Title :
Word learning in a multimodal environment
Author :
Roy, Deb ; Pentland, Alex
Author_Institution :
Media Lab., MIT, Cambridge, MA, USA
Abstract :
We are creating human machine interfaces which let people communicate with machines using natural modalities including speech and gesture. A problem with current multimodal interfaces is that users are forced to learn the set of words and gestures which the interface understands. We report on a trainable interface which lets the user teach the system words of their choice through natural multimodal interactions
Keywords :
learning systems; natural language interfaces; speech processing; speech recognition; acoustic models; gesture; gestures; human machine interfaces; multimodal environment; multimodal interfaces; natural multimodal interactions; trainable interface; trainable speech recognizer; word learning; Acoustic noise; Buildings; Eyebrows; Eyes; Humans; Man machine systems; Noise shaping; Shape; Speech; Vocabulary;
Conference_Titel :
Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-4428-6
DOI :
10.1109/ICASSP.1998.679702
