IEICE TRANSACTIONS on Information
Statistical Bandwidth Extension for Speech Synthesis Based on Gaussian Mixture Model with Sub-Band Basis Spectrum Model
Summary :
This paper describes a novel statistical bandwidth extension (BWE) technique based on a Gaussian mixture model (GMM) and a sub-band basis spectrum model (SBM), in which each dimensional component represents a specific acoustic space in the frequency domain. The proposed method can achieve the BWE from speech data with an arbitrary frequency bandwidth whereas the conventional methods perform the conversion from fixed narrow-band data. In the proposed method, we train a GMM with SBM parameters extracted from full-band spectra in advance. According to the bandwidth of input signal, the trained GMM is reconstructed to the GMM of the joint probability density between low-band SBM and high-band SBM components. Then high-band SBM components are estimated from low-band SBM components of the input signal based on the reconstructed GMM. Finally, BWE is achieved by adding the spectra decoded from estimated high-band SBM components to the ones of the input signal. To construct the full-band signal from the narrow-band one, we apply this method to log-amplitude spectra and aperiodic components. Objective and subjective evaluation results show that the proposed method extends the bandwidth of speech data robustly for the log-amplitude spectra. Experimental results also indicate that the aperiodic component extracted from the upsampled narrow-band signal realizes the same performance as the restored and the full-band aperiodic components in the proposed method.
- Publication
- IEICE TRANSACTIONS on Information Vol.E99-D No.10 pp.2481-2489
- Publication Date
- 2016/10/01
- Publicized
- 2016/07/19
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2016SLP0006
- Type of Manuscript
- Special Section PAPER (Special Section on Recent Advances in Machine Learning for Spoken Language Processing)
- Category
- Voice conversion
Authors
Yamato OHTANI
Toshiba Corporation
Masatsune TAMURA
Toshiba Corporation
Masahiro MORITA
Toshiba Corporation
Masami AKAMINE
Toshiba Corporation
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Yamato OHTANI, Masatsune TAMURA, Masahiro MORITA, Masami AKAMINE, "Statistical Bandwidth Extension for Speech Synthesis Based on Gaussian Mixture Model with Sub-Band Basis Spectrum Model" in IEICE TRANSACTIONS on Information,
vol. E99-D, no. 10, pp. 2481-2489, October 2016, doi: 10.1587/transinf.2016SLP0006.
Abstract: This paper describes a novel statistical bandwidth extension (BWE) technique based on a Gaussian mixture model (GMM) and a sub-band basis spectrum model (SBM), in which each dimensional component represents a specific acoustic space in the frequency domain. The proposed method can achieve the BWE from speech data with an arbitrary frequency bandwidth whereas the conventional methods perform the conversion from fixed narrow-band data. In the proposed method, we train a GMM with SBM parameters extracted from full-band spectra in advance. According to the bandwidth of input signal, the trained GMM is reconstructed to the GMM of the joint probability density between low-band SBM and high-band SBM components. Then high-band SBM components are estimated from low-band SBM components of the input signal based on the reconstructed GMM. Finally, BWE is achieved by adding the spectra decoded from estimated high-band SBM components to the ones of the input signal. To construct the full-band signal from the narrow-band one, we apply this method to log-amplitude spectra and aperiodic components. Objective and subjective evaluation results show that the proposed method extends the bandwidth of speech data robustly for the log-amplitude spectra. Experimental results also indicate that the aperiodic component extracted from the upsampled narrow-band signal realizes the same performance as the restored and the full-band aperiodic components in the proposed method.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016SLP0006/_p
Copy
@ARTICLE{e99-d_10_2481,
author={Yamato OHTANI, Masatsune TAMURA, Masahiro MORITA, Masami AKAMINE, },
journal={IEICE TRANSACTIONS on Information},
title={Statistical Bandwidth Extension for Speech Synthesis Based on Gaussian Mixture Model with Sub-Band Basis Spectrum Model},
year={2016},
volume={E99-D},
number={10},
pages={2481-2489},
abstract={This paper describes a novel statistical bandwidth extension (BWE) technique based on a Gaussian mixture model (GMM) and a sub-band basis spectrum model (SBM), in which each dimensional component represents a specific acoustic space in the frequency domain. The proposed method can achieve the BWE from speech data with an arbitrary frequency bandwidth whereas the conventional methods perform the conversion from fixed narrow-band data. In the proposed method, we train a GMM with SBM parameters extracted from full-band spectra in advance. According to the bandwidth of input signal, the trained GMM is reconstructed to the GMM of the joint probability density between low-band SBM and high-band SBM components. Then high-band SBM components are estimated from low-band SBM components of the input signal based on the reconstructed GMM. Finally, BWE is achieved by adding the spectra decoded from estimated high-band SBM components to the ones of the input signal. To construct the full-band signal from the narrow-band one, we apply this method to log-amplitude spectra and aperiodic components. Objective and subjective evaluation results show that the proposed method extends the bandwidth of speech data robustly for the log-amplitude spectra. Experimental results also indicate that the aperiodic component extracted from the upsampled narrow-band signal realizes the same performance as the restored and the full-band aperiodic components in the proposed method.},
keywords={},
doi={10.1587/transinf.2016SLP0006},
ISSN={1745-1361},
month={October},}
Copy
TY - JOUR
TI - Statistical Bandwidth Extension for Speech Synthesis Based on Gaussian Mixture Model with Sub-Band Basis Spectrum Model
T2 - IEICE TRANSACTIONS on Information
SP - 2481
EP - 2489
AU - Yamato OHTANI
AU - Masatsune TAMURA
AU - Masahiro MORITA
AU - Masami AKAMINE
PY - 2016
DO - 10.1587/transinf.2016SLP0006
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2016
AB - This paper describes a novel statistical bandwidth extension (BWE) technique based on a Gaussian mixture model (GMM) and a sub-band basis spectrum model (SBM), in which each dimensional component represents a specific acoustic space in the frequency domain. The proposed method can achieve the BWE from speech data with an arbitrary frequency bandwidth whereas the conventional methods perform the conversion from fixed narrow-band data. In the proposed method, we train a GMM with SBM parameters extracted from full-band spectra in advance. According to the bandwidth of input signal, the trained GMM is reconstructed to the GMM of the joint probability density between low-band SBM and high-band SBM components. Then high-band SBM components are estimated from low-band SBM components of the input signal based on the reconstructed GMM. Finally, BWE is achieved by adding the spectra decoded from estimated high-band SBM components to the ones of the input signal. To construct the full-band signal from the narrow-band one, we apply this method to log-amplitude spectra and aperiodic components. Objective and subjective evaluation results show that the proposed method extends the bandwidth of speech data robustly for the log-amplitude spectra. Experimental results also indicate that the aperiodic component extracted from the upsampled narrow-band signal realizes the same performance as the restored and the full-band aperiodic components in the proposed method.
ER -
English
