Spoken Term Detection Using SVM-Based Classifier Trained with Pre-Indexed Keywords

Kentaro DOMOTO; Takehito UTSURO; Naoki SAWADA; Hiromitsu NISHIZAKI

doi:10.1587/transinf.2016SLP0017

Spoken Term Detection Using SVM-Based Classifier Trained with Pre-Indexed Keywords

Kentaro DOMOTO, Takehito UTSURO, Naoki SAWADA, Hiromitsu NISHIZAKI

Full Text Views

0

Cite this

Summary :

This study presents a two-stage spoken term detection (STD) method that uses the same STD engine twice and a support vector machine (SVM)-based classifier to verify detected terms from the STD engine's output. In a front-end process, the STD engine is used to pre-index target spoken documents from a keyword list built from an automatic speech recognition result. The STD result includes a set of keywords and their detection intervals (positions) in the spoken documents. For keywords having competitive intervals, we rank them based on the STD matching cost and select the one having the longest duration among competitive detections. The selected keywords are registered in the pre-index. They are then used to train an SVM-based classifier. In a query term search process, a query term is searched by the same STD engine, and the output candidates are verified by the SVM-based classifier. Our proposed two-stage STD method with pre-indexing was evaluated using the NTCIR-10 SpokenDoc-2 STD task and it drastically outperformed the traditional STD method based on dynamic time warping and a confusion network-based index.

Publication: IEICE TRANSACTIONS on Information Vol.E99-D No.10 pp.2528-2538

Publication Date: 2016/10/01

Publicized: 2016/07/19

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2016SLP0017

Type of Manuscript: Special Section PAPER (Special Section on Recent Advances in Machine Learning for Spoken Language Processing)

Category: Spoken term detection

Authors

Kentaro DOMOTO
  University of Tsukuba
Takehito UTSURO
  University of Tsukuba
Naoki SAWADA
  University of Yamanashi
Hiromitsu NISHIZAKI
  University of Yamanashi

Keyword

decision process, pre-indexing, spoken term detection, support vector machine, verification

Cite this

Copy

Kentaro DOMOTO, Takehito UTSURO, Naoki SAWADA, Hiromitsu NISHIZAKI, "Spoken Term Detection Using SVM-Based Classifier Trained with Pre-Indexed Keywords" in IEICE TRANSACTIONS on Information, vol. E99-D, no. 10, pp. 2528-2538, October 2016, doi: 10.1587/transinf.2016SLP0017.
Abstract: This study presents a two-stage spoken term detection (STD) method that uses the same STD engine twice and a support vector machine (SVM)-based classifier to verify detected terms from the STD engine's output. In a front-end process, the STD engine is used to pre-index target spoken documents from a keyword list built from an automatic speech recognition result. The STD result includes a set of keywords and their detection intervals (positions) in the spoken documents. For keywords having competitive intervals, we rank them based on the STD matching cost and select the one having the longest duration among competitive detections. The selected keywords are registered in the pre-index. They are then used to train an SVM-based classifier. In a query term search process, a query term is searched by the same STD engine, and the output candidates are verified by the SVM-based classifier. Our proposed two-stage STD method with pre-indexing was evaluated using the NTCIR-10 SpokenDoc-2 STD task and it drastically outperformed the traditional STD method based on dynamic time warping and a confusion network-based index.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016SLP0017/_p

Copy

@ARTICLE{e99-d_10_2528,
author={Kentaro DOMOTO, Takehito UTSURO, Naoki SAWADA, Hiromitsu NISHIZAKI, },
journal={IEICE TRANSACTIONS on Information},
title={Spoken Term Detection Using SVM-Based Classifier Trained with Pre-Indexed Keywords},
year={2016},
volume={E99-D},
number={10},
pages={2528-2538},
abstract={This study presents a two-stage spoken term detection (STD) method that uses the same STD engine twice and a support vector machine (SVM)-based classifier to verify detected terms from the STD engine's output. In a front-end process, the STD engine is used to pre-index target spoken documents from a keyword list built from an automatic speech recognition result. The STD result includes a set of keywords and their detection intervals (positions) in the spoken documents. For keywords having competitive intervals, we rank them based on the STD matching cost and select the one having the longest duration among competitive detections. The selected keywords are registered in the pre-index. They are then used to train an SVM-based classifier. In a query term search process, a query term is searched by the same STD engine, and the output candidates are verified by the SVM-based classifier. Our proposed two-stage STD method with pre-indexing was evaluated using the NTCIR-10 SpokenDoc-2 STD task and it drastically outperformed the traditional STD method based on dynamic time warping and a confusion network-based index.},
keywords={},
doi={10.1587/transinf.2016SLP0017},
ISSN={1745-1361},
month={October},}

Copy

TY - JOUR
TI - Spoken Term Detection Using SVM-Based Classifier Trained with Pre-Indexed Keywords
T2 - IEICE TRANSACTIONS on Information
SP - 2528
EP - 2538
AU - Kentaro DOMOTO
AU - Takehito UTSURO
AU - Naoki SAWADA
AU - Hiromitsu NISHIZAKI
PY - 2016
DO - 10.1587/transinf.2016SLP0017
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2016
AB - This study presents a two-stage spoken term detection (STD) method that uses the same STD engine twice and a support vector machine (SVM)-based classifier to verify detected terms from the STD engine's output. In a front-end process, the STD engine is used to pre-index target spoken documents from a keyword list built from an automatic speech recognition result. The STD result includes a set of keywords and their detection intervals (positions) in the spoken documents. For keywords having competitive intervals, we rank them based on the STD matching cost and select the one having the longest duration among competitive detections. The selected keywords are registered in the pre-index. They are then used to train an SVM-based classifier. In a query term search process, a query term is searched by the same STD engine, and the output candidates are verified by the SVM-based classifier. Our proposed two-stage STD method with pre-indexing was evaluated using the NTCIR-10 SpokenDoc-2 STD task and it drastically outperformed the traditional STD method based on dynamic time warping and a confusion network-based index.
ER -