Discrete Wavelet Transforms with Multiclass SVM for Phoneme Recognition

被引：0

作者：

Cutajar, M. ^{[1
]}

Gatt, E. ^{[1
]}

Grech, I ^{[1
]}

Casha, O. ^{[1
]}

Micallef, J. ^{[1
]}

机构：

[1] Univ Malta, Fac ICT, Dept Microelect & Nanoelect, Msida, Malta

来源：

2013 IEEE EUROCON | 2013年

关键词：

discrete wavelet transforms; support vector machines; phoneme recognition; speaker-independent;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

A phoneme recognition system based on Discrete Wavelet Transforms (DWT) and Support Vector Machines (SVMs), is designed for multi-speaker continuous speech environments. Phonemes are divided into frames, and the DWTs are adopted, to obtain fixed dimensional feature vectors. For the multiclass SVM, the One-against-one method with the RBF kernel was implemented. To further improve the accuracies obtained, a priority scheme was added, to forecast the three most likely phonemes. After classification, all frames were again re-grouped, in order to evaluate the accuracy of the system according to the substitution, deletion and insertion errors. The percentage correct and accuracy, obtained from the designed phoneme recognition system, were 63.08% and 53.27% respectively. All tests were carried out on the TIMIT database. This phoneme recognition system is intended to be implemented on a dedicated chip, to improve the speed of the software implementation by approximately 100 times.

引用

页码：1689 / 1694

页数：6

共 50 条

[1] The use of wavelet transforms in phoneme recognition
Tan, BT
Fu, MY
Spray, A
Dermody, P
[J]. ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 2431 - 2434
[2] ASIC design of a Phoneme Recogniser based on Discrete Wavelet Transforms and Support Vector Machines
Cutajar, M.
Gatt, E.
Grech, I
Casha, O.
[J]. 2014 10TH CONFERENCE ON PH.D. RESEARCH IN MICROELECTRONICS AND ELECTRONICS (PRIME 2014), 2014,
[3] Face recognition using decimated redundant discrete wavelet transforms
Li, Deqiang
Tang, Xusheng
Pedrycz, Witold
[J]. MACHINE VISION AND APPLICATIONS, 2012, 23 (02) : 391 - 401
[4] Face recognition using decimated redundant discrete wavelet transforms
Deqiang Li
Xusheng Tang
Witold Pedrycz
[J]. Machine Vision and Applications, 2012, 23 : 391 - 401
[5] Design of a Hardware-based Discrete Wavelet Transform Architecture for Phoneme Recognition
Cutajar, M.
Gatt, E.
Grech, I.
Casha, O.
Micallef, J.
[J]. 2014 6TH INTERNATIONAL SYMPOSIUM ON COMMUNICATIONS, CONTROL AND SIGNAL PROCESSING (ISCCSP), 2014, : 554 - 557
[6] Redundant discrete wavelet transforms based moving object recognition and tracking
Gao Tao
Liu Zhengguang
Zhang Jun
[J]. JOURNAL OF SYSTEMS ENGINEERING AND ELECTRONICS, 2009, 20 (05) : 1115 - 1123
[7] Redundant discrete wavelet transforms based moving object recognition and tracking
Gao Tao
[J]. Journal of Systems Engineering and Electronics, 2009, 20 (05) : 1115 - 1123
[8] CONTINUOUS AND DISCRETE WAVELET TRANSFORMS
HEIL, CE
WALNUT, DF
[J]. SIAM REVIEW, 1989, 31 (04) : 628 - 666
[9] Adaptive wavelet based phoneme recognition
Kadambe, S
Srinivasan, P
[J]. 40TH MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1 AND 2, 1998, : 720 - 723
[10] Discrete wavelet transforms using Daubechies wavelet
Rao, IU
[J]. IETE JOURNAL OF RESEARCH, 2001, 47 (3-4) : 169 - 171

← 1 2 3 4 5 →