AutoIPA: development of an online platform to facilitate the use of automated phonetic transcription using Artificial Intelligence
Resumo
A transcrição fonética é uma ferramenta útil para descrever a variedade inerente à linguagem. Contudo, essa técnica ainda é pouco acessível para o público geral. A partir desse paradigma, desenvolveu-se o AutoIPA (autoipa.org): uma plataforma web baseada em IA para facilitar o acesso e a utilização da transcrição fonética para o Alfabeto Fonético Internacional (IPA). Nessa toada, foram estudados e avaliados diferentes modelos pré-existentes para viabilizar o desenvolvimento de uma aplicação que automatiza a transcrição fonética. Preliminarmente, notou-se a escassez de bases de dados rotuladas, o que restringe a performance dos modelos existentes. Ademais, observou-se que as ferramentas ainda são pouco acessíveis.
Referências
Alefiury (2024). wav2vec2-large-xlsr-53-gender-recognition-librispeech. Acesso em: maio 2025. Disponível em: [link].
Atkielski, A. (2005). Phonetic transcription can be a useful tool for teaching or correcting pronunciation in the esl/efl classroom. Using Phonetic Transcription in Class. p. 1–12.
Baevski, A., Zhou, H., Mohamed, A., and Auli, M. (2020). wav2vec 2.0: A framework for self-supervised learning of speech representations. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE. p. 1–5.
Bates, S., Watson, J., Heselwood, B., and Howard, S. (2024). Phonetic transcription in clinical practice. In Ball, M. J., Müller, N., and Spencer, E., editors, The Handbook of Clinical Linguistics. John Wiley & Sons. p. 471–489.
Battisti, E. (2014). Palatalização de t e d. In Bisol, L. and Battisti, E., editors, O português falado no Rio Grande do Sul. EDIPUCRS, Porto Alegre. p. 105–120.
Bhaskararao, P. (2004). Phonetic documentation of endangered languages: Creating a knowledge- base containing sound recording, transcription and analysis. Acoustical Science and Technology, 25(4). p. 219-226.
Bisol, L. (2005). Introdução a estudos de fonologia do português brasileiro. EDIPUCRS.
Bookbot (2022). Ljspeech phonemes dataset. [link]. Acesso em: maio de 2025.
Ethnologue (2025). Ethnologue: Languages of the world. Disponível em: [link]. Acesso em: abril de 2025.
Facebook (2025a). facebook/wav2vec2-lv-60-espeak-cv-ft: A fine-tuned model for speech recognition on commonvoice. Disponível em: [link]. Acesso em: abril de 2025.
Facebook (2025b). facebook/wav2vec2-xlsr-53-espeak-cv-ft: A fine-tuned model for speech recognition on commonvoice. Disponível em: [link]. Acesso em: abril de 2025.
International Phonetic Association (2020). The international phonetic alphabet (revised to 2020). [link]. Official IPA chart rendered in the TeX TIPA Roman font.
K, T. D., James, J., Gopinath, D. P., and K, M. A. (2024). Advocating character error rate for multilingual asr evaluation. Acesso em: maio de 2025.
Li, X., Dalmia, S., Li, J., Littell, P., Lee, M., Yao, J., Anastasopoulos, A., Mortensen, D., Neubig, G., Black, A., and Metze, F. (2020). Universal phone recognition with a multilingual allophone system. In 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona.
O’Grady, W. (2005). Contemporary Linguistics: An Introduction. Bedford/St. Martin’s, 5th edition. p. 15.
Peterson, D. J. (2015). The Art of Language Invention: From Horse-Lords to Dark Elves to Sand Worms, the Words Behind World-Building. p. 18–23.
Pratap, V., Tjandra, A., Shi, B., Tomasello, P., Babu, A., Kundu, S., Elkahky, A., Ni, Z., Vyas, A., Fazel-Zarandi, M., et al. (2024). Scaling speech technology to 1,000+ languages. Journal of Machine Learning Research, 25(97):1–52.
Ravanelli, M., Parcollet, T., Plantinga, P., Rouhe, A., Cornell, S., Lugosch, L., Subakan, C., Dawalatabad, N., Heba, A., Zhong, J., Chou, J.-C., Yeh, S.-L., Fu, S.-W., Liao, C.-F., Rastorgueva, E., Grondin, F., Aris, W., Na, H., Gao, Y., Mori, R. D., and Bengio, Y. (2021). Speechbrain: A general-purpose speech toolkit. Acesso em: maio 2025. Disponível em: [link].
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Łukasz Kaiser, and Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems, volume 30. p. 5998–6008.
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Ma, C., Jernite, Y., Plu, J., Xu, C., Scao, T. L., Gugger, S., Drame, M., Lhoest, Q., and Rush, A. M. (2020). Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages p. 38–45, Online. Association for Computational Linguistics.
Atkielski, A. (2005). Phonetic transcription can be a useful tool for teaching or correcting pronunciation in the esl/efl classroom. Using Phonetic Transcription in Class. p. 1–12.
Baevski, A., Zhou, H., Mohamed, A., and Auli, M. (2020). wav2vec 2.0: A framework for self-supervised learning of speech representations. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE. p. 1–5.
Bates, S., Watson, J., Heselwood, B., and Howard, S. (2024). Phonetic transcription in clinical practice. In Ball, M. J., Müller, N., and Spencer, E., editors, The Handbook of Clinical Linguistics. John Wiley & Sons. p. 471–489.
Battisti, E. (2014). Palatalização de t e d. In Bisol, L. and Battisti, E., editors, O português falado no Rio Grande do Sul. EDIPUCRS, Porto Alegre. p. 105–120.
Bhaskararao, P. (2004). Phonetic documentation of endangered languages: Creating a knowledge- base containing sound recording, transcription and analysis. Acoustical Science and Technology, 25(4). p. 219-226.
Bisol, L. (2005). Introdução a estudos de fonologia do português brasileiro. EDIPUCRS.
Bookbot (2022). Ljspeech phonemes dataset. [link]. Acesso em: maio de 2025.
Ethnologue (2025). Ethnologue: Languages of the world. Disponível em: [link]. Acesso em: abril de 2025.
Facebook (2025a). facebook/wav2vec2-lv-60-espeak-cv-ft: A fine-tuned model for speech recognition on commonvoice. Disponível em: [link]. Acesso em: abril de 2025.
Facebook (2025b). facebook/wav2vec2-xlsr-53-espeak-cv-ft: A fine-tuned model for speech recognition on commonvoice. Disponível em: [link]. Acesso em: abril de 2025.
International Phonetic Association (2020). The international phonetic alphabet (revised to 2020). [link]. Official IPA chart rendered in the TeX TIPA Roman font.
K, T. D., James, J., Gopinath, D. P., and K, M. A. (2024). Advocating character error rate for multilingual asr evaluation. Acesso em: maio de 2025.
Li, X., Dalmia, S., Li, J., Littell, P., Lee, M., Yao, J., Anastasopoulos, A., Mortensen, D., Neubig, G., Black, A., and Metze, F. (2020). Universal phone recognition with a multilingual allophone system. In 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona.
O’Grady, W. (2005). Contemporary Linguistics: An Introduction. Bedford/St. Martin’s, 5th edition. p. 15.
Peterson, D. J. (2015). The Art of Language Invention: From Horse-Lords to Dark Elves to Sand Worms, the Words Behind World-Building. p. 18–23.
Pratap, V., Tjandra, A., Shi, B., Tomasello, P., Babu, A., Kundu, S., Elkahky, A., Ni, Z., Vyas, A., Fazel-Zarandi, M., et al. (2024). Scaling speech technology to 1,000+ languages. Journal of Machine Learning Research, 25(97):1–52.
Ravanelli, M., Parcollet, T., Plantinga, P., Rouhe, A., Cornell, S., Lugosch, L., Subakan, C., Dawalatabad, N., Heba, A., Zhong, J., Chou, J.-C., Yeh, S.-L., Fu, S.-W., Liao, C.-F., Rastorgueva, E., Grondin, F., Aris, W., Na, H., Gao, Y., Mori, R. D., and Bengio, Y. (2021). Speechbrain: A general-purpose speech toolkit. Acesso em: maio 2025. Disponível em: [link].
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Łukasz Kaiser, and Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems, volume 30. p. 5998–6008.
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Ma, C., Jernite, Y., Plu, J., Xu, C., Scao, T. L., Gugger, S., Drame, M., Lhoest, Q., and Rush, A. M. (2020). Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages p. 38–45, Online. Association for Computational Linguistics.
Publicado
29/09/2025
Como Citar
BRIZZI, Guilherme; TOLEDO, Ana Lilian Alfonso; MINUZZI, Felipe Crivellaro.
AutoIPA: development of an online platform to facilitate the use of automated phonetic transcription using Artificial Intelligence. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 22. , 2025, Fortaleza/CE.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 1388-1397.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2025.11801.
