より詳細な情報
画像および音声認識
Using self-organizing maps for object classification in image analysis
Heiss-Czedik and Bajla (2005) Measurement Science Review 5:11
The recombinant form (rEpo) of eerythropoietin, a hormone used for doping, involves analysis of Epo chemiluminescence images containing bands. A research project funded by the World Anti-Doping Agency was established to develop software for Epo testing. The 506 objects of the training set were ordered by SOMs using Viscovery SOMine, which was chosen because of its visualization capabilities. After segmentation of band data, artifacts must be separated from the authentic bands. A classification method based on self-organizing map performs well when compared with other classification methods.
Neural networks for text-to-speech phoneme recognition
Embrechts and Arciniegas (2000) 2000 IEEE International Conference on Systems, Man, and Cybernetics 5:3582-3587
Two different artificial neural network (ANN) approaches were used for phoneme recognition for text-to-speech applications: staged backpropagation neural networks and self-organizing maps. Several current commercial approaches rely on an exhaustive dictionary approach for text-to-phoneme conversion. Applying neural networks to phoneme mapping for text-to-speech conversion creates a fast distributed recognition engine. This engine not only supports the mapping of missing words in the database, but it can also mitigate contradictions related to different pronunciations for the same word. The ANNs presented in this work were trained based on the 2,000 most common words in American English. Performance metrics for the 5,000, 7,000 and 10,000 most common words in English were also estimated to test the robustness of these neural networks.
