Title :
Isolated Mandarin syllable recognition with limited training data specially considering the effect of tones
Author :
Lee, Yumin ; Lee, Lin-shan ; Tseng, Chiu-Yu
Author_Institution :
Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
fDate :
1/1/1997 12:00:00 AM
Abstract :
A set of new approaches is proposed to model the Mandarin syllables for accurate recognition with limited training data while specially considering the effect of tones, including improved initial values and state transition topologies, and making use of the durational cue. The results show that these approaches are very useful practically
Keywords :
natural languages; speech processing; speech recognition; durational cue; initial values; isolated Mandarin syllable recognition; limited training data; state transition topologies; tones; Acoustic testing; Databases; Degradation; History; Natural languages; Speech recognition; Topology; Training data; Vocabulary;
Journal_Title :
Speech and Audio Processing, IEEE Transactions on
