Generation of fundamental frequency contours for Mandarin speech synthesis based on tone nucleus model

A new method for generating sentence F0 contours of Mandarin speech is proposed. The method assumes the F0 contour generation process model, but generates the tone and phrase components in different ways and sums them to produce a sentence F0 contour. The tone component is generated concatenating F0 patterns of tone nuclei, which are predicted by a corpus-based scheme (binary decision trees). Experiments of F0 contour generation were conducted by using 100 news utterances by a female speaker. The results showed that the method could generate F0 contours close to those of target speech. A perceptual evaluation was also conducted on the synthetic speech using the F0 contours generated by the method. An average score of 4.5 in a 5-point scale indicates the high naturalness, verifying the validity of the method.

[1]  Keikichi Hirose,et al.  Analysis and modeling of tonal features in polysyllabic words and sentences of the standard Chinese , 1990, ICSLP.

[2]  Keikichi Hirose,et al.  Synthesis of fundamental FDrequency contours of standard Chinese sentences from tone sandhi and focus conditions , 2000, INTERSPEECH.

[3]  Keikichi Hirose,et al.  A System for the Synthesis of High-Quality Speech from Texts on General Weather Conditions (Special Section on Speech Synthesis: Current Technologies and Equipment) , 1993 .

[4]  Keikichi Hirose,et al.  Automatic Extraction of Tone Command Parameters for the Model of F0 Contour Generation for Standard Chinese , 2004, IEICE Trans. Inf. Syst..

[5]  Keikichi Hirose,et al.  A method for automatic extraction of model parameters from fundamental frequency contours of speech , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6]  Keikichi Hirose,et al.  Analysis of voice fundamental frequency contours for declarative sentences of Japanese , 1984 .

[7]  Sin-Horng Chen,et al.  An RNN-based prosodic information synthesizer for Mandarin text-to-speech , 1998, IEEE Trans. Speech Audio Process..

[8]  Keikichi Hirose,et al.  Tone nucleus modeling for Chinese lexical tone recognition , 2004, Speech Commun..

[9]  Lianhong Cai,et al.  Clustering and feature learning based F0 prediction for Chinese speech synthesis , 2002, INTERSPEECH.

[10]  Sumio Ohno,et al.  Analysis of fundamental frequency contours of standard Chinese in terms of the command-response model and its application to synthesis by rule of intonation , 2000, INTERSPEECH.