Markov models; Labeling; Natural languages; Speech analysis; Speech synthesis; Strontium;
Conference_Titel :
Speech Database and Assessments, 2009 Oriental COCOSDA International Conference on
Conference_Location :
Urumqi
Print_ISBN :
978-1-4244-4400-7
Electronic_ISBN :
978-1-4244-4400-7
DOI :
10.1109/ICSDA.2009.5278360
