Automatic Evaluation of Synthesized Speech (CROSBI ID 553567)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Martinčić– Ipšić, Sanda ; Pobar, Miran ; Ipšić, Ivo
engleski
Automatic Evaluation of Synthesized Speech
This paper presents the development of a Croatian text-to-speech (TTS) system capable of synthesizing speech from arbitrary text. For speech generation Pitch Synchronous Overlap and Add (PSOLA) and Hidden Markov Models (HMM) based methods were used. The generated Croatian speech was evaluated subjectively by the mean opinion score (MOS) of the 40 evaluators and objectively by the automatic speech recognition (ASR) system. In the paper we propose an evaluation approach which combines objective and subjective evaluation results.
speech synthesis; Hidden Markov Models; diphone speech synthesis; PSOLA; MOS evaluation; ASR
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
305-310.
2009.
objavljeno
Podaci o matičnoj publikaciji
Proceedings of the 31st International Conference on Information Technology Interfaces (ITI 2009)
Luzar-Stiffler, Vesna ; Jarec, I. ; Bekić, Zoran
Zagreb: Sveučilišni računski centar Sveučilišta u Zagrebu (Srce)
978-953-7138-15-8
1330-1012
Podaci o skupu
31st International Conference on Information Technology Interfaces (31 ; 2009)
predavanje
22.06.2009-25.06.2009
Dubrovnik, Hrvatska; Cavtat, Hrvatska