Exploiting Phoneme Similarities in Hybrid HMM-ANN Keyword Spotting

被引：0

作者：

Pinto, Joel ^{[1
]}

Lovitt, Andrew ^{[1
]}

Hermansky, Hynek ^{[1
]}

机构：

[1] IDIAP Res Inst, Martigny, Switzerland

来源：

INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4 | 2007年

关键词：

keyword spotting; confusion matrix; HMM-ANN hybrid decoding;

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 propose a technique for generating alternative models for keywords in a hybrid hidden Markov model - artificial neural network (HMM-ANN) keyword spotting paradigm. Given a base pronunciation for a keyword from the lookup dictionary, our algorithm generates a new model for a keyword which takes into account the systematic errors made by the neural network and avoiding those models that can be confused with other words in the language. The new keyword model improves the keyword detection rate while minimally increasing the number of false alarms.

引用

页码：2388 / 2391

页数：4

共 50 条

[1] A Hybrid HMM/DNN Approach to Keyword Spotting of Short Words
Chen, I-Fan
Lee, Chin-Hui
[J]. 14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5, 2013, : 1573 - 1577
[2] Hybrid HMM/DNN System for Arabic Handwriting Keyword Spotting
Rouhou, Ahmed Cheikh
Kessentini, Yousri
Kanoun, Slim
[J]. IMAGE ANALYSIS AND RECOGNITION, ICIAR 2019, PT I, 2019, 11662 : 216 - 227
[3] Experiments on Hiwire database using Denoising and Adaptation with a hybrid HMM-ANN Model
Gemello, Roberto
Mana, Franco
Scanzio, Stefano
[J]. INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 209 - +
[4] An approach of keyword spotting based on HMM
Yan, BF
Guo, R
Zhu, XY
Zhang, B
[J]. PROCEEDINGS OF THE 3RD WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-5, 2000, : 2757 - 2759
[5] 基于HMM-ANN的咳嗽音识别
石锐
郑晓平
何庆华
[J]. 世界科技研究与发展, 2012, 34 (05) : 751 - 753
[6] A Discriminative Training Method Applied to a Hybrid ANN/HMM Phoneme Recognizer
Lopes, Carla
Perdigao, Fernando
[J]. ICSP: 2008 9TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, VOLS 1-5, PROCEEDINGS, 2008, : 1982 - 1985
[7] Discriminatively trained phoneme confusion model for keyword spotting
Karanasou, Panagiota
Burget, Lukas
Vergyri, Dimitra
Akbacak, Murat
Mandal, Arindam
[J]. 13TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2012 (INTERSPEECH 2012), VOLS 1-3, 2012, : 2433 - 2436
[8] Failure simulation for a phoneme HMM based keyword spotter
Holzapfel, M
Ruske, G
Hoge, H
[J]. 1997 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I - V: VOL I: PLENARY, EXPERT SUMMARIES, SPECIAL, AUDIO, UNDERWATER ACOUSTICS, VLSI; VOL II: SPEECH PROCESSING; VOL III: SPEECH PROCESSING, DIGITAL SIGNAL PROCESSING; VOL IV: MULTIDIMENSIONAL SIGNAL PROCESSING, NEURAL NETWORKS - VOL V: STATISTICAL SIGNAL AND ARRAY PROCESSING, APPLICATIONS, 1997, : 911 - 914
[9] Phoneme based acoustics keyword spotting in informal continuous speech
Szöke, I
Schwarz, P
Matejka, P
Burget, L
Karafiát, M
Cemocky, J
[J]. TEXT, SPEECH AND DIALOGUE, PROCEEDINGS, 2005, 3658 : 302 - 309
[10] HYBRID CONTEXT DEPENDENT CD-DNN-HMM KEYWORD SPOTTING (KWS) IN SPEECH CONVERSATIONS
Tyagi, Vivek
[J]. 2016 IEEE 26TH INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2016,

← 1 2 3 4 5 →