Utilizing glottal source pulse library for generating improved excitation signal for HMM-based speech synthesis

This paper describes a source modeling method for hidden Markov model (HMM) based speech synthesis for improved naturalness. A speech corpus is rst decomposed into the glottal source signal and the model of the vocal tract lter using glottal inverse ltering, and parametrized into excitation and spectral features. Additionally, a library of glottal source pulses is extracted from the estimated voice source signal. In the synthesis stage, the excitation signal is generated by selecting appropriate pulses from the library according to the target cost of the excitation features and a concatenation cost between adjacent glottal source pulses. Finally, speech is synthesized by ltering the excitation signal by the vocal tract lter. Experiments show that the naturalness of the synthetic speech is better or equal, and speaker similarity is better, compared to a system using only single glottal source pulse.

• Type: Journal
• Year: 2011
• Where: ICASSP
• Authors: Tuomo Raitio, Antti Suni, Hannu Pulakka, Martti Vainio, Paavo Alku
• Keywords: Excitation Signal, Glottal Source, ICASSP 2011, Signal Processing, Vocal Tract Lter