‘Huh?’ pada Mesin: Strategi Perbaikan Dialog (Repair) di Voice Assistant Lintas Bahasa
DOI:
https://doi.org/10.71094/jmsh.v1i6.265Keywords:
asisten suara, perbaikan dialog, lintas bahasa, kebingungan pengguna, interaksi percakapanAbstract
Penelitian ini mengeksplorasi penggunaan strategi perbaikan dialog (repair strategies) pada asisten suara lintas bahasa, dengan fokus pada interaksi pengguna yang mengekspresikan kebingungannya melalui respons "Huh?". Sebagai alat komunikasi berbasis suara, asisten suara sering menghadapi tantangan dalam memahami perintah atau pertanyaan pengguna, terutama ketika respons yang diberikan tidak sesuai dengan harapan pengguna. Penelitian ini bertujuan untuk mengidentifikasi dan menganalisis bagaimana asisten suara menerapkan strategi perbaikan untuk menangani kesalahan pemahaman lintas bahasa, dengan memperhatikan aspek lingual dan budaya yang berbeda. Melalui analisis percakapan yang dikumpulkan dari berbagai platform asisten suara di berbagai bahasa, ditemukan bahwa perbaikan dilakukan dengan beberapa pendekatan, seperti klarifikasi, pengulangan, dan konfirmasi. Temuan menunjukkan bahwa strategi perbaikan yang efektif sangat bergantung pada kemampuan asisten suara untuk mengenali konteks dan nuansa dalam percakapan, serta kepekaan terhadap perbedaan bahasa dan budaya. Penelitian ini juga memberikan rekomendasi bagi pengembangan asisten suara yang lebih responsif terhadap kebutuhan pengguna lintas bahasa, dengan menekankan pentingnya perbaikan dialog yang adaptif dan kontekstual.
References
Baughan, A., et al. (2023). A mixed-methods approach to understanding user trust after voice assistant failures. Proceedings of the CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3544548.3581152
Braun, V., & Clarke, V. (2006). Using thematic analysis in psychology. Qualitative Research in Psychology, 3(2), 77-101. https://doi.org/10.1191/1478088706qp063oa
Dingemanse, M., & Enfield, N. J. (2015). Other-initiated repair across languages: Towards a typology of conversational structures. Open Linguistics, 1, 98–118. https://doi.org/10.2478/opli-2014-0007
Dingemanse, M., Torreira, F., & Enfield, N. J. (2013). Is “Huh?” a universal word? Conversational infrastructure and the convergent evolution of linguistic items. PLOS ONE, 8(11), e78273. https://doi.org/10.1371/journal.pone.0078273
Galbraith, M. (2024). An analysis of dialogue repair in virtual assistants. Frontiers in Robotics and AI, 11, 1356847. https://doi.org/10.3389/frobt.2024.1356847
Hare, L., Smith, J., & Zhao, M. (2023). Cultural considerations in voice assistant interaction: Implications for dialogue repair strategies. International Journal of Human-Computer Studies, 144, 101210. https://doi.org/10.1016/j.ijhcs.2020.101210
Koenecke, A., et al. (2020). Racial disparities in automated speech recognition. Proceedings of the National Academy of Sciences, 117(14), 7684–7689. https://doi.org/10.1073/pnas.1915768117
Liu, A., Banchs, R. E., & Li, H. (2014). Detecting inappropriate clarification requests in spoken dialogue systems. Proceedings of the 18th Workshop on the Semantics and Pragmatics of Dialogue (SemDial). https://aclanthology.org/W14-4331
Masina, F., et al. (2020). Investigating the accessibility of voice assistants with cognitive and linguistic profiling. Sensors, 20(18), 1–18. https://doi.org/10.3390/s20185154
Maxwell, J. A. (2013). Qualitative research design: An interactive approach (3rd ed.). SAGE Publications.
Pajo, K., et al. (2023). Comparing timing of other-initiation of repair: A multimodal cross-linguistic study. Frontiers in Communication. https://doi.org/10.3389/fcomm.2023.1173179
Porcheron, M., Fischer, J. E., Reeves, S., & Sharples, S. (2018). Voice interfaces in everyday life. Proceedings of the CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3173574.3174214
Radford, A., Kim, J. W., Xu, T., Brockman, G., McLeavey, C., & Sutskever, I. (2022). Robust speech recognition via large-scale weak supervision (Whisper). arXiv preprint arXiv:2212.04356. https://arxiv.org/abs/2212.04356 arXiv
Sacks, H., Schegloff, E. A., & Jefferson, G. (1974). A simplest systematics for the organization of turn-taking for conversation. Language, 50(4), 696-735.
Sacks, H., Schegloff, E. A., & Jefferson, G. (1974). A simplest systematics for the organization of turn-taking for conversation. Language, 50(4), 696-735.
Schegloff, E. A., Jefferson, G., & Sacks, H. (1977). The preference for self-correction in the organization of repair in conversation. Language, 53(2), 361-382.
Seamless Communication Team. (2023). SeamlessM4T—Massively multilingual & multimodal machine translation. Meta AI Research Publication. https://ai.meta.com/research/seamless-communication/ Meta AI
Stoyanchev, S., Liu, A., & Hirschberg, J. (2014). Towards natural clarification questions in dialogue systems. AISB 2014 Proceedings. https://www.cs.columbia.edu/nlp/papers/2014/AISB2014_StoyanchevLiuHirschberg_final.pdf
Wenzel, K., & Kaufman, G. (2024). Designing for harm reduction: Communication repair for multicultural users' voice interactions. arXiv. https://arxiv.org/abs/2403.00265
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Randi Perkasa, Yudha Putra Indarto, Kalmiatin Musyawari (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
