The Role of Nasal Contexts on Quality of Vowel Concatenations
- 1.3k Downloads
This paper deals with the traditional problem of occurrence of audible discontinuities at concatenation points at diphone boundaries in the concatenative speech synthesis. We present results of an analysis of effects of nasal context mismatches on the quality of concatenations in five short Czech vowels. The study was conducted with two voices (one male and one female), and the results suggest that the female voice vowels /a/, /e/ and /o/ are inclined to concatenation discontinuities due to nasalized contexts.
Keywordsspeech synthesis unit selection concatenation cost nasality phase mismatch pitch marks
Unable to display preview. Download preview PDF.
- 2.Bellegarda, J.R.: A novel discontinuity metric for unit selection text-to-speech synthesis. In: SSW5 2004, Pittsburgh, PA, USA, pp. 133–138 (2004)Google Scholar
- 3.Vepa, J.: Join cost for unit selection speech synthesis. Ph.D. thesis, University of Edinburgh (2004)Google Scholar
- 4.Syrdal, A.K.: Phonetic effects on listener detection of vowel concatenation. In: EURO-SPEECH 2001, Aalborg, Denmark, pp. 979–982 (2001)Google Scholar
- 5.Syrdal, A.K., Conkie, A.: Perceptually-based data driven join costs: comparing join types. In: INTERSPEECH 2005, Lisbon, Portugal, pp. 2813–2816 (2005)Google Scholar
- 6.Kawai, H., Tsuzaki, M.: Acoustic measures vs. phonetic features as predictors of audible discontinuity in concatenative speech synthesis. In: ICSLP 2002, pp. 2621–2624. Denver, Colorado (2002)Google Scholar
- 8.Fant, G.: Acoustic theory of speech production. Mouton, The Hague (1960)Google Scholar
- 9.House, A.S., Stevens, K.N.: Analog studies of the nasalization of vowels. J. Speech Hearing Disorders 21, 218–232 (1956)Google Scholar
- 14.Legát, M., Matoušek, J.: Pitch contours as predictors of audible concatenation artifacts. In: Proceedings of the World Congress on Engineering and Computer Science, San Francisco, USA, pp. 525–529 (2011)Google Scholar