Pii: S0364-0213(01)00061-1
نویسندگان
چکیده
This paper presents an implemented computational model of word acquisition which learns directly from raw multimodal sensory input. Set in an information theoretic framework, the model acquires a lexicon by finding and statistically modeling consistent cross-modal structure. The model has been implemented in a system using novel speech processing, computer vision, and machine learning algorithms. In evaluations the model successfully performed speech segmentation, word discovery and visual categorization from spontaneous infant-directed speech paired with video images of single objects. These results demonstrate the possibility of using state-of-the-art techniques from sensory pattern recognition and machine learning to implement cognitive models which can process raw sensor data without the need for human transcription or labeling. © 2002 Cognitive Science Society, Inc. All rights reserved.
منابع مشابه
Learning words from sights and sounds: a computational model
This paper presents a model of word acquisition which learns from multimodal sensory input. Set in an information theoretic framework, the model acquires a lexicon by nding and statistically modeling consistent inter-modal structure. Learning is achieved from multimodal sensor data without any human annotation. An implementation of this model was able to acquire a primitive audio-visual lexicon...
متن کاملErratum to "Memories for goals: An activation-based model"[Cognitive Science 26 (2002) 39-83]
The publisher regrets that the errors listed below occurred during the processing of the above-referenced paper. p. 39: " Towers of Hanoi " in the list of keywords should read " Tower of Hanoi " p. 71: " Substituting into Equation A1 " (above Eq. A3) should read " Substituting into Equation 1 " p. 71: " n ϭ 1 " as the summation index in Eq. A3 should read " i ϭ 1 " p. 71: " converges if s Ͻ 0.5...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2002