The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Até agora propusemos um sistema de auxílio à fala para laringectomizados usando uma técnica estatística de conversão de voz. No sistema proposto, a fala artificial articulada com sinais de fonte sonora extremamente pequenos é detectada com um microfone Non-Audible Murmur (NAM) e, em seguida, a fala artificial detectada é convertida em voz mais natural de forma probabilística. Embora este sistema basicamente permita que os laringectomizados falem enquanto mantêm os sinais da fonte externa silenciosos, ainda é questionável o quanto esses novos sinais da fonte sonora afetam a qualidade da fala convertida. Neste artigo, investigamos o impacto de vários sinais de fontes sonoras na precisão da conversão de voz. Vários pequenos sinais de fonte sonora são projetados alterando o envelope espectral e a potência da forma de onda de forma independente. Realizamos avaliações objetivas e subjetivas. Os resultados destas avaliações experimentais demonstram que a conversão de voz aceita 1) vários sinais de fonte sonora com diferentes envelopes espectrais e 2) grande grau de potência dos sinais da fonte sonora, a menos que a potência das partes faladas seja quase igual à das partes silenciosas. Além disso, também investigamos a eficácia de melhorar o feedback auditivo durante a fala com sinais de fonte sonora extremamente pequenos.
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.
Copiar
Keigo NAKAMURA, Tomoki TODA, Hiroshi SARUWATARI, Kiyohiro SHIKANO, "Evaluation of Extremely Small Sound Source Signals Used in Speaking-Aid System with Statistical Voice Conversion" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 7, pp. 1909-1917, July 2010, doi: 10.1587/transinf.E93.D.1909.
Abstract: We have so far proposed a speaking-aid system for laryngectomees using a statistical voice conversion technique. In the proposed system, artificial speech articulated with extremely small sound source signals is detected with a Non-Audible Murmur (NAM) microphone, and then, the detected artificial speech is converted into more natural voice in a probabilistic manner. Although this system basically allows laryngectomees to speak while keeping the external source signals silent, it is still questionable how much these new sound source signals affect the converted speech quality. In this paper, we investigate the impact of various sound source signals on voice conversion accuracy. Various small sound source signals are designed by changing the spectral envelope and the waveform power independently. We conduct objective and subjective evaluations. The results of these experimental evaluations demonstrate that voice conversion accepts 1) various sound source signals with different spectral envelopes and 2) large degree of power of the sound source signals unless the power of speaking parts is almost equal to that of silence parts. Moreover, we also investigate the effectiveness of enhancing auditory feedback during speaking with the extremely small sound source signals.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.1909/_p
Copiar
@ARTICLE{e93-d_7_1909,
author={Keigo NAKAMURA, Tomoki TODA, Hiroshi SARUWATARI, Kiyohiro SHIKANO, },
journal={IEICE TRANSACTIONS on Information},
title={Evaluation of Extremely Small Sound Source Signals Used in Speaking-Aid System with Statistical Voice Conversion},
year={2010},
volume={E93-D},
number={7},
pages={1909-1917},
abstract={We have so far proposed a speaking-aid system for laryngectomees using a statistical voice conversion technique. In the proposed system, artificial speech articulated with extremely small sound source signals is detected with a Non-Audible Murmur (NAM) microphone, and then, the detected artificial speech is converted into more natural voice in a probabilistic manner. Although this system basically allows laryngectomees to speak while keeping the external source signals silent, it is still questionable how much these new sound source signals affect the converted speech quality. In this paper, we investigate the impact of various sound source signals on voice conversion accuracy. Various small sound source signals are designed by changing the spectral envelope and the waveform power independently. We conduct objective and subjective evaluations. The results of these experimental evaluations demonstrate that voice conversion accepts 1) various sound source signals with different spectral envelopes and 2) large degree of power of the sound source signals unless the power of speaking parts is almost equal to that of silence parts. Moreover, we also investigate the effectiveness of enhancing auditory feedback during speaking with the extremely small sound source signals.},
keywords={},
doi={10.1587/transinf.E93.D.1909},
ISSN={1745-1361},
month={July},}
Copiar
TY - JOUR
TI - Evaluation of Extremely Small Sound Source Signals Used in Speaking-Aid System with Statistical Voice Conversion
T2 - IEICE TRANSACTIONS on Information
SP - 1909
EP - 1917
AU - Keigo NAKAMURA
AU - Tomoki TODA
AU - Hiroshi SARUWATARI
AU - Kiyohiro SHIKANO
PY - 2010
DO - 10.1587/transinf.E93.D.1909
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2010
AB - We have so far proposed a speaking-aid system for laryngectomees using a statistical voice conversion technique. In the proposed system, artificial speech articulated with extremely small sound source signals is detected with a Non-Audible Murmur (NAM) microphone, and then, the detected artificial speech is converted into more natural voice in a probabilistic manner. Although this system basically allows laryngectomees to speak while keeping the external source signals silent, it is still questionable how much these new sound source signals affect the converted speech quality. In this paper, we investigate the impact of various sound source signals on voice conversion accuracy. Various small sound source signals are designed by changing the spectral envelope and the waveform power independently. We conduct objective and subjective evaluations. The results of these experimental evaluations demonstrate that voice conversion accepts 1) various sound source signals with different spectral envelopes and 2) large degree of power of the sound source signals unless the power of speaking parts is almost equal to that of silence parts. Moreover, we also investigate the effectiveness of enhancing auditory feedback during speaking with the extremely small sound source signals.
ER -