In this chapter we discuss modeling of supra-segmental features (intonation and duration) of syllables, and suggest some applications of these models. These supra-segmental features are also termed as prosodic features, and hence the corresponding models are known as prosody models. Neural networks are used to capture the implicit duration and intonation knowledge in the sequence of syllables of an utterance. A four layer feedforward neural network trained with backpropagation algorithm is used for modeling the duration and intonation knowledge of syllables separately. Labeled broadcast news data in the languages Hindi, Telugu and Tamil is used to develop neural network models in order to predict the duration and F0 of syllables in these languages. The input to the neural network consists of a feature vector representing the positional, contextual and phonological constraints. For improving the accuracy of prediction, further processing is done on the predicted values. We also propose a two-stage duration model for improving the accuracy of prediction. The performance of the prosody models is evaluated using objective measures such as average prediction error, standard deviation and correlation coefficient. The prosody models are examined for applications such as speaker recognition, language identification and text-to-speech synthesis.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Huang, X., Acero, A., Hon, H.W.: In: Spoken Language Proceesing. Prentice-Hall, New York, NJ, USA (2001)
Klatt, D.H.: Linguistic uses of segmental duration in English: Acoustic and perceptual evidence. Journal of Acoustic Society of America 59 (1976) 1209-1221
Yegnanarayana, B., Murthy, H.A., Sundar, R., Ramachandran, V.R., Kumar, A.S.M., Alwar, N., Rajendran, S.: Development of text-to-speech system for Indian languages. In: Proceedings of the International Conference on Knowledge Based Computer Systems, Pune, India (1990) 467-476
Chen, S.H., Lai, W.H., Wang, Y.R.: A new duration modeling approach for Mandarin speech. IEEE Transactions on Speech and Audio Processing 11 (2003) 308-320
Mixdorff, H., Jokisch, O.: Building an integrated prosodic model of German. In: Proceeding of the European Conference on Speech Communication and Technology. Volume 2, Aalborg, Denmark (2001) 947-950
Mixdorff, H.: An integrated approach to modeling German prosody. PhD Thesis, Technical University, Dresden, Germany (2002)
Santen, J.P.H.V.: Assignment of segment duration in text-to-speech synthesis. Computer Speech and Language 8 (1994) 95-128
Goubanova, O., Taylor, P.: Using Bayesian belief networks for modeling duration in text-to-speech systems. In: Proceedings of the International Conference on Spoken Language Processing. Volume 2, Beijing, China (2000) 427-431
Sayli, O.: Duration analysis and modeling for Turkish text-to-speech synthesis. Master’s Thesis, Department of Electrical and Electronics Engineering, Bogaziei University (2002)
Riley, M.: Tree-based modeling of segmental durations. Talking Machines: Theories, Models and Designs (1992) 265-273
Haykin, S. In: Neural Networks: A Comprehensive Foundation. Pearson Education Asia, Inc., New Delhi, India (1999)
Yegnanarayana, B. In: Artificial Neural Networks. Prentice-Hall, New Delhi, India (1999)
Campbell, W.N.: Analog i/o nets for syllable timing. Speech Communication 9 (1990) 57-61
Campbell, W.N.: Syllable based segment duration. In: Bailly, G., Benoit, C., Sawallis, T.R., eds.: Talking Machines: Theories, Models and Designs. Elsevier (1992) 211-224
Campbell, W.N.: Predicting segmental durations for accommodation within a syllable-level timing framework. In: Proceedings of the European Conference on Speech Communication and Technology. Volume 2, Berlin, Germany (1993) 1081-1084
Barbosa, P.A., Bailly, G.: Characterization of rhythmic patterns for text-to-speech synthesis. Speech Communication 15 (1994) 127-137
Barbosa, P.A., Bailly, G.: Generating segmental duration by P-centers. In: Proceedings of the Fourth Workshop on Rhythm Perception and Production, Bourges, France (1992) 163-168
Cordoba, R., Vallejo, J.A., Montero, J.M., Gutierrezarriola, J., Lopez, M.A., Pardo, J.M.: Automatic modeling of duration in a Spanish text-to-speech system using neural networks. In: Proceedings of the European Conference on Speech Communication and Technology, Budapest, Hungary (1999)
Hifny, Y., Rashwan, M.: Duration modeling of Arabic text-to-speech synthesis. In: Proceedings of the International Conference on Spoken Language Processing, Denver, Colorado, USA (2002) 1773-1776
Sonntag, G.P., Portele, T., Heuft, B.: Prosody generation with a neural network: Weighing the importance of input parameters. In: Proceedings of the IEEE International Conference on Acoustics, Speech, Signal Processing, Munich, Germany (1997) 931-934
Teixeira, J.P., Freitas, D.: Segmental durations predicted with a neural network. In: Proceedings of the European Conference on Speech Communication and Technology, Geneva, Switzerland (2003) 169-172
Klatt, D.H.: Review of text-to-speech conversion for English. Journal of Acoustic Society of America 82(3) (1987) 737-793
Olive, J.P.: Fundamental frequency rules for the synthesis of simple declarative English sentences. Journal of Acoustic Society of America (1975) 476-482
Fujisaki, H., Hirose, K., Takahashi, N.: Acoustic characteristics and the under-lying rules of the intonation of the common Japanese used by radio and TV anouncers. In: Proceedings of the IEEE International Conference on Acoustics, Speech, Signal Processing (1986) 2039-2042
Taylor, P.A.: Analysis and synthesis of intonation using the Tilt model. Journal of Acoustic Society of America 107 (2000) 1697-1714
Madhukumar, A.S., Rajendran, S., Sekhar, C.C., Yegnanarayana, B.: Synthe-sizing intonation for speech in Hindi. In: Proceedings of the Second European Conference on Speech Communication and Technology. Volume 3, Geneva, Italy (1991) 1153-1156
Pierrehumbert, J.B.: The Phonology and Phonetics of English Intonation. PhD Thesis, MIT, MA, USA (1980)
Fujisaki, H.: Dynamic characteristics of voice fundamental frequency in speech and singing. In: MacNeilage, P.F., ed.: The Production of Speech. Springer-Verlag, New York, USA (1983) 39-55
Fujisaki, H.: A note on the physiological and physical basis for the phrase and accent components in the voice fundamental frequency contour. In: Fujimura, O., ed.: Vocal Physiology: Voice Production, Mechanisms and Functions. Raven Press, New York, USA (1988) 347-355
t'Hart, J., Collier, R., Cohen, A.: A Perceptual Study of Intonation. Cambridge University Press, Cambridge
Cosi, P., Tesser, F., Gretter, R.: Festival speaks Italian. In: Proceedings of EUROSPEECH 2001, Aalborg, Denmark (2001) 509-512
Tesser, F., Cosi, P., Drioli, C., Tisato, G.: Prosodic data driven modeling of a narrative style in Festival TTS. In: Fifth ESCA Speech Synthesis Workshop, Pittsburgh, USA (2004) 185-190
Vainio, M., Altosaar, T.: Modeling the microprosody of pitch and loudness for speech synthesis with neural networks. In: Proceedings of the International Conference on Spoken Language Processing, Sidney, Australia (1998)
Vegnaduzzo, M.: Modeling intonation for the Italian festival TTS using linear regression. Master’s Thesis, Department of Linguistics, University of Edinburgh (2003)
Scordilis, M.S., Gowdy, J.N.: Neural network based generation of fundamental frequency contours. In: Proceedings of the IEEE International Conference on Acoustics, Speech, Signal Processing. Volume 1, Glasgow, Scotland (1989) 219-222
Vainio, M.: Artificial neural network based prosody models for Finnish text-to-speech synthesis. PhD Thesis, Department of Phonetics, University of Helsinki, Finland (2001)
Buhmann, J., Vereecken, H., Fackrell, J., Martens, J.P., Coile, B.V.: Data driven intonation modeling of 6 languages. In: Proceedings of the International Conference on Spoken Language Processing. Volume 3, Beijing, China (2000) 179-183
Hwang, S.H., Chen, S.H.: Neural-network-based F0 text-to-speech synthesizer for Mandarin. IEEE Proceedings on Image Signal Processing 141 (1994) 384-390
Khan, A.N., Gangashetty, S.V., Yegnanarayana, B.: Syllabic properties of three Indian languages: Implications for speech recognition and language identifica-tion. In: International Conference on Natural Language Processing, Mysore, India (2003) 125-134
Chopde, A.: (Itrans Indian language transliteration package version 5.2 source) http://www.aczone.con/itrans/.
Prasanna, S.R.M., Yegnanarayana, B.: Extraction of pitch in adverse conditions. In: Proceedings of the IEEE International Conference on Acoustics, Speech, Signal Processing, Montreal, Canada (2004)
Bellegarda, J.R., Silverman, K.E.A., Lenzo, K., Anderson, V.: Statistical prosodic modeling: From corpus design to parameter estimation. IEEE Transactions on Speech and Audio Processing 9 (2001) 52-66
Bellegarda, J.R., Silverman, K.E.A.: Improved duration modeling of English phonemes using a root sinusoidal transformation. In: Proceedings of the International Conference on Spoken Language Processing (1998) 21-24
Silverman, K.E.A., Bellegarda, J.R.: Using a sigmoid transformation for improved modeling of phoneme duration. In: Proceedings of the IEEE International Conference on Acoustics, Speech, Signal Processing, Phoenix, AZ, USA (1999) 385-388
Siebenhaar, B., Zellner-Keller, B., Keller, E.: Phonetic and timing considerations in a Swiss high German TTS system. In: Keller, E., Bailly, G., Monaghan, A., Terken, J., Huckvale, M., eds.: Improvements in Speech Synthesis. Wiley, Chichester (2001)
Burges, C.J.C.: A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery 2 (1998) 121-167
Shriberg, Elizabeth, Stolcke, Andreas: Prosody modeling for automatic speech understanding: An overview of recent research at SRI. In: Prosody in Speech Recognition and Understanding, ISCA Tutorial and Research Workshop (ITRW), Molly Pitcher Inn, Red Bank, NJ, USA (2001)
Srikanth, S., Kumar, S.R.R., Sundar, R., Yegnanarayana, B. In: A text-to-speech conversion system for Indian languages based on waveform concatenation model. Technical report no. 11, Project VOIS, Department of Computer Science and Engineering, Indian Institute of Technology Madras (1989)
Rao, K.S., Yegnanarayana, B.: Prosodic manipulation using instants of sig-nificant excitation. In: Proceedings of the IEEE International Conference on Multimedia and Expo, Baltimore, Maryland, USA (2003) 389-392
Smits, R., Yegnanarayana, B.: Determination of instants of significant excitation in speech using group delay function. IEEE Transactions on Speech and Audio Processing 3 (1995) 325-333
Murthy, P.S., Yegnanarayana, B.: Robustness of group-delay-based method for extraction of significant excitation from speech signals. IEEE Transactions on Speech and Audio Processing 7 (1999) 609-619
Deller, J.R., Proakis, J.G., Hansen, J.H.L. In: Discrete-Time Processing of Speech Signals. Macmillan, New York, USA (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Rao, K.S. (2008). Modeling Supra-Segmental Features of Syllables Using Neural Networks. In: Prasad, B., Prasanna, S.R.M. (eds) Speech, Audio, Image and Biomedical Signal Processing using Neural Networks. Studies in Computational Intelligence, vol 83. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-75398-8_4
Download citation
DOI: https://doi.org/10.1007/978-3-540-75398-8_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-75397-1
Online ISBN: 978-3-540-75398-8
eBook Packages: EngineeringEngineering (R0)