Title :
A statistical method for database reduction for embedded unit selection speech synthesis
Author :
Tsiakoulis, Pirros ; Chalamandaris, Aimilios ; Karabetsos, Sotiris ; Raptis, Spyros
Author_Institution :
Inst. for Language & Speech Process., Athens
fDate :
March 31 2008-April 4 2008
Abstract :
This paper presents a new method for the reduction of an existing speech database in order to be used for domain independent embedded unit selection text-to-speech synthesis. The method relies on statistical data produced by the unit selection process on a large text corpus. It utilizes the selection frequency, as well as the actual score of each unit. Both objective and subjective evaluation of the method is performed in comparison with existing similar techniques.
Keywords :
audio databases; speech synthesis; statistical analysis; database reduction; embedded unit selection speech synthesis; large text corpus; speech database; statistical method; text-to-speech synthesis; Clustering algorithms; Databases; Frequency; Natural languages; Performance evaluation; Space technology; Speech processing; Speech synthesis; Statistical analysis; Synthesizers; embedded text-to-speech (TtS); speech database reduction; unit selection;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on
Conference_Location :
Las Vegas, NV
Print_ISBN :
978-1-4244-1483-3
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2008.4518681