Improvements of Hungarian hidden Markov model-based text-to-speech synthesis

Authors:
Bálint Tóth;Géza Németh
Affiliations:
Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics;Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics
Venue:
Acta Cybernetica
Year:
2010

Citing 5
Cited 0

Diphone speech synthesis

Speech Communication
Incorporating a mixed excitation model and postfilter into HMM-based text-to-speech synthesis

Systems and Computers in Japan
Hidden Markov models based on multi-space probability distribution for pitch pattern modeling

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
Some aspects of ASR transcription based unsupervised speaker adaptation for HMM speech synthesis

TSD'10 Proceedings of the 13th international conference on Text, speech and dialogue
Analysis of Speaker Adaptation Algorithms for HMM-Based Speech Synthesis and a Constrained SMAPLR Adaptation Algorithm

IEEE Transactions on Audio, Speech, and Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Statistical parametric, especially Hidden Markov Model-based, text-to-speech (TTS) synthesis has received much attention recently. The quality of HMM-based speech synthesis approaches that of the state-of-the-art unit selection systems and possesses numerous favorable features, e.g. small runtime footprint, speaker interpolation, speaker adaptation. This paper presents the improvements of a Hungarian HMM-based speech synthesis system, including speaker dependent and adaptive training, speech synthesis with pulse-noise and mixed excitation. Listening tests and their evaluation are also described.