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
조회수
91
본 논문에서는 보코더 기반 음성 파형 생성을 위한 새로운 잡음 생성 알고리즘을 소개합니다. 백색 잡음은 일반적으로 비주기 성분을 생성하는 데 사용됩니다. 단기 백색잡음에는 영주파수 성분(ZFC)과 20Hz 이하의 비가청 성분이 포함되어 있으므로 합성 시 미리 줄여준다. 우리는 이러한 문제를 극복하기 위해 벨벳 노이즈에 기반한 새로운 노이즈 생성 알고리즘을 제안한다. 객관적인 평가를 통해 제안된 알고리즘이 원하지 않는 성분을 줄일 수 있음을 입증했습니다.
Masanori MORISE
University of Yamanashi,JST PRESTO
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.
부
Masanori MORISE, "Modification of Velvet Noise for Speech Waveform Generation by Using Vocoder-Based Speech Synthesizer" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 3, pp. 663-665, March 2019, doi: 10.1587/transinf.2018EDL8179.
Abstract: This paper introduces a new noise generation algorithm for vocoder-based speech waveform generation. White noise is generally used for generating an aperiodic component. Since short-term white noise includes a zero-frequency component (ZFC) and inaudible components below 20 Hz, they are reduced in advance when synthesizing. We propose a new noise generation algorithm based on that for velvet noise to overcome the problem. The objective evaluation demonstrated that the proposed algorithm can reduce the unwanted components.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDL8179/_p
부
@ARTICLE{e102-d_3_663,
author={Masanori MORISE, },
journal={IEICE TRANSACTIONS on Information},
title={Modification of Velvet Noise for Speech Waveform Generation by Using Vocoder-Based Speech Synthesizer},
year={2019},
volume={E102-D},
number={3},
pages={663-665},
abstract={This paper introduces a new noise generation algorithm for vocoder-based speech waveform generation. White noise is generally used for generating an aperiodic component. Since short-term white noise includes a zero-frequency component (ZFC) and inaudible components below 20 Hz, they are reduced in advance when synthesizing. We propose a new noise generation algorithm based on that for velvet noise to overcome the problem. The objective evaluation demonstrated that the proposed algorithm can reduce the unwanted components.},
keywords={},
doi={10.1587/transinf.2018EDL8179},
ISSN={1745-1361},
month={March},}
부
TY - JOUR
TI - Modification of Velvet Noise for Speech Waveform Generation by Using Vocoder-Based Speech Synthesizer
T2 - IEICE TRANSACTIONS on Information
SP - 663
EP - 665
AU - Masanori MORISE
PY - 2019
DO - 10.1587/transinf.2018EDL8179
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2019
AB - This paper introduces a new noise generation algorithm for vocoder-based speech waveform generation. White noise is generally used for generating an aperiodic component. Since short-term white noise includes a zero-frequency component (ZFC) and inaudible components below 20 Hz, they are reduced in advance when synthesizing. We propose a new noise generation algorithm based on that for velvet noise to overcome the problem. The objective evaluation demonstrated that the proposed algorithm can reduce the unwanted components.
ER -