Noise Reduction in Time Domain Using Referential Reconstruction

Takehiro IHARA; Takayuki NAGAI; Kazuhiko OZEKI; Akira KUREMATSU

doi:10.1093/ietisy/e89-d.3.1203

Noise Reduction in Time Domain Using Referential Reconstruction

Takehiro IHARA, Takayuki NAGAI, Kazuhiko OZEKI, Akira KUREMATSU

Full Text Views

0

Cite this

Summary :

We present a novel approach for single-channel noise reduction of speech signals contaminated by additive noise. In this approach, the system requires speech samples to be uttered in advance by the same speaker as that of the input signal. Speech samples used in this method must have enough phonetic variety to reconstruct the input signal. In the proposed method, which we refer to as referential reconstruction, we have used a small database created from examples of speech, which will be called reference signals. Referential reconstruction uses an example-based approach, in which the objective is to find the candidate speech frame which is the most similar to the clean input frame without noise, although the input frame is contaminated with noise. When candidate frames are found, they become final outputs without any special processing. In order to find the candidate frames, a correlation coefficient is used as a similarity measure. Through automatic speech recognition experiments, the proposed method was shown to be effective, particularly for low-SNR speech signals corrupted with white noise or noise in high-frequency bands. Since the direct implementation of this method requires infeasible computational cost for searching through reference signals, a coarse-to-fine strategy is introduced in this paper.

Publication: IEICE TRANSACTIONS on Information Vol.E89-D No.3 pp.1203-1213

Publication Date: 2006/03/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e89-d.3.1203

Type of Manuscript: PAPER

Category: Speech and Hearing

Cite this

Copy

Takehiro IHARA, Takayuki NAGAI, Kazuhiko OZEKI, Akira KUREMATSU, "Noise Reduction in Time Domain Using Referential Reconstruction" in IEICE TRANSACTIONS on Information, vol. E89-D, no. 3, pp. 1203-1213, March 2006, doi: 10.1093/ietisy/e89-d.3.1203.
Abstract: We present a novel approach for single-channel noise reduction of speech signals contaminated by additive noise. In this approach, the system requires speech samples to be uttered in advance by the same speaker as that of the input signal. Speech samples used in this method must have enough phonetic variety to reconstruct the input signal. In the proposed method, which we refer to as referential reconstruction, we have used a small database created from examples of speech, which will be called reference signals. Referential reconstruction uses an example-based approach, in which the objective is to find the candidate speech frame which is the most similar to the clean input frame without noise, although the input frame is contaminated with noise. When candidate frames are found, they become final outputs without any special processing. In order to find the candidate frames, a correlation coefficient is used as a similarity measure. Through automatic speech recognition experiments, the proposed method was shown to be effective, particularly for low-SNR speech signals corrupted with white noise or noise in high-frequency bands. Since the direct implementation of this method requires infeasible computational cost for searching through reference signals, a coarse-to-fine strategy is introduced in this paper.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.3.1203/_p

Copy

@ARTICLE{e89-d_3_1203,
author={Takehiro IHARA, Takayuki NAGAI, Kazuhiko OZEKI, Akira KUREMATSU, },
journal={IEICE TRANSACTIONS on Information},
title={Noise Reduction in Time Domain Using Referential Reconstruction},
year={2006},
volume={E89-D},
number={3},
pages={1203-1213},
abstract={We present a novel approach for single-channel noise reduction of speech signals contaminated by additive noise. In this approach, the system requires speech samples to be uttered in advance by the same speaker as that of the input signal. Speech samples used in this method must have enough phonetic variety to reconstruct the input signal. In the proposed method, which we refer to as referential reconstruction, we have used a small database created from examples of speech, which will be called reference signals. Referential reconstruction uses an example-based approach, in which the objective is to find the candidate speech frame which is the most similar to the clean input frame without noise, although the input frame is contaminated with noise. When candidate frames are found, they become final outputs without any special processing. In order to find the candidate frames, a correlation coefficient is used as a similarity measure. Through automatic speech recognition experiments, the proposed method was shown to be effective, particularly for low-SNR speech signals corrupted with white noise or noise in high-frequency bands. Since the direct implementation of this method requires infeasible computational cost for searching through reference signals, a coarse-to-fine strategy is introduced in this paper.},
keywords={},
doi={10.1093/ietisy/e89-d.3.1203},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - Noise Reduction in Time Domain Using Referential Reconstruction
T2 - IEICE TRANSACTIONS on Information
SP - 1203
EP - 1213
AU - Takehiro IHARA
AU - Takayuki NAGAI
AU - Kazuhiko OZEKI
AU - Akira KUREMATSU
PY - 2006
DO - 10.1093/ietisy/e89-d.3.1203
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2006
AB - We present a novel approach for single-channel noise reduction of speech signals contaminated by additive noise. In this approach, the system requires speech samples to be uttered in advance by the same speaker as that of the input signal. Speech samples used in this method must have enough phonetic variety to reconstruct the input signal. In the proposed method, which we refer to as referential reconstruction, we have used a small database created from examples of speech, which will be called reference signals. Referential reconstruction uses an example-based approach, in which the objective is to find the candidate speech frame which is the most similar to the clean input frame without noise, although the input frame is contaminated with noise. When candidate frames are found, they become final outputs without any special processing. In order to find the candidate frames, a correlation coefficient is used as a similarity measure. Through automatic speech recognition experiments, the proposed method was shown to be effective, particularly for low-SNR speech signals corrupted with white noise or noise in high-frequency bands. Since the direct implementation of this method requires infeasible computational cost for searching through reference signals, a coarse-to-fine strategy is introduced in this paper.
ER -