Abstract
Formants, considered to be responsible for differences in vowel quality, also represent regional variations in the vowel/diphthong sounds of a language. In this paper, three approaches based on the Gaussian Mixture Models (GMMs) are used to develop mapping functions to map the most informative formants, F1, F2, & F3 of vowels/diphthongs of one variety of Assamese to another. The first is based on a single GMM for vowel/diphthong formants in training data. The second, maps the formants at four equidistant temporal points of vowel/diphthong duration. The third approach trains separate GMMs for the formants of each vowel/diphthong. In objective evaluation, all three approaches bring the vowel/diphthong formants of the source variety closer to the target variety. The third, outperforms the previous two.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Fox, R.A., Jacewicz, E.: Cross-dialectal variation in formant dynamics of american english vowels. The Journal of the Acoustical Society of America 126(5) (2009) 2603–2618
Hagiwara, R.: Dialect variation and formant frequency: The american english vowels revisited. The Journal of the Acoustical Society of America 102(1) (1997) 655–658
Nath, S., Sharma, U.: An analysis of the vowels and diphthongs of the assamese language and its nalbaria variety. In: Computing and Communication Systems(I3CS), 2015 International Conference on. (2015)
Labov, W.: Principles of linguistic change, cognitive and cultural factors. Volume 3. John Wiley & Sons (2011)
Teutenberg, J., Watson, C.: Vowel quality in accent modification. In: Proc. Australian International Conference on Speech Science & Technology, University of Auckland, New Zealand. (2006) 292–295
Narendranath, M., Murthy, H.A., Rajendran, S., Yegnanarayana, B.: Voice conversion using artificial neural networks. In: Automatic Speaker Recognition, Identification and Verification. (1994)
Rentzos, D., Vaseghi, S., Yan, Q., Ho, C.H.: Parametric formant modelling and transformation in voice conversion. International Journal of Speech Technology 8(3) (2005) 227–245
Stylianou, Y., Cappé, O., Moulines, E.: Continuous probabilistic transform for voice conversion. Speech and Audio Processing, IEEE Transactions on 6(2) (1998) 131–142
Toda, T., Black, A.W., Tokuda, K.: Voice conversion based on maximum-likelihood estimation of spectral parameter trajectory. IEEE Transactions on Audio, Speech, and Language Processing 15(8) (2007) 2222–2235
Acknowledgements
The authors are thankful to Trideep Baruah and Mancha J. Malakar for their help in corpus building and to MHRD Centre of Excellence for financial support.
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
Sanghamitra, N., Utpal, S. (2018). GMM-Based Formant Transformation of the Vowels/Diphthongs of One Assamese Variety to Another. 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_40
Download citation
DOI: https://doi.org/10.1007/978-981-10-6890-4_40
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-6889-8
Online ISBN: 978-981-10-6890-4
eBook Packages: EngineeringEngineering (R0)