In this paper, we discuss a computational model of language acquisition which focuses on the detection of words and that is able to detect and build word-like representations on the basis of multimodal input data. Experiments carried out on three European languages (Finnish, Swedish, and Dutch) show that internal word representations can be learned without a predefined lexicon. The computational model is inspired by a memory structure that is assumed to be functional for human cognitive processing. The model does not use any prior segmentation, nor does it use the concept of segmentation later in the processing. This calls into question the importance that is conventionally attributed to the segmentation of the speech signal in terms of symbolic units for the purpose of detecting structure in speech.
Cite as: Bosch, L.t., Van hamme, H., Boves, L. (2008) Unsupervised detection of words - questioning the relevance of segmentation. Proc. ISCA ITRW on Speech Analysis and Processing for Knowledge Discovery, paper 046
@inproceedings{bosch08_spkd,
author={Louis ten Bosch and Hugo {Van hamme} and Lou Boves},
title={{Unsupervised detection of words - questioning the relevance of segmentation}},
year=2008,
booktitle={Proc. ISCA ITRW on Speech Analysis and Processing for Knowledge Discovery},
pages={paper 046}
}