Mandarin to Lanzhou dialect conversion based on Five Degree Tone Model

摘要

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 ƒ0 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.