Adaptive Refinements of Pitch Tracking and HNR Estimation within a Vocoder for Statistical Parametric Speech Synthesis
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...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/12/2460 |
| _version_ | 1818151215235596288 |
|---|---|
| author | Mohammed Salah Al-Radhi Tamás Gábor Csapó Géza Németh |
| author_facet | Mohammed Salah Al-Radhi Tamás Gábor Csapó Géza Németh |
| author_sort | Mohammed Salah Al-Radhi |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-11T13:35:17Z |
| format | Article |
| id | doaj.art-d270da1b6eba4e2cacbea4ea292f8dc5 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-11T13:35:17Z |
| publishDate | 2019-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-d270da1b6eba4e2cacbea4ea292f8dc52022-12-22T01:05:04ZengMDPI AGApplied Sciences2076-34172019-06-01912246010.3390/app9122460app9122460Adaptive Refinements of Pitch Tracking and HNR Estimation within a Vocoder for Statistical Parametric Speech SynthesisMohammed Salah Al-Radhi0Tamás Gábor Csapó1Géza Németh2Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, 1117 Budapest, HungaryDepartment of Telecommunications and Media Informatics, Budapest University of Technology and Economics, 1117 Budapest, HungaryDepartment of Telecommunications and Media Informatics, Budapest University of Technology and Economics, 1117 Budapest, HungaryRecent 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.https://www.mdpi.com/2076-3417/9/12/2460continuous F0speech synthesisKalman filtertime-warpingHNR |
| spellingShingle | Mohammed Salah Al-Radhi Tamás Gábor Csapó Géza Németh Adaptive Refinements of Pitch Tracking and HNR Estimation within a Vocoder for Statistical Parametric Speech Synthesis Applied Sciences continuous F0 speech synthesis Kalman filter time-warping HNR |
| title | Adaptive Refinements of Pitch Tracking and HNR Estimation within a Vocoder for Statistical Parametric Speech Synthesis |
| title_full | Adaptive Refinements of Pitch Tracking and HNR Estimation within a Vocoder for Statistical Parametric Speech Synthesis |
| title_fullStr | Adaptive Refinements of Pitch Tracking and HNR Estimation within a Vocoder for Statistical Parametric Speech Synthesis |
| title_full_unstemmed | Adaptive Refinements of Pitch Tracking and HNR Estimation within a Vocoder for Statistical Parametric Speech Synthesis |
| title_short | Adaptive Refinements of Pitch Tracking and HNR Estimation within a Vocoder for Statistical Parametric Speech Synthesis |
| title_sort | adaptive refinements of pitch tracking and hnr estimation within a vocoder for statistical parametric speech synthesis |
| topic | continuous F0 speech synthesis Kalman filter time-warping HNR |
| url | https://www.mdpi.com/2076-3417/9/12/2460 |
| work_keys_str_mv | AT mohammedsalahalradhi adaptiverefinementsofpitchtrackingandhnrestimationwithinavocoderforstatisticalparametricspeechsynthesis AT tamasgaborcsapo adaptiverefinementsofpitchtrackingandhnrestimationwithinavocoderforstatisticalparametricspeechsynthesis AT gezanemeth adaptiverefinementsofpitchtrackingandhnrestimationwithinavocoderforstatisticalparametricspeechsynthesis |