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
A desreverberação de fala é uma das tarefas mais difíceis no processamento de sinais acústicos. Dos vários problemas envolvidos nesta tarefa, este artigo destaca o “branqueamento excessivo”, que atenua as características da fala recuperada. Essa distorção às vezes acontece quando os filtros inversos são calculados diretamente a partir dos sinais do microfone. Este artigo revisa dois estudos relacionados a esse problema. O primeiro estudo mostra a possibilidade de compensar esse branqueamento excessivo para obter uma deseverberação precisa da fala. O segundo estudo apresenta uma nova abordagem para aproximar a fala original, removendo o efeito das reflexões tardias da fala reverberante observada.
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
Masato MIYOSHI, Marc DELCROIX, Keisuke KINOSHITA, "Calculating Inverse Filters for Speech Dereverberation" in IEICE TRANSACTIONS on Fundamentals,
vol. E91-A, no. 6, pp. 1303-1309, June 2008, doi: 10.1093/ietfec/e91-a.6.1303.
Abstract: Speech dereverberation is one of the most difficult tasks in acoustic signal processing. Of the various problems involved in this task, this paper highlights "over-whitening," which flattens the characteristics of recovered speech. This distortion sometimes happens when inverse filters are directly calculated from microphone signals. This paper reviews two studies related to this problem. The first study shows the possibility of compensating for such over-whitening to achieve precise speech-dereverberation. The second study presents a new approach for approximating the original speech by removing the effect of late reflections from observed reverberant speech.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1093/ietfec/e91-a.6.1303/_p
Copiar
@ARTICLE{e91-a_6_1303,
author={Masato MIYOSHI, Marc DELCROIX, Keisuke KINOSHITA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Calculating Inverse Filters for Speech Dereverberation},
year={2008},
volume={E91-A},
number={6},
pages={1303-1309},
abstract={Speech dereverberation is one of the most difficult tasks in acoustic signal processing. Of the various problems involved in this task, this paper highlights "over-whitening," which flattens the characteristics of recovered speech. This distortion sometimes happens when inverse filters are directly calculated from microphone signals. This paper reviews two studies related to this problem. The first study shows the possibility of compensating for such over-whitening to achieve precise speech-dereverberation. The second study presents a new approach for approximating the original speech by removing the effect of late reflections from observed reverberant speech.},
keywords={},
doi={10.1093/ietfec/e91-a.6.1303},
ISSN={1745-1337},
month={June},}
Copiar
TY - JOUR
TI - Calculating Inverse Filters for Speech Dereverberation
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1303
EP - 1309
AU - Masato MIYOSHI
AU - Marc DELCROIX
AU - Keisuke KINOSHITA
PY - 2008
DO - 10.1093/ietfec/e91-a.6.1303
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E91-A
IS - 6
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - June 2008
AB - Speech dereverberation is one of the most difficult tasks in acoustic signal processing. Of the various problems involved in this task, this paper highlights "over-whitening," which flattens the characteristics of recovered speech. This distortion sometimes happens when inverse filters are directly calculated from microphone signals. This paper reviews two studies related to this problem. The first study shows the possibility of compensating for such over-whitening to achieve precise speech-dereverberation. The second study presents a new approach for approximating the original speech by removing the effect of late reflections from observed reverberant speech.
ER -