DocumentCode :
2798694
Title :
HMM-based speech synthesis with unsupervised labeling of accentual context based on F0 quantization and average voice model
Author :
Nose, Takashi ; Ooki, Koujirou ; Kobayashi, Takao
Author_Institution :
Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Yokohama, Japan
fYear :
2010
fDate :
14-19 March 2010
Firstpage :
4622
Lastpage :
4625
Abstract :
This paper proposes an HMM-based speech synthesis technique without any manual labeling of accent information for a target speaker´s training data. To appropriately model the fundamental frequency (F0) feature of speech, the proposed technique uses coarsely quantized F0 symbols instead of accent types for the context-dependent labeling. By using F0 quantization, we can automatically conduct the labeling of F0 contexts for training data. When synthesizing speech, an average voice model trained in advance using manually labeled multiple speakers´ speech data including accent information is used to create the label sequence for synthesis. Specifically, the input text is converted to a full context label sequence, and an F0 contour is generated from the label sequence and the average voice model. Then, a label sequence including the quantized F0 symbols is created from the generated F0 contour. We conduct objective and subjective evaluation tests, and discuss the results.
Keywords :
hidden Markov models; quantisation (signal); speaker recognition; speech synthesis; HMM-based speech synthesis; accentual context; average voice model; context-dependent labeling; hidden Markov model; label sequence; quantization; target speaker training data; unsupervised labeling; Context modeling; Costs; Frequency; Hidden Markov models; Labeling; Loudspeakers; Nose; Quantization; Speech synthesis; Training data; F0 modeling; F0 quantization; HMM-based speech synthesis; average voice model; unsupervised training;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on
Conference_Location :
Dallas, TX
ISSN :
1520-6149
Print_ISBN :
978-1-4244-4295-9
Electronic_ISBN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.2010.5495548
Filename :
5495548
Link To Document :
بازگشت