Keywords
K-nearest neighbor
Centroid minimum distance
Artificial neural networks
Language learning
How to Cite
Abstract
Transfer phenomena between Portuguese (L1) and English (L2) produced by Brazilian learners are well documented in the literature. However, the identification and classification of these processes are made mainly through transcriptions, a slow and laborious process done by specialized linguists. The rapid identification of these phenomena would be of great value for software doing proficiency placement tests and could be used in language schools, distance education, computer-assisted pronunciation training (CAPT) or by autodidacts and researchers. The present work analyzed possible techniques and tools that can be used in the automatic identification of some transfer processes. The data for the grapho-phonic-phonological transfer were synthetically generated in the Google Translate™ TTS system. Then we tested three classification algorithms to perform the identification: k-Nearest Neighbor, Centroid Minimum Distance, and Artificial Neural Networks. The results indicate that these techniques are of great value for Linguistics and for new software applications in language learning.
References
Rocha ARS. Os efeitos da instrução explícita em fonologia na produção e percepção de consoantes da língua inglesa. [Dissertation - Masters]. Fortaleza, Brazil: Programa de Pós-Graduação em Linguística Aplicada, Universidade Estadual do Ceará; 2012. [accessed 25 Mar 2018] Available from: http://www.uece.br/posla/dmdocuments/AratuzaRodriguesSilvaRocha.pdf
Zimmer MC, Alves UK. A produção de aspectos fonético-fonológicos da segunda língua: instrução explícita e conexionismo. Rev Ling Ensino. 2006;9(2):101–43. [accessed 25 Mar 2018] Available from: http://www.rle.ucpel.tche.br/index.php/rle/article/view/168
Hayes-Harb R, Nicol J, Barker J. Learning the phonological forms of new words: effects of orthographic and auditory input. Lang Speech. 2010;53(Pt 3):367–81. doi: 10.1177/0023830910371460
Bassetti B, Escudero P, Hayes-Harb R. Second language phonology at the interface between acoustic and orthographic input. Appl Psycholinguist. 2015 Jan;36(1):1–6. [accessed 24 Oct 2021] Available from: https://www.cambridge.org/core/journals/applied-psycholinguistics/article/second-language-phonology-at-the-interface-between-acoustic-and-orthographic-input/349B5CD70A06209C334EB78454305D25
Gonçalves AR, Silveira R. Orthographic effects in speech production: A psycholinguistic study with adult Brazilian-Portuguese English bilinguals / Efeitos ortográficos na produção da fala: um estudo psicolinguístico com adultos bilíngues falantes de Português Brasileiro e Inglês. Rev Estud Ling. 2020 May 27;28(3):1461–94. [accessed 24 Oct 2021] Available from: http://www.periodicos.letras.ufmg.br/index.php/relin/article/view/16454
Silveira R. PL2 production of english word-final consonants: the role of orthography and learner profile variables. Trab Em Linguística Apl. 2012 Jun;51:13–34. [accessed 24 Oct 2021] Available from: http://www.scielo.br/j/tla/a/xRmprsgPSBS8v6Wfw36tpTJ/?lang=en
Erdener VD, Burnham DK. The Role of Audiovisual Speech and Orthographic Information in Nonnative Speech Production. Lang Learn. 2005;55(2):191–228. [accessed 27 Oct 2021] Available from: https://onlinelibrary.wiley.com/doi/abs/10.1111/j.0023-8333.2005.00303.x
Flege JE, Bohn O-S, Jang S. Effects of experience on non-native speakers’ production and perception of English vowels. J Phon. 1997 Oct 1;25(4):437–70. [accessed 24 Mar 2018] Available from: http://www.sciencedirect.com/science/article/pii/S0095447097900528
Flege JE, Liu S. THE EFFECT OF EXPERIENCE ON ADULTS’ ACQUISITION OF A SECOND LANGUAGE. Stud Second Lang Acquis. 2001 Dec;23(4):527–52. [accessed 24 Mar 2018] Available from: https://www.cambridge.org/core/journals/studies-in-second-language-acquisition/article/the-effect-of-experience-on-adults-acquisition-of-a-second-language/4671D40F6250DB3E2F1FCF9B90190ED5
Bassetti B, Atkinson N. Effects of orthographic forms on pronunciation in experienced instructed second language learners. Appl Psycholinguist. 2015 Jan;36(1):67–91. [accessed 27 Oct 2021] Available from: https://www.cambridge.org/core/journals/applied-psycholinguistics/article/abs/effects-of-orthographic-forms-on-pronunciation-in-experienced-instructed-second-language-learners/335A18457216E019DF582B372319FA05
Silveira R, Gonçalves AR. Efeito da ortografia. In: Kupske F, Alves UK, Lima Jr. RM, editors. Investigando os sons de línguas não nativas: uma introdução. Editora da Abralin; 2021. [accessed 28 Oct 2021] Available from: https://www.doi.org/10.25189/9788568990117
Silva ACC, Macedo ACP, Barreto GA. A SOM-Based Analysis of Early Prosodic Acquisition of English by Brazilian Learners: Preliminary Results. In: Laaksonen J, Honkela T, editors. Advances in Self-Organizing Maps. Berlin, Heidelberg: Springer; 2011. p. 267–76. (Lecture Notes in Computer Science). doi: 10.1007/978-3-642-21566-7_27
Rocha ARS. Identificação de processos de transferência do português do brasil para o inglês (L2) por meio de rede neural artificial MLP [PhD]. Fortaleza, Brazil: Programa de Pós-Graduação em Linguística Aplicada, Universidade Estadual do Ceará; 2017. [accessed 25 Mar 2018] Available from: http://www.uece.br/posla/dmdocuments/Aratuza%20R.%20Silva.pdf
Zimmer MC, Bittencourt HR. Produção e percepção oral em L2: os processos de transferência do conhecimento grafo fônico-fonológico do português brasileiro (L1) para o inglês (L2) e o desempenho em listening (L2). Cad Estud Lingüíst. 2008;50(1). [accessed 25 Mar 2018] Available from: https://periodicos.sbu.unicamp.br/ojs/index.php/cel/article/view/8637237
Zimmer MC. A transferência do conhecimento fonético-fonológico do português brasileiro (L1) para o inglês (L2) na recodificação leitora: uma abordagem conexionista [PhD]. Porto Alegre, Brazil: Faculdade de Letras, Pontifícia Universidade Católica do Rio Grande do Sul; 2003. [accessed 25 Mar 2018] Available from: http://www.leffa.pro.br/tela4/Textos/Textos/Teses/marcia_zimmer.pdf
Zen H, Tokuda K, Black AW. Statistical parametric speech synthesis. Speech Commun. 2009 Nov 1;51(11):1039–64. [accessed 25 Mar 2018] Available from: http://www.sciencedirect.com/science/article/pii/S0167639309000648
Zen H. Acoustic Modeling in Statistical Parametric Speech Synthesis - From HMM to LSTM-RNN. In Fukushima, Japan; 2015. [accessed 25 Mar 2018] Available from: https://research.google.com/pubs/pub43893.html
Tokuday K, Zen H. Directly modeling voiced and unvoiced components in speech waveforms by neural networks. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2016. p. 5640–4. doi: 10.1109/ICASSP.2016.7472757
Tokuday K, Zen H. Directly modeling speech waveforms by neural networks for statistical parametric speech synthesis. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2015. p. 4215–9. doi: 10.1109/ICASSP.2015.7178765
Ze H, Senior A, Schuster M. Statistical parametric speech synthesis using deep neural networks. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. 2013. p. 7962–6. doi: 10.1109/ICASSP.2013.6639215
Zen H, Agiomyrgiannakis Y, Egberts N, Henderson F, Szczepaniak P. Fast, Compact, and High Quality LSTM-RNN Based Statistical Parametric Speech Synthesizers for Mobile Devices. In: arXiv:160606061 [cs]. San Francisco, CA, USA; 2016. [accessed 25 Mar 2018] Available from: http://arxiv.org/abs/1606.06061
Zen H. Generative Model-Based Text-to-Speech Synthesis. 2017. [accessed 25 Mar 2018] Available from: https://research.google.com/pubs/pub45882.html
Elman JL. Learning and development in neural networks: the importance of starting small. Cognition. 1993 Jul 1;48(1):71–99. [accessed 24 Mar 2018] Available from: http://www.sciencedirect.com/science/article/pii/0010027793900584
Li P, Farkas I, MacWhinney B. Early lexical development in a self-organizing neural network. Neural Netw. 2004 Oct 1;17(8):1345–62. [accessed 26 Mar 2018] Available from: http://www.sciencedirect.com/science/article/pii/S0893608004001534
MacDonald M, Christiansen M. Reassessing working memory: A reply to Just & Carpenter and Waters & Caplan. Psychol Rev. 2002 Feb 1;109:35–54; discussion 55. doi: 10.1037//0033-295X.109.1.35
Gonzalvo X, Podsiadlo M. Text-To-Speech with cross-lingual Neural Network-based grapheme-to-phoneme models. In 2014. [accessed 25 Mar 2018] Available from: https://research.google.com/pubs/pub45183.html
Li B, Zen H. Multi-Language Multi-Speaker Acoustic Modeling for LSTM-RNN Based Statistical Parametric Speech Synthesis. In 2016. p. 2468–72. doi: 10.21437/Interspeech.2016-172
Fujinaga K, Nakai M, Shimodaira H, Sagayama S. Multiple-regression hidden Markov model. In: 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing Proceedings (Cat No01CH37221). 2001. p. 513–6 vol.1. doi: 10.1109/ICASSP.2001.940880
Chen K, Yang C. The Effect of Fundamental Frequency on Mandarin Intelligibility by L2 Learners in Quiet and Noise Environments: A Pilot Study. In: Yang C, editor. The Acquisition of Chinese as a Second Language Pronunciation: Segments and Prosody. Singapore: Springer; 2021. p. 213–32. (Prosody, Phonology and Phonetics). [accessed 26 Jun 2021] Available from: https://doi.org/10.1007/978-981-15-3809-4_10
Boersma P. Accurate short-term analysis of the fundamental frequency and the harmonics-to-noise ratio of a sampled sound. In: IFA Proceedings 17. 1993. p. 97–110.
Fix E, Hodges JL. Discriminatory Analysis. Nonparametric Discrimination: Consistency Properties. Int Stat Rev Rev Int Stat. 1989;57(3):238–47. [accessed 29 Mar 2018] Available from: http://www.jstor.org/stable/1403797
Morariu N. Using Pattern Classification and Recognition Techniques for Diagnostic and Prediction. Adv Electr Comput Eng. 2007 Apr 2;7(1):63–7. [accessed 25 Mar 2018] Available from: http://dx.doi.org/10.4316/AECE.2007.01014
Aha DW. Tolerating noisy, irrelevant and novel attributes in instance-based learning algorithms. Int J Man-Mach Stud. 1992 Feb 1;36(2):267–87. [accessed 29 Mar 2018] Available from: http://www.sciencedirect.com/science/article/pii/002073739290018G
Petrushin V. Emotion recognition in speech signal: Experimental study, development, and application. In: Proc ICSLP. 2000. p. 222–5.
Velican V. Automatic Recognition of Improperly Pronounced Initial ‘r’ Consonant in Romanian. Adv Electr Comput Eng. 2012 Aug 31;12(3):79–84. [accessed 29 Mar 2018] Available from: http://dx.doi.org/10.4316/AECE.2012.03012
Yan Z, Xu C. Combining KNN algorithm and other classifiers. In: 2010 9th IEEE International Conference on Cognitive Informatics (ICCI). 2010. p. 800–5. doi: 10.1109/COGINF.2010.5599804
Scaranti A, Bernardi R. Identificação de Órgãos Foliares utilizando as Wavelets de Daubechies. In Presidente Prudente, Brazil; 2010. [accessed 29 Mar 2018] Available from: http://iris.sel.eesc.usp.br/wvc/anais_WVC2010/artigos/poster/72803.pdf
Frutuoso RL, Santos JRVD, Siqueira R da S, Oliveira AC de. Uso de algoritmos de reconhecimento de padrões aplicados ao problema de câncer de pele do tipo melanoma. In SBIC; 2016. p. 1–6. [accessed 29 Mar 2018] Available from: http://abricom.org.br/eventos/cbic_2013/bricsccicbic2013_submission_321
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) 2021 Atos Borges, Washington Rodrigues, Aratuza Rocha, Wilson Carvalho, Ronaldo Lima, Fábio Rocha
