Abstract
Speech intelligibility is the most important parameter in evaluation of speech quality. In the contribution, a new objective intelligibility assessment of general speech processing algorithms is proposed. It is based on automatic recognition methods developed for discrete and fluent speech processing. The idea is illustrated on two case studies: a) comparison of listening evaluation of Czech rhyme tests with automatic discrete speech recognition and b) automatic continuous speech recognition of general topic Czech texts read by professional and nonprofessional speakers vs. the same texts generated by several Czech Text-to-Speech systems. The aim of the proposed approach is fast and objective intelligibility assessment of Czech Text-to-Speech systems, which include male and female voices and a voice conversion module.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Deller, J.R., Hansen, J.H.L., Proakis, J.G.: Discrete-Time Processing of Speech Signals. IEEE Press, N. York (2000)
Jekosch, U.: Voice and Speech Quality Perception, Assessment and Evaluation. Springer, Berlin (2005)
Mahdi, A.E.: Voice Quality Measurement in Modern Telecommunication Networks. In: CD Proceedings of the 6th EURASIP Conference Focused on Speech & Image Processing, Multimedia Communications & Services (EC-SIPMCS), Maribor, Slovenia, June 27-30, pp. 29–36 (2007)
Loizou, P.: C. Speech Enhancement. Theory and Practice. CRC Press, London (2007)
Nouza, J., Vích, R., Vondra, M.: Can ASR be Used for Evaluating Speech Quality? In: Vích, R. (ed.) Proceedings of the 17th Czech-German Workshop Speech Processing, Prague, pp. 115–121 (2007)
Vích, R., Nouza, J.: Application of Speech Recognition and Rhyme Tests for Assessement of Czech Speech Processing Systems. In: Duběda, T., Vlčková, J. (eds.) Proceedings of the 2nd Czech-Slovak Conference ISPhS, Karolinum, Prague, pp. 141–151 (2007)
Červa, P., Nouza, J.: Design and Development of Voice Controlled Aids for Motor-Handicapped Persons. In: Proceedings of Interspeech, pp. 2521–2524. Antwerp (2007)
Nouza, J., Žďánský, J., Červa, P., Kolorenč, J.: A System for Information Retrieval from Large Records of Broadcast Programs. In: Text, Speech and Dialogue. Lecture Notes in Artificial Intelligence, LNAI, vol. 4188, pp. 401–408. Springer, Berlin (2006)
Přibil, J., Přibilová, A.: Czech TTS Engine for BraillePen Device Based on Pocket PC Platform. In: Vích, R. (ed.) Proceedings of the 16th Conference Electronic Speech Signal Processing joined with the 15th Czech-German Workshop Speech Processing, Prague, pp. 402–408 (2005)
Přibilová, A., Přibil, J.: Nonlinear Frequency Scale Mapping for Voice Conversion in Text-to-Speech System with Cepstral Description. Speech Communication 48, 1691–1703 (2006)
Hanika, J., Horák, P.: Epos – A New Approach to Speech Synthesis. In: Proceedings of the First Workshop on Text, Speech and Dialogue – TSD 1998, Brno, pp. 51–54 (1998)
Horák, P., Hesounová, A.: Czech Triphone Synthesis of Female Voice. In: Vích, R. (ed.) Proceedings of the 11th Czech-German Workshop Speech Processing, Prague, pp. 32–33 (2001)
Horák, P., Hanika, J.: Epos Text-to-Speech System (2007), http://epos.ufe.cz/
Vondra, M., Vích, R.: Speech Identity Conversion. In: Chollet, G., Esposito, A., Faúndez-Zanuy, M., Marinaro, M. (eds.) Nonlinear Speech Modeling and Applications. LNCS (LNAI), vol. 3445, pp. 421–426. Springer, Heidelberg (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Vích, R., Nouza, J., Vondra, M. (2008). Automatic Speech Recognition Used for Intelligibility Assessment of Text-to-Speech Systems. In: Esposito, A., Bourbakis, N.G., Avouris, N., Hatzilygeroudis, I. (eds) Verbal and Nonverbal Features of Human-Human and Human-Machine Interaction. Lecture Notes in Computer Science(), vol 5042. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-70872-8_10
Download citation
DOI: https://doi.org/10.1007/978-3-540-70872-8_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-70871-1
Online ISBN: 978-3-540-70872-8
eBook Packages: Computer ScienceComputer Science (R0)