10.3390/app9122460
https://zenodo.org/records/5729320
oai:zenodo.org:5729320
Al-Radhi, Mohammed Salah
Mohammed Salah
Al-Radhi
0000-0003-3094-6916
Budapest University of Technology and Economics
Csapó, Tamás Gábor
Tamás Gábor
Csapó
0000-0003-4375-7524
Budapest University of Technology and Economics
Németh, Géza
Géza
Németh
0000-0002-2311-4858
Budapest University of Technology and Economics
Adaptive Refinements of Pitch Tracking and HNR Estimation within a Vocoder for Statistical Parametric Speech Synthesis
Zenodo
2019
continuous F0
speech synthesis
time-warping
2019-06-16
eng
10.3390/app9122460
https://zenodo.org/communities/ai4eu
https://zenodo.org/communities/eu
1
Creative Commons Attribution 4.0 International
Recent studies in text-to-speech synthesis have shown the benefit of using a continuous pitch estimate; one that interpolates fundamental frequency (F0) even when voicing is not present. However, continuous F0 is still sensitive to additive noise in speech signals and suffers from short-term errors (when it changes rather quickly over time). To alleviate these issues, three adaptive techniques have been developed in this article for achieving a robust and accurate F0: (1) we weight the pitch estimates with state noise covariance using adaptive Kalman-filter framework, (2) we iteratively apply a time axis warping on the input frame signal, (3) we optimize all F0 candidates using an instantaneous-frequency-based approach. Additionally, the second goal of this study is to introduce an extension of a novel continuous-based speech synthesis system (i.e., in which all parameters are continuous). We propose adding a new excitation parameter named Harmonic-to-Noise Ratio (HNR) to the voiced and unvoiced components to indicate the degree of voicing in the excitation and to reduce the influence of buzziness caused by the vocoder. Results based on objective and perceptual tests demonstrate that the voice built with the proposed framework gives state-of-the-art speech synthesis performance while outperforming the previous baseline.
1
European Commission
10.13039/501100000780
825619
A European AI On Demand Platform and Ecosystem