Abstract
The paper proposes a general, flexible and efficient method for the distribution of time-scale modification Factors. The method is inspired by the analogy with a sequence of springs with different rates/constants, allowing simple and straightforward non-linear distribution of modification factors through the speech to modify. The flexibility and generality of the proposed scheme enables its use for any number of speech/sound segment categories of any type and length, while the modification factors can either be set heuristically, ad-hoc, or trained from data. At the end of the paper, an attempt to use statistics of phone durations to set the modification factors is described and discussed.
This research was supported by the Grant Agency of the Czech Republic, project No. GACR 102/09/0989, by the Ministry of Education of the Czech Republic, project No. 2C06020, and by the internal UWB grant, project No. SGS-2010-054.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Huang, Y., Xu, B.: A novel model TD-PSPTP for speech synthesis. In: Proc. EUROSPEECH 1999, Budapest, Hungary, pp. 2303–2306 (1999)
Lawlor, B., Fagan, A.D.: A novel high quality efficient algorithm for time-scale modification of speech. In: Proc. EUROSPEECH 1999, Budapest, Hungary, pp. 2785–2788 (1999)
Kumar, S., Mandal, D., Datta, A.K.: Epoch Synchronous Non Overlap Add (ESNOLA) Method based Concatenative Speech Synthesis System for Bangla. In: Proc. SSW–6, Bonn, Germany (2007)
Verhelst, W., Roelands, M.: An Overlap-Add Technique Based on Waveform Similarity (WSOLA) for High Qquality Time-Scale Modification of Speech. In: Proc. ICASSP, Minneapolis, USA, vol. 2, pp. 554–557 (1993)
Lee, S., Kim, H.D., Kim, H.S.: Variable Time-Scale Modification of Speech Using Transient Information. In: Proc. ICASSP, Munich, Germany, vol. 1, pp. 1319–1322 (1997)
Covell, M., Withgott, M., Slaney, M.: MACH1: Non Uniform Time-Scale Modification of Speech. In: Proc. ICASSP, Seattle, USA, vol. 1, pp. 349–352 (1998)
Donnellan, O., Jung, E., Coylem, E.: Speech-Adaptive Time-scale Modification for Computer Assited Language Learning. In: Proc. ICALT 2003, Aix-en-Provence, France, pp. 165–169 (2003)
Demol, M., Verhelst, W., Struyve, K., Verhoeve, P.: Efcient non-uniform time-scaling of speech with WSOLA. In: Proc. SPECOM, Patras, Greece, pp. 163–166 (2005)
Verhelst, W.: Overlap-add Methods for Time-Scaling of Speech. Speech Communication 30(4), 207–221 (2000)
Hanzlíček, Z., Matoušek, J., Tihelka, D.: Towards automatic audio track generation for Czech TV broadcasting: Initial experiments with subtitles-to-speech synthesis. In: Proc. ICSP, Beijing, China, vol. 3, pp. 2721–2724 (2008)
Matoušek, J., Romportl, J.: Automatic Pitch-Synchronous Phonetic Segmentation. In: Proc. Interspeech, Brisbane, Australia, pp. 1626–1629 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tihelka, D., Méner, M. (2011). Generalized Non-uniform Time Scaling Distribution Method for Natural-Sounding Speech Rate Change. In: Habernal, I., Matoušek, V. (eds) Text, Speech and Dialogue. TSD 2011. Lecture Notes in Computer Science(), vol 6836. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23538-2_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-23538-2_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23537-5
Online ISBN: 978-3-642-23538-2
eBook Packages: Computer ScienceComputer Science (R0)