Modelling Early Language Acquisition Skills: Towards a General Statistical Learning Mechanism

This paper reports the on-going research of a thesis project investigating a computational model of early language acquisition. The model discovers word-like units from cross-modal input data and builds continuously evolving internal representations within a cognitive model of memory. Current cognitive theories suggest that young infants employ general statistical mechanisms that exploit the statistical regularities within their environment to acquire language skills. The discovery of lexical units is modelled on this behaviour as the system detects repeating patterns from the speech signal and associates them to discrete abstract semantic tags. In its current state, the algorithm is a novel approach for segmenting speech directly from the acoustic signal in an unsupervised manner, therefore liberating it from a pre-defined lexicon. By the end of the project, it is planned to have an architecture that is capable of acquiring language and communicative skills in an online manner, and carry out robust speech recognition. Preliminary results already show that this method is capable of segmenting and building accurate internal representations of important lexical units as 'emergent' properties from cross-modal data.

[1]  Katherine S. White,et al.  A Statistical Basis for Speech Sound Discrimination , 2003, Language and speech.

[2]  Shane S. Sturrock,et al.  Time Warps, String Edits, and Macromolecules – The Theory and Practice of Sequence Comparison . David Sankoff and Joseph Kruskal. ISBN 1-57586-217-4. Price £13.95 (US$22·95). , 2000 .

[3]  P. Kuhl Early language acquisition: cracking the speech code , 2004, Nature Reviews Neuroscience.

[4]  Hugo Van hamme,et al.  Discovering Phone Patterns in Spoken Utterances by Non-Negative Matrix Factorization , 2008, IEEE Signal Processing Letters.

[5]  S. Trehub,et al.  Tuning in to musical rhythms: infants learn more readily than adults. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[6]  Scott P. Johnson,et al.  Visual statistical learning in infancy: evidence for a domain general learning mechanism , 2002, Cognition.

[7]  P. D. Eimas,et al.  Speech Perception in Infants , 1971, Science.

[8]  Michael Don Palmer,et al.  Reflections on language , 1977 .

[9]  P. Jusczyk,et al.  Infants′ Sensitivity to the Sound Patterns of Native Language Words , 1993 .

[10]  R N Aslin,et al.  Statistical Learning by 8-Month-Old Infants , 1996, Science.

[11]  Jenny R. Saffran,et al.  Does Grammar Start Where Statistics Stop? , 2002, Science.

[12]  James R. Glass,et al.  Unsupervised Pattern Discovery in Speech , 2008, IEEE Transactions on Audio, Speech, and Language Processing.

[13]  Bert Cranen,et al.  A computational model for unsupervised word discovery , 2007, INTERSPEECH.

[14]  Elizabeth K. Johnson,et al.  Statistical learning of tone sequences by human infants and adults , 1999, Cognition.

[15]  Morten H. Christiansen,et al.  Learning to Segment Speech Using Multiple Cues: A Connectionist Model , 1998 .

[16]  C. Best,et al.  Examination of perceptual reorganization for nonnative speech contrasts: Zulu click discrimination by English-speaking adults and infants. , 1988, Journal of experimental psychology. Human perception and performance.

[17]  Dylan M. Jones,et al.  Perceptual organization masquerading as phonological storage: Further support for a perceptual-gestural view of short-term memory , 2006 .

[18]  M. Brent Speech segmentation and word discovery: a computational perspective , 1999, Trends in Cognitive Sciences.

[19]  Roger K. Moore,et al.  The application of dynamic programming techniques to non-word based topic spotting , 1995, EUROSPEECH.

[20]  Alex Pentland,et al.  Learning words from sights and sounds: a computational model , 2002, Cogn. Sci..

[21]  J R Saffran,et al.  The acquisition of language by children , 2001, Proceedings of the National Academy of Sciences of the United States of America.