The importance of word-final vowel duration for non-native portuguese speaker identification by means of Support Vector Machines

Suzanne Franks; Rommel Barbosa

Autori

Suzanne Franks University of Georgia Autor
Rommel Barbosa UFG

Parole chiave:

phonetics, acoustic phonetics, second language acquisition, Brazilian Portuguese, vowels, Support Vector Machines

Abstract

This article studies the acoustic characteristics of some Brazilian Portuguese (BP) vowels and looks at which acoustic features are important for classifying native speakers versus non-native speakers of BP. Native speakers and non-native speakers of BP were recorded for the purpose of performing acoustic analysis of vowel segments [a], [i], and [u] in syllables bearing primary stress. Acoustic parameters for segments were analyzed using the data-mining algorithm Support Vector Machines to determine to which group, native versus non-native, a speaker belonged. When all variables were considered, 91% accuracy was obtained. The two important acoustic cues for determining whether a speaker is native or non-native were duration of [i] and [u] in word-final position. These findings can contribute to better speaker identification as well as the teaching of pronunciation of Portuguese as a foreign language.

Downloads

La data di download non è ancora disponibile.

Biografia autore

Suzanne Franks, University of Georgia

Suzanne Franks is a PhD candidate in Linguistics in the Linguistics Program at the University of Georgia. Her research interests include second language acquisition, phonology, and phonetics. She has a Master of Arts in Teaching English as a Foreign Language from Southern Illinois University. She has taught at public universities in Brazil and the USA, as well as private schools and intensive English programs. Classes taught include Introduction to Linguistics, English Phonology, English as a second (and foreign) language, and Portuguese as a foreign language.

Riferimenti bibliografici

AGUIAR, G. F. M. et al. Determination of trace elements in bovine semen samples by inductively coupled plasma mass spectrometry and data mining techniques for identification of bovine class. In: Journal of Dairy Science, v. 95, n. 12 Amsterdam, December, 2012. p. 7066-7073.

BAPTISTA, B. O. Adult phonetic learning of a second language vowel system. In: BAPTISTA, B. O.; WATKINS, M. A. (Orgs.) English with a Latin beat: Studies in Portuguese/Spanish-English Interphonology. Amsterdam: John Benjamins Publishing Company, 2006. p. 19-40.

BATISTA, B. L. et al. Multi-element determination in Brazilian honey samples by inductively coupled plasma mass spectrometry and estimation of geographic origin with data mining techniques. In: Food Research International, v. 49, Amsterdam, November, 2012. p. 209-215.

BLEY-VROMAN, R. The Comparative fallacy in interlanguage studies: the case of systematicity. In: Language Learning, v. 33, n. 1, Oxford, March, 1983. p. 1-17.

BOERSMA, P.; WEENINK, D. Praat: doing phonetics by computer [Computer program]. Version 5.3.35. Available at: <http://www.praat.org/>. Retrieved November 18, 2013.

BOHN, O.; FLEGE, J. E. The production of new and similar vowels by adult German learners of English. In: Studies in Second Language Acquisition, v. 14, n. 2, Cambridge, June, 1992. p. 131-158.

BOND, Z. S.; PETROSINO, L.; DEAN, C.R. The emergence of vowels: 17 to 26 months. In: Journal of Phonetics, v. 10, n. 4, Amsterdam, October, 1982. p. 417-422.

BROSSEAU-LAPRÉ, F. et. al. Stimulus variability and perceptual learning of nonnative vowel categories. In: Applied Psycholinguistics, v. 34, n. 3, Cambridge, May, 2013. p. 419-441.

CALLOU, D.; MORAES, J. A.; LEITA, Y. As vogais orais: Um estudo acústico-variacionsita. In: ABAURRE, M. B. M. (Org.). Gramática do português culto falado no Brasil, Vol. VII: A construção fonológica da palavra. São Paulo: Contexto, 2013. p. 75-93.

CAMPBELL, W. M. et. al. Support vector machines for speaker and language recognition. In: Computer Speech and Language, v. 20, n. 4, Amsterdam, October, 2006. p. 210-229.

CORTES, C.; VAPNIC, V. Support-vector networks. In: Machine Learning, v. 20. n. 3, Berlin, September, 1995. p. 273-297.

CULTER, A.; BUTTERFIELD, S. Durational cues to word boundaries in clear speech. In: Speech Communication, v. 9, Amsterdam, December, 1990. p. 485-495.

ECKMAN, F. R. The reduction of word-final consonant clusters in interlanguage. In: JAMES, A.; LEATHER, J. (Org.), Sound patterns in second language acquisition. Dordrecht: Foris Publications, 1987. p. 143-162.

ECKMAN, F. R. The structural conformity hypothesis and the acquisition of consonant clusters in the interlanguage of ESL learners. In: Studies in Second Language Acquisition, v. 13, n. 1, Cambridge, March, 1991. p. 23-41.

ECKMAN, F. R.; MORAVCSIK, E. A.; WIRTH, J. R. Implicational universals and interrogative structures in the interlanguage of ESL learners. In: Language Learning, v. 39, n. 2, Oxford, June, 1989. p. 173-205.

FLEGE, J. E. Production of "new" and "similar" phones in a foreign language: Evidence for the effect of equivalent classification. In: Journal of Phonetics, v. 15, Amsterdam, January, 1987. p. 47-65.

FLEGE, J. E. Second language speech theory: theory, findings, and problems, In: STRANGE, W. (Org.). Speech perception and linguistic experience: issues in cross-language research. Baltimore: Timonium, York Press, 1995. p. 233-277.

FROTA, S.; VIGÁRIO, M. On the correlates of rhythm distinction: The European/Brazilian Portuguese case. In: Probus, v. 13, n. 2, Madrid, July, 2001. p. 247-275.

GAMA-ROSSI, A. The perception-production relationship in the acquisition of vowel duration in Brazilian Portuguese. In: Letras de Hoje, v. 36, n. 3, Porto Alegre, September, 2001. p. 177-186.

HALL, M. A. Correlation-based feature subset selection for machine learning (Ph.D. Dissertation). Hamilton, New Zealand: University of Waikato, 1998.

HILLENBRAND, J. et. al. Acoustic characteristics of American English vowels. In: Journal of the Acoustical Society of America, v. 97, n. 3, Melville, May, 1995. p. 3099-3111.

HIRST, D. J. Analyse_tier.praat. Aix-en-Provence: PRAAT script, 2012.

HUANG, B. H.; JUN, S. The effect of age on the acquisition of second language prosody. In: Language & Speech, v. 54, n. 3, London, September, 2011. p. 387-414.

Instituto Brasileiro de Geografia e Estatística (IBGE). 2010 population census. This government document provides the data regarding census of the Brazilian population in 2010. November 2010. Available at: <http://www.ibge.gov.br/english/estatistica/populacao/censo2010/default.shtm>. Retrieved January 25, 2014.

KOLLY, M.; DELLWO, V. Cues to linguistic origin: The contribution of speech temporal information to foreign accent recognition. In: Journal of Phonetics, v. 42, Amsterdam, January, 2014. p. 12-23.

LADEFOGED, P. A course in phonetics. 5 ed. Boston: Thomason Wadsworth, 2006.

LEWIS, M. P.; SIMONS, G. F.; FENNIG, C. D. (Org.). Portuguese. Ethnologue: Languages of the World, 7th edition. Available at: <http://www.ethnologue.com>. Retrieved November 18, 2013.

LIMA-GREGIO, A. M. et. al. Spectral findings for vowels [a] and [] at different velopharyngeal openings. In: PRO-FONO: Revista de Actualização Cientifica, v. 22, n. 4, São Paulo, December, 2010. p. 515-520.

MARKHAM, D. Phonetic imitation, accent, and the learner. Lund: Lund University Press, 1997.

MORAES, J. A.; CALLOU, D.; LEITE, Y. O Sistema vocálico no português do Brasil: Caracterização acústica. In: KATO, M. A. Gramática do português falado, vol. V. Campinas: UNICAMP/FAPESP, 1996a. p. 33-53.

MORAES, J. A.; CALLOU, D.; LEITE, Y. O vocalismo do português do Brasil. In: Letras de Hoje v. 31, n. 2, Porto Alegre, June, 1996b. p. 27-40.

MORRISON, G. S. L1-Spanish Speakers' Acquisition of the English /i//i/ contrast: Duration-based perception is not the initial developmental stage. In: Language & Speech, v. 51, n. 4, London, December, 2008. p. 285-315.

NOBRE, M. A.; INGEMANN, F. Oral vowel reduction in Brazilian Portuguese. In: CHANNON, R.; SHOCKEY, L. (Org.), In honor of Ilse Lehiste. Dordrecht: Foris Publications, 1987.

OH, E. Coarticulation in non-native speakers of English and French: An acoustic study. In: Journal of Phonetics, v. 36, n. 2, Amsterdam, April, 2008. p. 361-384.

PATKOWSKI, M. S. Age and accent in a second language: a reply to James Emil Flege. In: Applied Linguistics, v. 11, Oxford, March, 1990. p. 73-89.

PISKE, T. et. al. The production of English vowels by fluent early and late Italian-English bilinguals. In: Phonetica, v. 59, Basel, January-March, 2002. p. 49-71.

PISKE, T.; MACKAY, I.R.A.; FLEGE, J.E. Factors affecting degree of foreign accent in an L2: a review. In: Journal of Phonetics, v. 29, n. 2, Amsterdam, April, 2001. p. 191-215.

RAUBER, A. S. An acoustic description of Brazilian Portuguese oral vowels. In: Diacrítica, Ciências da Linguagem, v. 22, n. 1, Braga, January, 2008. p. 229-238.

REDENBARGER, W. J. Articulator features and Portuguese vowel height. Cambridge: Department of Romance Languages and Literatures, Harvard University Press, 1981.

RVACHEW, S. et. al. Emergence of the corner vowels in the babble produced by infants exposed to Canadian English or Canadian French. In: Journal of Phonetics, v. 36, n. 4, Amsterdam, October, 2008. p. 564-577.

SCHÖLKOPF, B.; SMOLA, A. J. Learning with kernels: support vector machines, regularization, optimization, and beyond. Cambridge: The MIT Press, 2001.

SHAIMAN, S. Kinematics of compensatory vowel shortening: the effect of speaking rate and coda composition on intra- and inter-articulatory timing. In: Journal of Phonetics, v. 29, n. 1, Amsterdam, January, 2001. p. 89-107.

SILVA, T. C. Fonética e fonologia de Português: Roteiro de estudos e guia de exercícios. São Paulo: Editora Contexto, 1998.

SIMÕES, A. R. M. Towards a phonetics of discourse. In: Cadernos de estudos linguísticos - Instituto do Estudo da Linguagem. v. 21, Campinas. July/December, 1991. p. 59-78.

SNOW, C. E.; HOEFNAGEL-HÖHLE, M. Age differences in pronunciation of foreign sounds. In: Language & Speech, v. 20, London, October-December, 1977. p. 357-365.

TAN, P.; STEINBACH, M.; KUMAR, V. Introduction to data mining. Boston: Addison-Wesley: Pearson PLC, 2006.

TROVIMOVICH, P.; BAKER, W. Learning second language suprasegmentals: Effect of L2 experience on prosody and fluency characteristics of L2 speech. In: Studies in Second Language Acquisition, v. 28, Cambridge, March, 2006. p. 1-30.

WHITE, L.; MATTYS, S. L. Calibrating rhythm: First language and second language studies. In: Journal of Phonetics, v. 35, n. 4, Amsterdam, October, 2007a. p. 501-522.

WHITE, L.; MATTYS, S. L. Rhythm typology and variation in first and second languages. In: PRIETO, P.; MASCARÓ, J.; SOLÉ, M. (Org.). Current Issues in Linguistic Theory: Segmental and prosodic issues in Romance phonology. Amsterdam: John Benjamins Company, 2007b. p. 237-257.

WHITLAM, J. Modern Brazilian Portuguese grammar: a practical guide. New York: Routledge: Taylor & Francis Group, 2011.

WITTEN, I. H.; FRANK, E.; HALL, M. A. Data mining: practical machine learning tools and techniques. 3rd edition. Burlington: Elsevier-Morgan Kaufmann Publishers, 2011.