Discovering keywords from cross-modal input: ecological vs. engineering methods for enhancing acoustic repetitions

This paper introduces a computational model that automati­ cally segments acoustic speech data and builds internal repre­ sentations of keyword classes from cross-modal (acoustic and pseudo-visual) input. Acoustic segmentation is achieved using a novel dynamic time warping technique and the focus of this paper is on recent investigations conducted to enhance the iden­ tification of repeating portions of speech. This ongoing research is inspired by current cognitive views of early language acqui­ sition and therefore strives for ecological plausibility in an at­ tempt to build more robust speech recognition systems. Results show that an ad-hoc computationally engineered solution can aid the discovery of repeating acoustic patterns. However, we show that this improvement can be simulated in a more ecolog­ ically valid way.