Recently, many techniques have been proposed to improve speaker identification in noise environments. Among these techniques, we consider the feature recombination technique for the multi-band approach in noise robust speaker identification. The conventional feature recombination technique is very effective in the band-limited noise condition, but in broad-band noise condition, the conventional feature recombination technique does not provide notable performance improvement compared with the full-band system. Even though the speech is corrupted by the broad-band noise, the degree of the noise corruption on each sub-band is different from each other. In the conventional feature recombination for speaker identification, all sub-band features are used to compute multi-band likelihood score, but this likelihood computation does not use a merit of multi-band approach effectively, even though the sub-band features are extracted independently. Here we propose a new technique of sub-band likelihood computation with sub-band weighting in the feature recombination method. The signal to noise ratio (SNR) is used to compute the sub-band weights. The proposed sub-band-weighted likelihood computation makes a speaker identification system more robust to noise. Experimental results show that the average error reduction rate (ERR) in various noise environments is more than 24% compared with the conventional feature recombination-based speaker identification system.
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.
Copy
Sungtak KIM, Mikyong JI, Youngjoo SUH, Hoirin KIM, "Noise Robust Speaker Identification Using Sub-Band Weighting in Multi-Band Approach" in IEICE TRANSACTIONS on Information,
vol. E90-D, no. 12, pp. 2110-2114, December 2007, doi: 10.1093/ietisy/e90-d.12.2110.
Abstract: Recently, many techniques have been proposed to improve speaker identification in noise environments. Among these techniques, we consider the feature recombination technique for the multi-band approach in noise robust speaker identification. The conventional feature recombination technique is very effective in the band-limited noise condition, but in broad-band noise condition, the conventional feature recombination technique does not provide notable performance improvement compared with the full-band system. Even though the speech is corrupted by the broad-band noise, the degree of the noise corruption on each sub-band is different from each other. In the conventional feature recombination for speaker identification, all sub-band features are used to compute multi-band likelihood score, but this likelihood computation does not use a merit of multi-band approach effectively, even though the sub-band features are extracted independently. Here we propose a new technique of sub-band likelihood computation with sub-band weighting in the feature recombination method. The signal to noise ratio (SNR) is used to compute the sub-band weights. The proposed sub-band-weighted likelihood computation makes a speaker identification system more robust to noise. Experimental results show that the average error reduction rate (ERR) in various noise environments is more than 24% compared with the conventional feature recombination-based speaker identification system.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e90-d.12.2110/_p
Copy
@ARTICLE{e90-d_12_2110,
author={Sungtak KIM, Mikyong JI, Youngjoo SUH, Hoirin KIM, },
journal={IEICE TRANSACTIONS on Information},
title={Noise Robust Speaker Identification Using Sub-Band Weighting in Multi-Band Approach},
year={2007},
volume={E90-D},
number={12},
pages={2110-2114},
abstract={Recently, many techniques have been proposed to improve speaker identification in noise environments. Among these techniques, we consider the feature recombination technique for the multi-band approach in noise robust speaker identification. The conventional feature recombination technique is very effective in the band-limited noise condition, but in broad-band noise condition, the conventional feature recombination technique does not provide notable performance improvement compared with the full-band system. Even though the speech is corrupted by the broad-band noise, the degree of the noise corruption on each sub-band is different from each other. In the conventional feature recombination for speaker identification, all sub-band features are used to compute multi-band likelihood score, but this likelihood computation does not use a merit of multi-band approach effectively, even though the sub-band features are extracted independently. Here we propose a new technique of sub-band likelihood computation with sub-band weighting in the feature recombination method. The signal to noise ratio (SNR) is used to compute the sub-band weights. The proposed sub-band-weighted likelihood computation makes a speaker identification system more robust to noise. Experimental results show that the average error reduction rate (ERR) in various noise environments is more than 24% compared with the conventional feature recombination-based speaker identification system.},
keywords={},
doi={10.1093/ietisy/e90-d.12.2110},
ISSN={1745-1361},
month={December},}
Copy
TY - JOUR
TI - Noise Robust Speaker Identification Using Sub-Band Weighting in Multi-Band Approach
T2 - IEICE TRANSACTIONS on Information
SP - 2110
EP - 2114
AU - Sungtak KIM
AU - Mikyong JI
AU - Youngjoo SUH
AU - Hoirin KIM
PY - 2007
DO - 10.1093/ietisy/e90-d.12.2110
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E90-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2007
AB - Recently, many techniques have been proposed to improve speaker identification in noise environments. Among these techniques, we consider the feature recombination technique for the multi-band approach in noise robust speaker identification. The conventional feature recombination technique is very effective in the band-limited noise condition, but in broad-band noise condition, the conventional feature recombination technique does not provide notable performance improvement compared with the full-band system. Even though the speech is corrupted by the broad-band noise, the degree of the noise corruption on each sub-band is different from each other. In the conventional feature recombination for speaker identification, all sub-band features are used to compute multi-band likelihood score, but this likelihood computation does not use a merit of multi-band approach effectively, even though the sub-band features are extracted independently. Here we propose a new technique of sub-band likelihood computation with sub-band weighting in the feature recombination method. The signal to noise ratio (SNR) is used to compute the sub-band weights. The proposed sub-band-weighted likelihood computation makes a speaker identification system more robust to noise. Experimental results show that the average error reduction rate (ERR) in various noise environments is more than 24% compared with the conventional feature recombination-based speaker identification system.
ER -