We investigate strategies to improve the utterance verification performance using a 2-class pattern classification approach, including: utilizing N-best candidate scores, modifying segmentation boundaries, applying background and out-of-vocabulary filler models, incorporating contexts, and minimizing verification errors via discriminative training. A connected-digit database recorded in a noisy, moving car with a hands-free microphone mounted on the sun-visor is used to evaluate the verification performance. The equal error rate (EER) of word verification is employed as the sole performance measure. All factors and their effects on the verification performance are presented in detail. The EER is reduced from 29%, using the standard likelihood ratio test, down to 21.4%, when all features are properly integrated.
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
Tomoko MATSUI, Frank K. SOONG, Biing-Hwang JUANG, "Verification of Multi-Class Recognition Decision: A Classification Approach" in IEICE TRANSACTIONS on Information,
vol. E88-D, no. 3, pp. 455-462, March 2005, doi: 10.1093/ietisy/e88-d.3.455.
Abstract: We investigate strategies to improve the utterance verification performance using a 2-class pattern classification approach, including: utilizing N-best candidate scores, modifying segmentation boundaries, applying background and out-of-vocabulary filler models, incorporating contexts, and minimizing verification errors via discriminative training. A connected-digit database recorded in a noisy, moving car with a hands-free microphone mounted on the sun-visor is used to evaluate the verification performance. The equal error rate (EER) of word verification is employed as the sole performance measure. All factors and their effects on the verification performance are presented in detail. The EER is reduced from 29%, using the standard likelihood ratio test, down to 21.4%, when all features are properly integrated.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e88-d.3.455/_p
Copy
@ARTICLE{e88-d_3_455,
author={Tomoko MATSUI, Frank K. SOONG, Biing-Hwang JUANG, },
journal={IEICE TRANSACTIONS on Information},
title={Verification of Multi-Class Recognition Decision: A Classification Approach},
year={2005},
volume={E88-D},
number={3},
pages={455-462},
abstract={We investigate strategies to improve the utterance verification performance using a 2-class pattern classification approach, including: utilizing N-best candidate scores, modifying segmentation boundaries, applying background and out-of-vocabulary filler models, incorporating contexts, and minimizing verification errors via discriminative training. A connected-digit database recorded in a noisy, moving car with a hands-free microphone mounted on the sun-visor is used to evaluate the verification performance. The equal error rate (EER) of word verification is employed as the sole performance measure. All factors and their effects on the verification performance are presented in detail. The EER is reduced from 29%, using the standard likelihood ratio test, down to 21.4%, when all features are properly integrated.},
keywords={},
doi={10.1093/ietisy/e88-d.3.455},
ISSN={},
month={March},}
Copy
TY - JOUR
TI - Verification of Multi-Class Recognition Decision: A Classification Approach
T2 - IEICE TRANSACTIONS on Information
SP - 455
EP - 462
AU - Tomoko MATSUI
AU - Frank K. SOONG
AU - Biing-Hwang JUANG
PY - 2005
DO - 10.1093/ietisy/e88-d.3.455
JO - IEICE TRANSACTIONS on Information
SN -
VL - E88-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2005
AB - We investigate strategies to improve the utterance verification performance using a 2-class pattern classification approach, including: utilizing N-best candidate scores, modifying segmentation boundaries, applying background and out-of-vocabulary filler models, incorporating contexts, and minimizing verification errors via discriminative training. A connected-digit database recorded in a noisy, moving car with a hands-free microphone mounted on the sun-visor is used to evaluate the verification performance. The equal error rate (EER) of word verification is employed as the sole performance measure. All factors and their effects on the verification performance are presented in detail. The EER is reduced from 29%, using the standard likelihood ratio test, down to 21.4%, when all features are properly integrated.
ER -