hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.2498/cit.1001049

An Efficient Unit-Selection Method for Concatenative Text-to-Speech Synthesis Systems

Zganec Mario
Jerneja Zganec Gros

Puni tekst: engleski, pdf (517 KB) str. 69-78 preuzimanja: 874* citiraj
APA 6th Edition
Mario, Z. i Zganec Gros, J. (2008). An Efficient Unit-Selection Method for Concatenative Text-to-Speech Synthesis Systems. Journal of computing and information technology, 16 (1), 69-78. https://doi.org/10.2498/cit.1001049
MLA 8th Edition
Mario, Zganec i Jerneja Zganec Gros. "An Efficient Unit-Selection Method for Concatenative Text-to-Speech Synthesis Systems." Journal of computing and information technology, vol. 16, br. 1, 2008, str. 69-78. https://doi.org/10.2498/cit.1001049. Citirano 27.02.2021.
Chicago 17th Edition
Mario, Zganec i Jerneja Zganec Gros. "An Efficient Unit-Selection Method for Concatenative Text-to-Speech Synthesis Systems." Journal of computing and information technology 16, br. 1 (2008): 69-78. https://doi.org/10.2498/cit.1001049
Harvard
Mario, Z., i Zganec Gros, J. (2008). 'An Efficient Unit-Selection Method for Concatenative Text-to-Speech Synthesis Systems', Journal of computing and information technology, 16(1), str. 69-78. https://doi.org/10.2498/cit.1001049
Vancouver
Mario Z, Zganec Gros J. An Efficient Unit-Selection Method for Concatenative Text-to-Speech Synthesis Systems. Journal of computing and information technology [Internet]. 2008 [pristupljeno 27.02.2021.];16(1):69-78. https://doi.org/10.2498/cit.1001049
IEEE
Z. Mario i J. Zganec Gros, "An Efficient Unit-Selection Method for Concatenative Text-to-Speech Synthesis Systems", Journal of computing and information technology, vol.16, br. 1, str. 69-78, 2008. [Online]. https://doi.org/10.2498/cit.1001049

Sažetak
This paper presents a method for selecting speech units for polyphone concatenative speech synthesis, in which the simplification of procedures for search paths in a graph accelerated the speed of the unit-selection procedure with minimum effects on the speech quality. The speech units selected are still optimal; only the costs of merging the units on which the selection is based are less accurately determined. Due to its low processing power and memory footprint requirements, the method is suitable for use in embedded speech synthesizers.

Hrčak ID: 44607

URI
https://hrcak.srce.hr/44607

Posjeta: 1.044 *