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
Neste artigo, é proposto um novo método para reduzir o ruído aditivo variável no tempo. Ao contrário dos métodos anteriores, o método proposto não requer nem a suposição sobre o ruído nem a estimativa das estatísticas de ruído de quaisquer regiões de pausa. O aprimoramento é realizado banda por banda para cada período de tempo. Com base na decisão sobre se uma banda específica em um quadro é dominante na fala ou no ruído e na propriedade de mascaramento do sistema auditivo humano, uma quantidade apropriada de ruído é reduzida no domínio tempo-frequência usando subtração espectral modificada. O método proposto foi testado em várias condições ruidosas: ruído de carro, ruído F16, ruído gaussiano branco, ruído rosa, ruído de tanque e ruído de balbucio. Com base na SNR segmentada, inspeção de espectrogramas e testes MOS, o método proposto mostrou-se mais eficaz que a subtração espectral com e sem detecção de pausa na redução do ruído e minimizando a distorção da fala.
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
Sukhyun YOON, Chang D. YOO, "Speech Enhancement Based on Speech/Noise-Dominant Decision" in IEICE TRANSACTIONS on Information,
vol. E85-D, no. 4, pp. 744-750, April 2002, doi: .
Abstract: In this paper, a novel method to reduce additive time-varying noise is proposed. Unlike the previous methods, the proposed method requires neither the assumption about noise nor the estimate of the noise statistics from any pause regions. The enhancement is performed on a band-by-band basis for each time frame. Based on both the decision on whether a particular band in a frame is speech or noise dominant and the masking property of the human auditory system, an appropriate amount of noise is reduced in time-frequency domain using modified spectral subtraction. The proposed method was tested on various noisy conditions: car noise, F16 noise, white Gaussian noise, pink noise, tank noise and babble noise. On the basis of segmental SNR, inspection of spectrograms and MOS tests, the proposed method was found to be more effective than spectral subtraction with and without pause detection in reducing noise while minimizing distortion to speech.
URL: https://global.ieice.org/en_transactions/information/10.1587/e85-d_4_744/_p
Copiar
@ARTICLE{e85-d_4_744,
author={Sukhyun YOON, Chang D. YOO, },
journal={IEICE TRANSACTIONS on Information},
title={Speech Enhancement Based on Speech/Noise-Dominant Decision},
year={2002},
volume={E85-D},
number={4},
pages={744-750},
abstract={In this paper, a novel method to reduce additive time-varying noise is proposed. Unlike the previous methods, the proposed method requires neither the assumption about noise nor the estimate of the noise statistics from any pause regions. The enhancement is performed on a band-by-band basis for each time frame. Based on both the decision on whether a particular band in a frame is speech or noise dominant and the masking property of the human auditory system, an appropriate amount of noise is reduced in time-frequency domain using modified spectral subtraction. The proposed method was tested on various noisy conditions: car noise, F16 noise, white Gaussian noise, pink noise, tank noise and babble noise. On the basis of segmental SNR, inspection of spectrograms and MOS tests, the proposed method was found to be more effective than spectral subtraction with and without pause detection in reducing noise while minimizing distortion to speech.},
keywords={},
doi={},
ISSN={},
month={April},}
Copiar
TY - JOUR
TI - Speech Enhancement Based on Speech/Noise-Dominant Decision
T2 - IEICE TRANSACTIONS on Information
SP - 744
EP - 750
AU - Sukhyun YOON
AU - Chang D. YOO
PY - 2002
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E85-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2002
AB - In this paper, a novel method to reduce additive time-varying noise is proposed. Unlike the previous methods, the proposed method requires neither the assumption about noise nor the estimate of the noise statistics from any pause regions. The enhancement is performed on a band-by-band basis for each time frame. Based on both the decision on whether a particular band in a frame is speech or noise dominant and the masking property of the human auditory system, an appropriate amount of noise is reduced in time-frequency domain using modified spectral subtraction. The proposed method was tested on various noisy conditions: car noise, F16 noise, white Gaussian noise, pink noise, tank noise and babble noise. On the basis of segmental SNR, inspection of spectrograms and MOS tests, the proposed method was found to be more effective than spectral subtraction with and without pause detection in reducing noise while minimizing distortion to speech.
ER -