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
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;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1992. ICASSP-92., 1992 IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0532-9
DOI :
10.1109/ICASSP.1992.226050
