DocumentCode
2017216
Title
Mandarin to Lanzhou dialect conversion based on Five Degree Tone Model
Author
Yang, Hong-wu ; Guo, Wei-Tong ; Pei, Dong ; Liang, Qing-Qing
Author_Institution
Coll. of Phys. & Electron. Eng., Northwest Normal Univ., Lanzhou, China
fYear
2010
fDate
Nov. 29 2010-Dec. 3 2010
Firstpage
387
Lastpage
391
Abstract
Dialect conversion is one of the most important aspects of Chinese speech synthesis. A Lanzhou dialect corpus has been built based on “word-list in dialectal survey” for the conversion of Lanzhou dialect from Mandarin. Speech corpus was recorded with contrastive (Lanzhou dialect vs. Mandarin) recordings. Five Degrees Tone Model based f0 models and statistical based duration and pause duration model were built for Lanzhou Dialect by analyzing the differences of pitch, duration and pause duration between Lanzhou dialect and Mandarin. Lanzhou dialect was converted from Mandarin by STRAIGHT algorithm. Subjective experiments demonstrated that the converted monosyllables, disyllables and sentences achieve 4.17, 4.22 and 3.55 of the average mean opinion score.
Keywords
natural languages; speech synthesis; Chinese speech synthesis; Lanzhou dialect conversion; Mandarin; STRAIGHT algorithm; five degree tone model; pause duration model; speech corpus; statistical based duration; Analytical models; Computational modeling; Frequency conversion; Mathematical model; Speech; Statistical analysis; Time frequency analysis; corpus; dialect conversion; duration; fundamental frequency; prosody model;
fLanguage
English
Publisher
ieee
Conference_Titel
Chinese Spoken Language Processing (ISCSLP), 2010 7th International Symposium on
Conference_Location
Tainan
Print_ISBN
978-1-4244-6244-5
Type
conf
DOI
10.1109/ISCSLP.2010.5684863
Filename
5684863
Link To Document