A segmentation algorithm based on acoustical features using a self organizing neural network.

View/Open
Document typeConference report
Defense date1993
Publisher. EUROSPEECH
Rights accessOpen Access
Abstract
In this paper we investigate the use of a self-organizing map in an acoustic segmentation task. The aim is to obtain a limited number of acoustic classes and to segment whenever a change in the class between two adjacent frames occurs. Energy in different frequency ranges is used as input in the map training process. A structure based on a Kohonen map connected to a neural network trained with the back-propagation algorithm is proposed.
CitationMonte, E. A segmentation algorithm based on acoustical features using a self organizing neural network.. A: EUROSPEECH. "?". . EUROSPEECH, 1993, p. 661-663.
Publisher versionhttp://dblp.uni-trier.de/db/conf/interspeech/eurospeech1993.html
Files | Description | Size | Format | View |
---|---|---|---|---|
e93_0661.pdf | 216,7Kb | View/Open |
Except where otherwise noted, content on this work
is licensed under a Creative Commons license
:
Attribution-NonCommercial-NoDerivs 3.0 Spain