Abstract
Speech synthesis research has recently focused on developing polyglot speech synthesizers for handling mixed-language sentences. Polyglot speech synthesis systems are particularly essential in multilingual countries like India. This paper aims at enhancing the quality of hidden Markov model (HMM)-based polyglot synthesizer for the two popular Indian languages (Telugu–Hindi) by incorporating an advanced excitation modeling approach. Experimental results show that the voice quality of our mixed-language synthesizer is significantly better than the baseline systems.
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
Zen H, Tokuda K, Black AW (2009) Statistical parametric speech synthesis. Speech Commun 51(11):1039–1064
Zen H, Senior A, Schuster M (2013) Statistical parametric speech synthesis using deep neural networks. In: Proc. ICASSP, Vancouver, Canada, pp 7962–7966
Solomi V, Christina S, Rachel G, Ramani B, Vijayalakshmi P, Nagarajan T (2013) Analysis on acoustic similarities between Tamil and English phonemes using product of likelihood-Gaussians for an HMM-based mixed-language synthesizer. In: Proc. IEEE O-COCOSDA/CASLRE, Gurgaon, India, pp 1–5
Qian Y, Cao H, Soong FK (2008) HMM-based mixed-language (Mandarin-English) speech synthesis. In: Proc. INTERSPEECH, Brisbane, Australia, pp 4460–4464
Justin T et al. (2012) A bilingual HMM-based speech synthesis system for closely related languages. In: Proc. TSD, Czech Republic, pp 543–550
Reddy MK, Rao KS (2018) DNN-based bilingual (Telugu–Hindi) polyglot speech synthesis. In: Proc. ICACCI, Bangalore, India, pp 1808–1811
Zen H, Toda T, Nakamura M, Tokuda K (2007) Details of the Nitech HMM-based speech synthesis system for the Blizzard challenge 2005. IEICE Trans Inf Syst 90(1):325–333
Reddy MK, Rao KS (2018) Inverse filter based excitation model for HMM-based speech synthesis system. IET Signal Proc 12(4):544–548
Ramani B et al. (2013) A common attribute based unified HTS framework for speech synthesis in Indian languages. In: Proc. SSW, Barcelona, Spain, pp 291–296
“HMM-based speech synthesis system (HTS).” [online]. Available:http://hts.sp.nitech.ac.jp/
Reddy MK, Rao KS (2017) Robust pitch extraction method for the HMM-based speech synthesis system. In: IEEE signal processing letters, vol. 24. no. 8, pp 1133–1137
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Reddy, M.K., Rao, K.S. (2020). Improved HMM-Based Mixed-Language (Telugu–Hindi) Polyglot Speech Synthesis. In: Kalya, S., Kulkarni, M., Shivaprakasha, K. (eds) Advances in Communication, Signal Processing, VLSI, and Embedded Systems. Lecture Notes in Electrical Engineering, vol 614. Springer, Singapore. https://doi.org/10.1007/978-981-15-0626-0_23
Download citation
DOI: https://doi.org/10.1007/978-981-15-0626-0_23
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-0625-3
Online ISBN: 978-981-15-0626-0
eBook Packages: EngineeringEngineering (R0)