Dear guest, welcome to this publication database. As an anonymous user, you will probably not have edit rights. Also, the collapse status of the topic tree will not be persistent. If you like to have these and other options enabled, you might ask Admin (Ivan Eggel) for a login account.
 [BibTeX] [RIS]
Influence of Vector Quantization on Isolated Word Recognition
Type of publication: Inproceedings
Citation: font94:eusip
Booktitle: European Signal Processing Conference (EUSIPCO 94), Edinburgh, UK
Year: 1994
Pages: 115-118
URL: http://diuf.unifr.ch/people/he...
Abstract: Vector Quantization can be considered as a data compression technique. In the last few years, vector quantization has been increasingly applied to reduce problem complexity like pattern recognition. In speech recognition, discrete systems are developed to build up real-time systems. This paper presents original results by comparing the K-Means and the Kohonen approaches on the same recognition platform. Influence of some quantization parameters is also investigated. It can be observed through the results presented in this paper that the quantization quality has a significant influence on the recognition rates. Surprisingly, the Kohonen approach leads to better recognition results despite its poor distortion performance.
Keywords: Kohonen, Speech Recognition, Vector Quantization
Authors Fontaine, Vincent
Hennebert, Jean
Leich, Henri
Added by: []
Total mark: 0
Attachments
    Notes
      Topics