DocumentCode
431245
Title
Scalable Concatenative Speech Synthesis Based on the Plural Unit Selection and Fusion Method
Author
Tamura, Masatsune ; Mizutani, Tatsuya ; Kagoshima, Takehiko
Author_Institution
Multimedia Lab., Toshiba Corp., Kawasaki, Japan
Volume
1
fYear
2005
fDate
March 18-23, 2005
Firstpage
361
Lastpage
364
Keywords
sensor fusion; speech synthesis; very large databases; concatenative speech synthesis; fusion method; half-size waveform database; high-quality speech synthesis; large databases; offline unit fusion; pitch-cycle waveforms; plural unit selection; scalable concatenative speech synthesizer; voiced segments; Computational efficiency; Cost function; Fusion power generation; Laboratories; Multimedia databases; Natural languages; Research and development; Scalability; Speech synthesis; Synthesizers;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on
ISSN
1520-6149
Print_ISBN
0-7803-8874-7
Type
conf
DOI
10.1109/ICASSP.2005.1415125
Filename
1415125
Link To Document