BATŮŠEK, Robert. Symbolic Segment Dissimilarity Measure and Its Applications in Speech Synthesis. In Proceedings of IEEE Workshop on Speech Synthesis. Santa Monica, USA: UCLA, 2002, s. 1-4.
Další formáty:   BibTeX LaTeX RIS
Základní údaje
Originální název Symbolic Segment Dissimilarity Measure and Its Applications in Speech Synthesis
Název anglicky Symbolic Segment Dissimilarity Measure and Its Applications in Speech Synthesis
Autoři BATŮŠEK, Robert (203 Česká republika, garant).
Vydání Santa Monica, USA, Proceedings of IEEE Workshop on Speech Synthesis, s. 1-4, 2002.
Nakladatel UCLA
Další údaje
Originální jazyk čeština
Typ výsledku Stať ve sborníku
Obor 20206 Computer hardware and architecture
Stát vydavatele Spojené státy
Utajení není předmětem státního či obchodního tajemství
Kód RIV RIV/00216224:14330/02:00006531
Organizační jednotka Fakulta informatiky
UT WoS 000185236800032
Klíčová slova anglicky speech synthesis; segment dissimilarity
Štítky segment dissimilarity, Speech synthesis
Změnil Změnil: Mgr. Robert Batůšek, učo 2999. Změněno: 15. 5. 2003 09:42.
Anotace
This paper presents a novel method for determining a measure of dissimilarity of symbolic representations of speech segments. It is supposed that these symbolic representations can be completely derived from text, e.g. using a text analysis component of a text-to-speech synthesiser. An analysis is made to evaluate the correspondence of the particular symbolic features with the acoustic variability. A final dissimilarity measure is designed so that to maximise the correspondence with the selected acoustic measure. The designed measure is applied to the problem of sentence selection for the speech synthesis voice databases.
Anotace anglicky
This paper presents a novel method for determining a measure of dissimilarity of symbolic representations of speech segments. It is supposed that these symbolic representations can be completely derived from text, e.g. using a text analysis component of a text-to-speech synthesiser. An analysis is made to evaluate the correspondence of the particular symbolic features with the acoustic variability. A final dissimilarity measure is designed so that to maximise the correspondence with the selected acoustic measure. The designed measure is applied to the problem of sentence selection for the speech synthesis voice databases.
Návaznosti
MSM 143300003, záměrNázev: Interakce člověka s počítačem, dialogové systémy a asistivní technologie
Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, Interakce člověka s počítačem, dialogové systémy a asistivní technologie
VytisknoutZobrazeno: 21. 5. 2024 22:53