Abstract
This paper deals with a major issue for designing a Text-to-Speech synthesizer. To design a speech synthesizer, we need speech prosody where all significant and important utterance-related information are systematically stored. An utterance can be divided into the segmental level as well as suprasegmental level. Suprasegmental level deals with syllable, word, and sentence. We are experimentally studying the behaviors of these segments with respect to Northeast Indian language Assamese. To design intonation model of any language, a clear understanding of a prominent portion of an utterance, prosodic boundary as well as tunes of the concerned sentences are necessary. In this paper, we are discussing all these features with the help of some selected speech items from our Assamese speech database. We are trying to explain the suprasegmental behavior of utterances with the help of tables and graphs prepared from our experiment.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Thomas S.: Natural Sounding Text-To-Speech Synthesis Based On Syllable-Like Units, (2007).
Shattuck-Hufnagel, S. and Turk A. E.: A prosody tutorial for investigators of auditory sentence processing. Journal of sycholinguistic Research 25 (2), (1996), 56–80.
Kakati Banikanta.:Assamese its formation and development, 5th ed.. Guwahati, India, LBS publication, 2007.
Goswami G.C.:Structure of Assamese, FIRST EDITION, Department of Publication, GAUHATI UNIVERSITY, 1982.
Kishore S.P., Sangal R. and Srinivas M., Building Hindi and Telugu voices using Festvox, in Proceedings of International Conference on Natural Language Processing, (2002), 18–21.
Agrawal A, Jain A, Prakash N, Agrawal S.S.: Word boundary detection in continuous speech based on suprasegmental features for Hindi language, Signal Processing System, 2nd International Conference, IEEE (2012).
Shreenivasa Rao. K: Modeling Supra-Segmental Features of Syllables Using Neural Networks, Book Chapter “Speech, Audio, Image and Biomedical Signal Processing using Neural Networks” By Prasnna Prasad, volume 83, pp 71– 95.
Alam F.:kotha The First Text to Speech Synthesis for Bangla Language, (2006), 17–21.
S. Lee, Y.H. Oh,:Tree-based modeling of prosodic phrasing and segmental duration for Korean TTS systems, Speech Communication, Vol. 28, 1999, 283–300.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sarma, P., Sarma, S.K. (2018). A Study on Variation of Suprasegmental Phonetic Appearance Considered for Prosody Design with Respect to Assamese Language. In: Mandal, J., Saha, G., Kandar, D., Maji, A. (eds) Proceedings of the International Conference on Computing and Communication Systems. Lecture Notes in Networks and Systems, vol 24. Springer, Singapore. https://doi.org/10.1007/978-981-10-6890-4_25
Download citation
DOI: https://doi.org/10.1007/978-981-10-6890-4_25
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-6889-8
Online ISBN: 978-981-10-6890-4
eBook Packages: EngineeringEngineering (R0)