A computational model of word segmentation from continuous speech using transitional probabilities of atomic acoustic events

Cognition

Volumn 120, Issue 2, 2011, Pages 149-176

  Räsänen, Okko ^a  

^a AALTO UNIVERSITY   (Finland)

Author keywords

Distributional learning; Language acquisition; Unsupervised learning; Word segmentation

Indexed keywords

ALGORITHM; ARTICLE; FEMALE; GESTURE; HUMAN; HUMAN EXPERIMENT; LEARNING; LINGUISTICS; MALE; MATHEMATICAL MODEL; PHONEME; PHONETICS; PRIORITY JOURNAL; PROBABILITY; PROFESSIONAL KNOWLEDGE; SPEECH; SPEECH ARTICULATION; TASK PERFORMANCE; WORD SEGMENTATION;

ADULT; FEMALE; HUMANS; INFANT; LANGUAGE; LANGUAGE DEVELOPMENT; MALE; MODELS, PSYCHOLOGICAL; SPEECH; SPEECH PERCEPTION; VERBAL LEARNING;

EID: 79959228147     PISSN: 00100277     EISSN: 18737838     Source Type: Journal    
DOI: 10.1016/j.cognition.2011.04.001     Document Type: Article

References (71)

1. Ahissar E., Ahissar M. Processing of the temporal envelope of speech. The auditory cortex: A synthesis of human and animal research 2005, Lawrence Erlbaum Associates, New Jersey. R. König, P. Heil, E. Budinger, H. Scheich (Eds.).
2. Aimetti, G. (2009). Modelling early language acquisition skills: Towards a general statistical learning mechanism. In Proceedings of EACL-2009-SRWS (pp. 1-9), Athens, Greece .
3. Altosaar, T., ten Bosch, L., Aimetti, G., Koniaris, C., Demuynck, K., & van den Heuvel, H. (2010). A speech corpus for modeling language acquisition: CAREGIVER. In Proceedings of the international conference on language resources and evaluation (LREC) (pp. 1062-1068), Malta.
4. Baldwin D., Andersson A., Saffran J., Meyer M. Segmenting dynamic human action via statistical structure. Cognition 2008, 106:1382-1407.
5. Bortfeld H., Morgan J.L. Is early word-form processing stress-full? How natural variability supports recognition. Cognitive Psychology 2010, 60:241-266.
6. Brent M.R. An efficient, probabilistically sound algorithm for segmentation and word discovery. Machine Learning 1999, 34:71-105.
7. Brent M.R., Cartwright T.A. Distributional regularity and phonotactics are useful for segmentation. Cognition 1996, 61:93-125.
8. Cairns, P., Shillcock, R., Chater, N., & Levy, J. (1994). Lexical Segmentation, the role of sequential statistics in supervised and un-supervised models. In Proceedings of the 16th annual conference of cognitive science society (pp. 36-141).
9. Ching W.K., Fung E.S., Ng M.K. High-order markov chain models for categorical data sequences. Naval Research Logistic 2004, 51:557-574.
10. Christiansen M.H., Allen J.A., Seidenberg M.S. Learning to segment speech using multiple cues: A connectionist model. Language and Cognitive Processes 1998, 13:221-268.
11. Coen, M. H. (2006). Self-supervised acquisition of vowels in American English. In Proceedings of the 21st national conference on artificial intelligence (Vol. 2, pp. 451-1456), Boston, USA.
12. Cutler A. Segmentation problems, rhythmic solutions. Lingua 1994, 92:81-104.
13. Davis S.B., Mermelstein P. Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions of Acoustics, Speech, and Signal Processing 1980, 28:357-366.
14. de Marcken, C. (1995). The unsupervised acquisition of a lexicon from continuous speech. AI Memo No. 1558. Massachusetts Institute of Technology.
15. Feldman, N. H., Griffiths, T. L., & Morgan, J. L. (2009). Learning phonetic categories by learning a lexicon. In Proceedings of the 31st annual conference of the cognitive science society (pp. 2208-2213), Amsterdam, Netherlands.
16. Fenson L., Marchman V.A., Thal D.J., Dale P.S., Bates E. MacArthur-Bates communicative development inventories (CDIs) 2003, Brooks Publishing, Baltimore, MD. 2nd ed.
17. Hillenbrand J.L., Getty L.A., Clark M.J., Wheeler K. Acoustic characteristics of American English vowels. Journal of the Acoustical Society of America 1995, 97:3099-3111.
18. Houston D.M., Jusczyk P.W. The role of talker specific information in word segmentation by infants. Journal of Experimental Psychology: Human Perception and Performance 2000, 26:1570-1582.
19. Huang, X. (1992). Minimizing speaker variation effects for speaker-independent speech recognition. In Proceedings of the workshop on speech and natural language of the human language technology conference (pp. 191-196), Harriman, New York.
20. Huang, A. (2008). Similarity measures for text document clustering. In Proceedings of the sixth New Zealand computer science research student conference NZCSRSC2008 (pp. 49-56), Christchurch, New Zealand.
21. Johnson E.K., Jusczyk P.W. Word segmentation by 8-month-olds: When speech cues count more than statistics. Journal of Memory and Language 2001, 44:548-567.
22. Jusczyk, P. W. (1993). Discovering sound patterns in the native language. In Proceedings of the 15th annual meeting of the cognitive science society (pp. 49-60), Colorado, Boulder.
23. Jusczyk P.W. How infants begin to extract words from speech. Trends in Cognitive Sciences 1999, 3:323-328.
24. Jusczyk P.W., Aslin R.N. Infants' detection of the sound patterns of words in fluent speech. Cognitive Psychology 1995, 29:1-23.
25. Kirkham N.Z., Slemmer J.A., Johnson S.P. Visual statistical learning in infancy: Evidence for a domain general learning mechanism. Cognition 2002, 83:B35-B42.
26. Kuhl P.K. Theoretical contributions of tests on animals to the special-mechanisms debate in speech. Experimental Biology 1986, 45:233-265.
27. Kuhl P.K. Early language acquisition: Cracking the speech code. Nature Reviews Neuroscience 2004, 5:831-843.
28. Kuhl P.K., Conboy B.T., Coffey-Corina S., Padden D., Rivera-Gaxiola M., Nelson T. Phonetic learning as a pathway to language: New data and native language magnet theory expanded (NLM-e). Philosophical Transaction Royal Society B 2008, 363:979-1000.
29. Lake B.M., Vallabha G.K., McClelland J.L. Modeling unsupervised perceptual category learning. IEEE Transactions on Autonomous Mental Development 2009, 1:35-43.
30. MacQueen, J. B. (1967). Some methods for classification and analysis of multivariate observations. In Proceedings of 5th berkeley symposium on mathematical statistics and probability (pp. 281-297). Berkeley: University of California Press.
31. McClelland J.L., Elman J.L. The TRACE model of speech perception. Cognitive Psychology 1986, 18:1-86.
32. McMurray B., Aslin R.N., Toscano J.C. Statistical learning of phonetic categories: Insights from a computational approach. Developmental Science 2009, 12:369-378.
33. Meltzoff A.N., Kuhl P.K., Movellan J., Sejnowski T.J. Foundations for a new science of learning. Science 2009, 325:284-288.
34. Oates, T. (2001). Grounding knowledge in sensors: Unsupervised learning for language and planning. Doctoral thesis, University of Massachusetts Amherst, USA.
35. Oates, T. (2002). PERUSE: An unsupervised algorithm for finding recurrent patterns in time-series. In Proceedings of the IEEE international conference on data mining (ICDM) (pp. 330-337), Maebashi City, Japan.
36. Oudeyer P.-Y., Kaplan F. Discovering communication. Connection Science 2006, 18:189-206.
37. Park, A., & Glass, J. R. (2005). Towards unsupervised pattern discovery in speech. In Proceedings of 2005 IEEE workshop automatic speech recognition and understanding (ASRU'05) (pp. 53-58), Cancún, Mexico.
38. Park, A., & Glass, J. R. (2006). Unsupervised word acquisition from speech using pattern discovery. In Proceedings of international conference on acoustics, speech, and signal processing (ICASSP'06) (pp. 409-412), Toulouse, France.
39. Pelucchi B., Hay J.F., Saffran J.R. Eight-month-old infants track backward transitional probabilities. Cognition 2009, 113:244-247.
40. Pisoni D.B. Some thoughts on " Normalization" in speech perception. Talker variability in speech processing 1997, 9-32. Academic Press, San Diego. K. Johnson, J.W. Mullennix (Eds.).
41. Port R. How are words stored in memory? Beyond phones and phonemes. New Ideas in Psychology 2007, 25:143-170.
42. Raftery A.E. A new model for discrete-valued time series: Autocorrelations and extensions. Rassegna di Metodi Statistici ed Applicazioni 1985, 3-4:149-162.
43. Räsänen, O. J., & Laine, U. K. (submitted for publication). A method for noise robust context-aware pattern discovery from symbolic time series.
44. Räsänen, O. J., Laine, U. K., & Altosaar, T. (2008). Computational language acquisition by statistical bottom-up processing. In Proceedings of 9th annual conference of the international speech communication association (Interspeech'09) (pp. 1980-1983), Brisbane, Australia.
45. Räsänen, O. J., Laine, U. K., & Altosaar, T. (2009a). A noise robust method for pattern discovery in quantized time series: The concept matrix approach. Proceedings of 10th annual conference of the international speech communication association (Interspeech'09), Brighton, England, 3035-3038.
46. Räsänen, O. J., Laine, U. K., & Altosaar, T. (2009b). Self-learning vector quantization for pattern discovery from speech. In Proceedings of 10th annual conference of the international speech communication association (Interspeech'09) (pp. 852-855), Brighton, England.
47. Räsänen, O. J., Laine, U. K., & Altosaar, T. (in press). Blind segmentation of speech using non-linear filtering methods. In I. Ipsic (Ed.), Speech technologies (accepted book chapter).
48. Rissanen J. Modeling by shortest data description. Automatica 1978, 14:465-471.
49. Rost G.C., McMurray B. Speaker variability augments phonological processing in early word learning. Developmental Science 2009, 12:339-349.
50. Saffran J.R. Words in the sea of sounds: The output of infant statistical learning. Cognition 2001, 81:149-169.
51. Saffran J.R., Aslin R.N., Newport E.L. Statistical learning by 8-month-old infants. Science 1996, 274:1926-1928.
52. Saffran J.R., Johnson E.K., Aslin R.N., Newport E.L. Statistical learning of tone sequences by human infants and adults. Cognition 1999, 70:27-52.
53. Saffran J.R., Newport E.L., Aslin R.N. Word segmentation: The role of distributional cues. Journal of Memory and Language 1996, 35:606-621.
54. Scharenborg, O., Ernestus, M., & Wan, V. (2007). Segmentation of speech: Child's play? In Proceedings of 8th annual conference of the international speech communication association (Interspeech'07) (pp. 1953-1956), Antwerp, Belgium.
55. Shillcock, R., Lindsey, G., Levy, J., & Chater, N. (1992). A phonologically motivated input representation for the modeling of auditory word perception in continuous speech. In Proceedings of the fourteenth annual conference of the cognitive science society (pp. 408-413), Bloomington, Indiana.
56. Singh L., White K.S., Morgan J.L. Building a word-form lexicon in the face of variable input: Influences of pitch and amplitude on early spoken word recognition. Language Learning and Development 2008, 4:157-178.
57. Smith L., Yu C. Infants rapidly learn word-referent mappings via cross-situational statistics. Cognition 2008, 106:1558-1568.
58. Stager C.L., Werker J.F. Infants listen for more phonetic detail in speech perception than in word-learning tasks. Nature 1997, 388:381-382.
59. Swingley D. Statistical clustering and the contents of the infant vocabulary. Cognitive Psychology 2005, 50:86-132.
60. Thiessen E., Saffran J.R. When cues collide: Use of stress and statistical cues to word boundaries by 7- to 9-month-old infants. Developmental Psychology 2003, 39:706-716.
61. Thiessen E., Saffran J.R. Spectral tilt as a cue to word segmentation in infancy and adulthood. Perception and Psychophysics 2004, 65:779-791.
62. Toledano D.T., Hernández Gómez L.A., Villarrubia Grande L. Automatic phonetic segmentation. IEEE Transactions on Speech and Audio Processing 2003, 11:617-625.
63. Toscano J.C., McMurray B. Cue integration with categories: Weighting acoustic cues in speech using unsupervised learning and distributional statistics. Cognitive Science 2010, 34:434-464.
64. Vallabha G.K., McLelland J.L., Pons F., Werker J.F., Amano S. Unsupervised learning of vowel categories from infant-directed speech. Proceedings of National Academy of Sciences 2007, 104:13273-13278.
65. Venkataraman A. A statistical model for word discovery in transcribed speech. Computational Linguistics 2001, 27:351-372.
66. Warren, R. M. (2000). Phonemic organization does not occur: Hence no feedback. Commentary to Norris, D., McQueen, J. M., & Cutler, A. (2000). Merging information in speech recognition: Feedback is never necessary. Behavioral and Brain Sciences, 23, 350-351.
67. Werker J.F., Curtin S. PRIMIR: A developmental framework of infant speech processing. Language Learning and Development 2005, 1:197-234.
68. Werker J.F., Tees R.C. Cross-language speech perception: Evidence from perceptual reorganization during the first year of life. Infant Behavior and Development 1984, 7:49-63.
69. White K.S., Morgan J.L. Sub-segmental detail in early lexical representations. Journal of Memory and Language 2008, 59:114-132.
70. Yang C.D. Universal grammar, statistics, or both?. TRENDS in Cognitive Sciences 2004, 8:451-456.
71. Yu C., Ballard D.H., Aslin R.N. The role of embodied intention in early lexical acquisition. Cognitive Science 2005, 29:961-1005.