Name
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. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1109/ISCSLP.2010.5684863 | ISCSLP |
Keywords | Field | DocType |
duration,speech corpus,corpus,prosody model,natural languages,statistical based duration,chinese speech synthesis,fundamental frequency,five degree tone model,speech synthesis,straight algorithm,lanzhou dialect conversion,mandarin,dialect conversion,pause duration model,mathematical model,speech,time frequency analysis,statistical analysis,computational modeling,mean opinion score | Speech corpus,Speech synthesis,Computer science,Chinese speech synthesis,Mean opinion score,Speech recognition,Frequency conversion,Mandarin Chinese,Statistical analysis | Conference |
Volume | Issue | ISBN |
null | null | 978-1-4244-6244-5 |
Citations | PageRank | References |
0 | 0.34 | 1 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yang Hongwu | 1 | 16 | 14.32 |
| Weitong Guo | 2 | 2 | 1.08 |
| Dong Pei | 3 | 0 | 0.34 |
| Qingqing Liang | 4 | 9 | 1.54 |