Fast approximate matching algorithm for phone-based keyword spotting

被引：0

作者：

Zhang, Xin ^{[1
]}

Cai, Meng ^{[1
]}

Liu, Jia ^{[1
]}

机构：

[1] Department of Electronic Engineering, Tsinghua University, Beijing, China

来源：

Journal of Networks | 2013年 / 8卷 / 10期

基金：

中国国家自然科学基金;

关键词：

Artificial intelligence;

D O I：

10.4304/jnw.8.10.2227-2233

中图分类号：

学科分类号：

摘要：

Generally, exact matching is widely used for keyword spotting (KWS). Its performance depends heavily on the recognition accuracy. As for phone-based KWS system, the influence of phoneme error rate (PER) on KWS increases as the length of phoneme sequence for the keyword grows. Approximate matching is an alteration to compensate errors in recognition. Compared to exact matching, the calculation cost of approximate matching is extremely larger, limiting its application in KWS systems. In this paper, a fast approximate matching algorithm based on phone confusion network (PCN) is proposed. Given the keyword sequence, only paths with possible minimum edit distance are reserved during detection. Then others with larger edit distance are generated by detected ones. All paths are split into sub-paths during processing, which further reduces calculation cost effectively. Experimental results show that our algorithm is faster significantly than before optimization, with little performance degradation. © 2013 ACADEMY PUBLISHER.

引用

页码：2227 / 2233

共 50 条

[21] An utterance verification algorithm in keyword spotting system
Dai, HS
Zhu, XY
Luo, YP
Yang, SY
PATTERN RECOGNITION AND IMAGE ANALYSIS, PT 2, PROCEEDINGS, 2005, 3523 : 555 - 561
[22] BTH:An efficient parsing algorithm for keyword spotting
Yano, Takehide
Sasajima, Munehiko
Kono, Yasuyuki
Transactions of the Japanese Society for Artificial Intelligence, 2002, 17 (06) : 658 - 666
[23] Fast algorithm for approximate string matching on gene sequences
Liu, Z
Chen, X
Borneman, J
Jiang, T
COMBINATORIAL PATTERN MATCHING, PROCEEDINGS, 2005, 3537 : 79 - 90
[24] Feature matching algorithm based on KAZE and fast approximate nearest neighbor search
Cai, Ze-Ping
Xiao, De-Gui
PROCEEDINGS OF THE 3RD INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND SERVICE SYSTEM (CSSS), 2014, 109 : 270 - 273
[25] A Simple, Fast, Filter-Based Algorithm for Approximate Circular Pattern Matching
Azim, Md. Aashikur Rahman
Iliopoulos, Costas S.
Rahman, M. Sohel
Samiruzzaman, M.
IEEE TRANSACTIONS ON NANOBIOSCIENCE, 2016, 15 (02) : 95 - 102
[26] Improved Keyword Spotting based on Keyword/Garbage Models
Chen, Qiyu
Zhang, Weibin
Xu, Xiangmin
Xing, Xiaofen
2016 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2016,
[27] A Mobile Phone-based Arrhythmia Recognition System Using Characteristic Matching Scheme
Ho, Chen-Shie
Chang, Yu-Mei
2018 INTERNATIONAL CONFERENCE ON COMPUTER, COMMUNICATIONS AND MECHATRONICS ENGINEERING (CCME 2018), 2018, 332 : 111 - 114
[28] An approach of keyword spotting based on HMM
Yan, BF
Guo, R
Zhu, XY
Zhang, B
PROCEEDINGS OF THE 3RD WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-5, 2000, : 2757 - 2759
[29] Phone-based diagnostics dials in
Gefvert, Barbara
LASER FOCUS WORLD, 2015, 51 (08): : 57 - 57
[30] A fast bit-vector algorithm for approximate string matching based on dynamic programming
Myers, G
COMBINATORIAL PATTERN MATCHING, 1998, 1448 : 1 - 13

← 1 2 3 4 5 →