Robust speech recognizer using multiclass SVM

被引：0

作者：

Gavat, I ^{[1
]}

Costache, G ^{[1
]}

Iancu, C ^{[1
]}

机构：

[1] Univ Politehn Bucuresti, Bucharest, Romania

来源：

NEUREL 2004: SEVENTH SEMINAR ON NEURAL NETWORK APPLICATIONS IN ELECTRICAL ENGINEERING, PROCEEDINGS | 2004年

关键词：

robust speech; bimodal system; support vector machines; neural networks;

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：

In this paper a robust speech recognizer is presented based on features obtained from the speech signal. and also from the image of the speaker. The features were combined by simple concatenation, resulting composed feature vectors to train the models corresponding to each class. For recognition, the classification process relies on a very effective algorithm, namely the multiclass SVM. Under additive noise conditions the bimodal system based on combined features acts better than the unimodal systems based only on the speech features, the added Information obtained from the Image, playing an important role In robustness Improvement.

引用

页码：63 / 66

页数：4

共 50 条

[31] Multiclass Classification of Disease Using CNN and SVM of Medical Imaging
Tiwari, Pallavi
Upadhyay, Deepak
Pant, Bhaskar
Mohd, Noor
ADVANCES IN COMPUTING AND DATA SCIENCES (ICACDS 2022), PT II, 2022, 1614 : 88 - 99
[32] "A speech recognizer" a tool to recognize the high clarity speech signal based on existing speech using ISCA
Velammal, M. Navaneetha
Kumar, P. Nirmal
ANALOG INTEGRATED CIRCUITS AND SIGNAL PROCESSING, 2019, 98 (01) : 41 - 58
[33] Approximate Multiobjective Multiclass SVM by Using the Reference Point Method
Matsugi, Yasuhiro
Sugimoto, Takafumi
Qi, Yuxiao
Kusunoki, Yoshifumi
Tatsumi, Keiji
2018 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2018, : 3535 - 3540
[34] A Hierarchical SVM Based Multiclass Classification by Using Similarity Clustering
Dong, Chao
Zhou, Bo
Hu, Jinglu
2015 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2015,
[35] “A speech recognizer” a tool to recognize the high clarity speech signal based on existing speech using ISCA
M. Navaneetha Velammal
P. Nirmal Kumar
Analog Integrated Circuits and Signal Processing, 2019, 98 : 41 - 58
[36] A SVM-based cursive character recognizer
Camastra, Francesco
PATTERN RECOGNITION, 2007, 40 (12) : 3721 - 3727
[37] Wearable IoT based diagnosis of prostate cancer using GLCM-multiclass SVM and SIFT-multiclass SVM feature extraction strategies
Chandrasekhara, Swetha Parvatha Reddy
Kabadi, Mohan G.
Srivinay
INTERNATIONAL JOURNAL OF PERVASIVE COMPUTING AND COMMUNICATIONS, 2024, 20 (01) : 19 - 37
[38] An Effective Feature Compensation Scheme Tightly Matched with Speech Recognizer Employing SVM-based GMM Generation
Kim, Wooil
Suh, Jun-Won
Hansen, John H. L.
11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 3 AND 4, 2010, : 2078 - 2081
[39] Using boosting to improve a hybrid hmm/neural network speech recognizer
Schwenk, H
ICASSP '99: 1999 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS VOLS I-VI, 1999, : 1009 - 1012
[40] HMM-based speech recognizer using overlapping articulatory features
Erler, Kevin
Freeman, George H.
Journal of the Acoustical Society of America, 1996, 100 (4 pt 1):

← 1 2 3 4 5 →