Title: Enhancements of Viterbi search for fast unit selection synthesis
Other Titles: Vylepšení Viterbiho prohledávání pro rychlou syntézu metodou výběru jednotek
Authors: Tihelka, Daniel
Kala, Jiří
Matoušek, Jindřich
Citation: TIHELKA, Daniel; KALA, Jiří; MATOUŠEK, Jindřích. Enhancements of Viterbi search for fast unit selection synthesis. In: Proceedings of ICSPL 2010: 11th Annual Conference of the International Speech Communication Association 2010, 26-30 September 2010, Makuhari, Chiba, Japan. [Baixas]: ISCA, 2010, p. 174-177. ISSN 1990-9772.
Issue Date: 2010
Publisher: ISCA
Document type: článek
article
URI: http://www.kky.zcu.cz/cs/publications/TihelkaD_2010_Enhancementsof
http://hdl.handle.net/11025/16973
ISSN: 1990-9772
Keywords: syntéza řeči;výběr jednotky;Viterbiho prohledávání
Keywords in different language: speech synthesis;unit selection;Viterbi search
Abstract in different language: The paper describes the optimisation of Viterbi search used in unit selection TTS, since with a large speech corpus necessary to achieve a high level of naturalness, the performance still suffers. To improve the search speed, the combination of sophisticated stopping schemes and pruning thresholds is employed into the baseline search. The optimised search is, moreover, extremely flexible in configuration, requiring only three intuitively comprehensible coefficients to be set. This provides the means for tuning the search depending on device resources, while it allows reaching significant performance increase. To illustrate it, several configuration scenarios, with speed-up ranging from 6 to 58 times, are presented. Their impact on speech quality is verified by CCR listening test, taking into account only the phrases with the highest number of differences when compared to the baseline search.
Rights: © Daniel Tihelka - Jiří Kala - Jindřich Matoušek
Appears in Collections:Články / Articles (NTIS)

Files in This Item:
File Description SizeFormat 
TihelkaD_2010_Enhancementsof.pdfPlný text260,37 kBAdobe PDFView/Open


Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/16973

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.