Integrating a fast speech corpus in unit selection speech synthesis: Experiments on perception, segmentation and duration prediction
Moers D, Wagner P, Möbius B, Müllers F, Jauk I (2010)
In: Proceedings of Speech Prosody 2010. P2a-28.
Konferenzbeitrag
| Veröffentlicht | Englisch
Download
Autor*in
Moers, Donata;
Wagner, PetraUniBi 
;
Möbius, Bernd;
Müllers, Filip;
Jauk, Igor
;
Möbius, Bernd;
Müllers, Filip;
Jauk, IgorEinrichtung
Abstract / Bemerkung
This paper examines viable paths for integrating a fast speech corpus into a unit selection synthesis system. After selecting a suitable speaker, two inventories were recorded: one at normal and one at fast speech rate articulated as accurately as possible. A perceptual evaluation showed that for ultra fast speech rate, stimuli generated from fast utterances were judged to be as intelligible as stimuli generated from normal rate utterances; moreover, they were clearly preferred with respect to naturalness. Based on the results of an automatic phone segmentation which produced only marginal differences in label timing accuracy, CART based duration prediction models for both corpora were built. Prediction accuracy was very similar. We concluded that automatic phone segmentation and CART based duration prediction are applicable to both normal and fast rate recordings.
Stichworte
biphonetics
Erscheinungsjahr
2010
Titel des Konferenzbandes
Proceedings of Speech Prosody 2010
Seite(n)
P2a-28
Urheberrecht / Lizenzen
Konferenz
Speech Prosody 2010
Konferenzort
Chicago
Page URI
https://pub.uni-bielefeld.de/record/1917158
Zitieren
Moers D, Wagner P, Möbius B, Müllers F, Jauk I. Integrating a fast speech corpus in unit selection speech synthesis: Experiments on perception, segmentation and duration prediction. In: Proceedings of Speech Prosody 2010. 2010: P2a-28.
Moers, D., Wagner, P., Möbius, B., Müllers, F., & Jauk, I. (2010). Integrating a fast speech corpus in unit selection speech synthesis: Experiments on perception, segmentation and duration prediction. Proceedings of Speech Prosody 2010, P2a-28.
Moers, Donata, Wagner, Petra, Möbius, Bernd, Müllers, Filip, and Jauk, Igor. 2010. “Integrating a fast speech corpus in unit selection speech synthesis: Experiments on perception, segmentation and duration prediction”. In Proceedings of Speech Prosody 2010, P2a-28.
Moers, D., Wagner, P., Möbius, B., Müllers, F., and Jauk, I. (2010). “Integrating a fast speech corpus in unit selection speech synthesis: Experiments on perception, segmentation and duration prediction” in Proceedings of Speech Prosody 2010 P2a-28.
Moers, D., et al., 2010. Integrating a fast speech corpus in unit selection speech synthesis: Experiments on perception, segmentation and duration prediction. In Proceedings of Speech Prosody 2010. pp. P2a-28.
D. Moers, et al., “Integrating a fast speech corpus in unit selection speech synthesis: Experiments on perception, segmentation and duration prediction”, Proceedings of Speech Prosody 2010, 2010, pp.P2a-28.
Moers, D., Wagner, P., Möbius, B., Müllers, F., Jauk, I.: Integrating a fast speech corpus in unit selection speech synthesis: Experiments on perception, segmentation and duration prediction. Proceedings of Speech Prosody 2010. p. P2a-28. (2010).
Moers, Donata, Wagner, Petra, Möbius, Bernd, Müllers, Filip, and Jauk, Igor. “Integrating a fast speech corpus in unit selection speech synthesis: Experiments on perception, segmentation and duration prediction”. Proceedings of Speech Prosody 2010. 2010. P2a-28.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Creative Commons Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 International (CC BY-NC-ND 4.0):
Volltext(e)
Name
Access Level
Open Access
Zuletzt Hochgeladen
2019-09-06T08:57:11Z
MD5 Prüfsumme
ce253d9b59b4779176b979245d5cdebf
Google Scholar