DocumentCode
284740
Title
Using SOMs as feature extractors for speech recognition
Author
Kangas, Jari ; Torkkola, Kari ; Kokkonen, Makko
Author_Institution
Lab. of Inf. & Comput. Sci., Helsinki Univ. of Technol., Espoo, Finland
Volume
2
fYear
1992
fDate
23-26 Mar 1992
Firstpage
341
Abstract
The authors demonstrate that the self-organizing maps (SOMs) of Kohonen can be used as speech feature extractors that are able to take temporal context into account. They have investigated two alternatives for using SOMs as such feature extractors, one based on tracing the location of highest activity on a SOM, the other on integrating the activity of the whole SOM for a period of time. The experiments indicated that an improvement is achievable by using these methods
Keywords
self-organising feature maps; speech recognition; Kohonen self-organising feature maps; feature extractors; speech recognition; temporal context; Artificial neural networks; Clustering algorithms; Computer science; Data mining; Feature extraction; Hidden Markov models; Laboratories; Pattern recognition; Self organizing feature maps; Speech recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech, and Signal Processing, 1992. ICASSP-92., 1992 IEEE International Conference on
Conference_Location
San Francisco, CA
ISSN
1520-6149
Print_ISBN
0-7803-0532-9
Type
conf
DOI
10.1109/ICASSP.1992.226050
Filename
226050
Link To Document