Title
Dynamic fixed-point arithmetic design of embedded SVM-Based speaker identification system
Abstract
This work proposes a dynamic fixed-point arithmetic design for SVM-based speaker identification in embedded environment The whole speaker identification system includes LPCC extraction, SVM training with sequential minimal optimization (SMO), and SVM recognition The proposed dynamic fixed-point design is applied to each arithmetic procedure and fixed-point error analysis is also performed The fixed-point SVM-based speaker identification system have been implemented and evaluated on ARM9 DMA2400 The experimental results show that the speaker identification accuracy is slightly degraded with the proposed dynamic fixed-point technique.
Year
DOI
Venue
2010
10.1007/978-3-642-13318-3_65
ISNN (2)
Keywords
Field
DocType
dynamic fixed-point arithmetic design,proposed dynamic fixed-point technique,speaker identification accuracy,whole speaker identification system,embedded svm-based speaker identification,svm recognition,svm-based speaker identification,fixed-point error analysis,svm training,proposed dynamic fixed-point design,fixed-point svm-based speaker identification,sequential minimal optimization,fixed point,support vector machine,fixed point arithmetic
ARM9,Speaker identification,Pattern recognition,Fixed-point arithmetic,Computer science,Support vector machine,Speech recognition,Artificial intelligence,Sequential minimal optimization,Machine learning
Conference
Volume
ISSN
ISBN
6064
0302-9743
3-642-13317-7
Citations 
PageRank 
References 
1
0.35
2
Authors
4
Name
Order
Citations
PageRank
Jhing-fa Wang1982114.31
Ta-Wen Kuan2376.59
Jia-Ching Wang351558.13
Ta-Wei Sun420.70