SCORE NORMALIZATION AND SYSTEM COMBINATION FOR IMPROVED KEYWORD SPOTTING

被引：0

作者：

Karakos, Damianos ^{[1
]}

Schwartz, Richard ^{[1
]}

Tsakalidis, Stavros ^{[1
]}

Zhang, Le ^{[1
]}

Ranjan, Shivesh ^{[1
]}

Ng, Tim ^{[1
]}

Hsiao, Roger ^{[1
]}

Saikumar, Guruprasad ^{[1
]}

Bulyko, Ivan ^{[1
]}

Long Nguyen ^{[1
]}

Makhoul, John ^{[1
]}

Grezl, Frantisek ^{[2
]}

Hannemann, Mirko ^{[2
]}

Karafiat, Martin ^{[2
]}

Szoke, Igor ^{[2
]}

Vesely, Karel ^{[2
]}

Lamel, Lori ^{[3
]}

Le, Viet-Bac ^{[4
]}

机构：

[1] Raytheon BBN Technol, Cambridge, MA 02138 USA

[2] Brno Univ Technol, SpeechFIT, Brno, Czech Republic

[3] CNRS LIMSI, Paris, France

[4] Vocapia Res, Paris, France

来源：

2013 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING (ASRU) | 2013年

关键词：

keyword search; score normalization; system combination; indexing and search;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present two techniques that are shown to yield improved Keyword Spotting (KWS) performance when using the ATWV/MTWV performance measures: (i) score normalization, where the scores of different keywords become commensurate with each other and they more closely correspond to the probability of being correct than raw posteriors; and (ii) system combination, where the detections of multiple systems are merged together, and their scores are interpolated with weights which are optimized using MTWV as the maximization criterion. Both score normalization and system combination approaches show that significant gains in ATWV/MTWV can be obtained, sometimes on the order of 8-10 points (absolute), in five different languages. A variant of these methods resulted in the highest performance for the official surprise language evaluation for the IARPA-funded Babel project in April 2013.

引用

页码：210 / 215

页数：6

共 50 条

[21] Improved lattice-based speech keyword spotting algorithm
Department of Electronic Engineer, Tsinghua University, Beijing
100084, China
Qinghua Daxue Xuebao, 5 (508-513): : 508 - 513
[22] An improved Mandarin keyword spotting system using mce training and context-enhanced verification
Liang, JiaEn
Meng, Meng
Wang, XiaoRui
Ding, Peng
Xu, Bo
2006 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-13, 2006, : 1145 - 1148
[23] A keyword spotting method
Guo, R
Zhu, XY
PROCEEDINGS OF THE 4TH ASIA-PACIFIC CONFERENCE ON CONTROL & MEASUREMENT, 2000, : 301 - 304
[24] Non-Keyword Model for the Improvement of Vocabulary Independent Keyword Spotting System
Kim, Min-Je
Lee, Jung-Chul
JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA, 2006, 25 (07): : 319 - 324
[25] KEYWORD AND PHRASE SPOTTING BY USE OF HARPY SPEECH SYSTEM
LOWERRE, BT
REDDY, R
JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1978, 64 : S182 - S182
[26] Keyword spotting system based on biomimetic pattern recognition
Wu Yan
Shi Ning
Wang Shoujue
CHINESE JOURNAL OF ELECTRONICS, 2006, 15 (4A): : 903 - 906
[27] A spoken dialogue system based on keyword spotting technology
Zhang, Pengyuan
Zhao, Qingwei
Yan, Yonghong
HUMAN-COMPUTER INTERACTION, PT 3, PROCEEDINGS, 2007, 4552 : 253 - +
[28] Discriminative keyword spotting
Keshet, Joseph
Grangier, David
Bengio, Samy
SPEECH COMMUNICATION, 2009, 51 (04) : 317 - 329
[29] A Keyword Spotting Based Sports Type Determination System
Lu, Li
Xu, Ran
Ge, Fengpei
Zhao, Qingwei
Yan, Younghong
2009 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND COMPUTATIONAL INTELLIGENCE, VOL II, PROCEEDINGS, 2009, : 361 - 365
[30] TSDNet: An Efficient Light Footprint Keyword Spotting Deep Network Base on Tempera Segment Normalization
Chen, Fei
Xue, Hui
Fang, Pengfei
PROCEEDINGS OF THE 2024 27 TH INTERNATIONAL CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK IN DESIGN, CSCWD 2024, 2024, : 335 - 340

← 1 2 3 4 5 →