A Computational Model of Language Acquisition: the Emergence of Words

• Autorzy: ten Bosch L. , Boves L. , Van Hamme H. , Moore R.K.
• Języki publikacji: EN

Abstrakty

EN

In this paper, we discuss a computational model that is able to detect and build word-like representations on the basis of sensory input. The model is designed and tested with a further aim to investigate how infants may learn to communicate by means of spoken language. The computational model makes use of a memory, a perception module, and the concept of 'learning drive'. Learning takes place within a communicative loop between a 'caregiver' and the 'learner'. Experiments carried out on three European languages with different genetic background (Finnish, Swedish, and Dutch) show that a robust word representation can be learned in using less than 100 acoustic tokens (examples) of that word. The model is inspired by the memory structure that is assumed functional for human cognitive processing.

Słowa kluczowe

EN

I5 pattern recognition; J5 arts and humanities; F5 theory of computation; miscellaneous; cognitive modelling

• Wydawca: IOS Press
• Czasopismo: Fundamenta Informaticae
• Rocznik: 2009
• Tom: Vol. 90, nr 3
• Strony: 229--249
• Opis fizyczny: bibliogr. 42 poz., wykr.

Twórcy

autor

ten Bosch L.

autor

Boves L.

autor

Van Hamme H.

autor

Moore R.K.

• Centre for Language and Speech Technology Radboud University P.O. Box 9103, 6500 HD Nijmegen, the Netherlands,

Bibliografia

• [1] Baddeley, A.: Working Memory, Clarendon Press, Oxford, 1986.
• [2] Bellegarda, J.: Exploiting Latent Semantic Information for Statistical Language Modeling, Proceedings of the IEEE, 88, 2000, 1279-1296.
• [3] ten Bosch, L., Kirchhoff, K.: Bridging the gap between human and automatic speech recognition, Speech Communication, 49, 2007, 331-335.
• [4] Cooke, M., Ellis, D.: The auditory organization of speech and other sources in listeners and computational models, Speech Communication, 35, 2001, 141-177.
• [5] Cutler, A., McQueen, J., Butterfield, S., Norris, D.: Prelexically-driven perceptual retuning of phoneme boundaries, Proc. Interspeech 2008, ISCA, Brisbane, Australia. September 2008, 2008.
• [6] den Os, E., Boves, L., Rossignol, S., ten Bosch, L., Vuurpijl, L.: ConversationalAgent or DirectManipulation in Human-System Interaction, Speech Communication, 47, 2005, 194-207.
• [7] Ernestus, M., Baayen, R., Schreuder, R.: The recognition of reduced word forms, Brain and Language, 81, 2002, 162-173.
• [8] Goldinger, S.: Words and voices: episodic traces in spoken word identification and recognition memory, Journal Experimental Psychology Learning Memory Cognition, 22, 1996, 1166-1183.
• [9] Goldinger, S.: Echoes of echoes? An episodic theory of lexical access, Psychological Review, 105, 1998, 251-279.
• [10] Van hamme, H.: HAC-models: a Novel Approach to Continuous Speech Recognition, Proceedings Interspeech, ISCA, Brisbane, Australia. September 2008, 2008.
• [11] Hermansky, H.: Auditory modeling in automatic recognition of speech, ESCA Workshop on the Auditory basis of speech perception, Keele University (UK), 15-19 July, 1996.
• [12] Hintzman, D.: Schema-abstraction in a multiple-trace memory model, Psychological Review, 93, 1986, 411-427.
• [13] Hoyer, P.: Non-negative matrix factorization with sparseness constraints, Journal of Machine Learning Research, 5, 2004, 1457-1469.
• [14] Johnson, S.: Emergence, New York: Scribner, 2002.
• [15] Jones, D., Hughes, R., Macken, W.: Perceptual organization masquerading as phonological storage: Further support for a perceptual-gestural view of short-term memory, Journal Memory and Language, 54, 2006, 265-281.
• [16] Kaplan, F., Oudeyer, P.-Y., Bergen, B.: Computational Models in the Debate Over Language Learnability, Infant and Child Development, 17, 2008, 55-80.
• [17] Kuhn, R., Nowell, P., Drouin, C.: Approaches to Phoneme-Based Topic Spotting: An Experimental Comparison, Proceedings ICASSP, 1997.
• [18] Lee, D., Seung, H.: Algorithms for non-negative matrix factorization, Advances in Neural Information Processing Systems, 13, 2001.
• [19] Lippmann, R.: Speech Recognition by Human and Machines, Speech Communication, 22, 1997, 1-14.
• [20] MacWhinney, B.: Models of the emergence of language, Annual Review of Psychology, 49, 1998, 199-227.
• [21] Maloof, M., Michalski, R.: Incremental learning with partial instance memory, Artificial Intelligence, 154, 2004, 95-126.
• [22] Marr, D. C.: Vision: A computational investigation into the human representation and processing of visual information, W.H.Freeman & Co Ltd., 1982.
• [23] Maslow, A.: Motivation and Personality, New York: Harper & Row, 1954.
• [24] McClelland, J., Elman, J.: The TRACE model of speech perception, Cognitive Psychology, 18, 1986, 1-86.
• [25] McMurray, B.: Defusing the childhood vocabulary explosion, Science, 317, 2007, 631.
• [26] Moore, R.: A comparison of the data requirements of automatic speech recognition systems and human listeners, Proceedings EUROSPEECH'03, Geneva, 2003.
• [27] Newport, E., Aslin, R.: Learning at a distance: I. Statistical learning of non-adjacent dependencies, Cognitive Psychology, 48, 2004, 127-162.
• [28] Norris, D.: Shortlist: A connectionist model of continuous speech recognition, Cognition, 52, 1994, 189-234.
• [29] Norris, D.: How do computational models help us develop better theories?, A. Cutler (Ed.), Twenty-first century psycholinguistics: Four cornerstones, 2005, 331-346.
• [30] Ostendorf, M.: Moving beyond the 'beads-on-a-string' model of speech, Proc. IEEE ASRU-99, Keystone, Colorado, USA. Dec 12-15, 1999.
• [31] Park, A., Glass, J.: Unsupervised pattern discovery in speech, Transactions of the ASLP, 16, 2008, 186-197.
• [32] Pfeifer, R., Scheier, C.: Understanding Intelligence, Cambridge, Mass.: MIT Press, 1999.
• [33] Roy, D., Pentland, A.: Learning words from sights and sounds: a computational model, Cognitive Science, 26, 2002, 113-146.
• [34] Sarma, A., van der Hoek, A.: A Needs Hierarchy for Teams, ISR Technical Report: UCI-ISR-04-9, 2004.
• [35] Scharenborg, O., Norris, D., ten Bosch, L., McQueen, J.: How should a speech recognizer work?, Cognitive Science: A Multidisciplinary Journal, 29(6), 2005, 867-918.
• [36] Snow, C., Ferguson, C.: Talking to children: language input and acquisition, Cambridge, New York: Cambridge University Press, 1977.
• [37] Sroka, J., Braida, L.: Human and machine consonant recognition, Speech Communication, 44, 2005, 401-423.
• [38] Stouten, V., Demuynck, K., Van hamme, H.: Automatically Learning the Units of Speech by Non-negative Matrix Factorisation, Proceedings Interspeech-2007, Antwerp, 2007.
• [39] Wang, Y.: Cognitive Informatics: A new transdiciplinary research field, Brain and Mind, 4, 2003, 115-127.
• [40] Wang, Y.: On cognitive informatics foundations of knowledge and formal knowledge systems, Proc. ICCI 2007, IEEE, Lake Tahoe, California, USA. August 2007, 2007.
• [41] Werker, J., Curtis, S.: PRIMIR: a developmental framework for infant speech processing, Language Learning and Development, 1, 2005, 197-234.
• [42] Wesker, T., Meyer, B., Wagener, K., Anemueller, J., Mertins, A., Kollmeier, B.: Oldenburg logatome speech corpus (OLLO) for speech recognition experiments with humans and machines, Proceeding of Interspeech-2005, Lisboa, 2005.