Implementasi Sistem Rumah Pintar Berbasis Pengenalan Suara Menggunakan Keyword Spotting dan Convolutional Neural Network
Abstrak
Penelitian ini mengembangkan sistem rumah pintar menggunakan Raspberry Pi dengan pengenalan suara berbasis Keyword Spotting (KWS) dan Convolutional Neural Network (CNN). Sistem ini dirancang untuk mengenali perintah suara sederhana seperti "nyalakan lampu" atau "buka pintu" dalam lingkungan yang tenang maupun bising. Data audio diproses menggunakan Mel-Frequency Cepstral Coefficients (MFCC) untuk mengekstrak fitur yang digunakan dalam pelatihan model CNN. Hasil pengujian menunjukkan bahwa sistem mencapai akurasi rata-rata 85,07% dalam kondisi ideal dan 74,74% dalam kondisi bising. Penelitian ini memberikan wawasan untuk pengembangan sistem rumah pintar berbasis suara.
Referensi
Afaq, N., Saleem, M., Khan, J. T., & Abbasi, I. H. (2021). Convolutional Neural Networks for Deep Spoken Keyword Spotting. IEEE Transactions on Audio, Speech, and Language Processing, 29, 1009-1018.
Amodei, D., Ananthanarayanan, S., Anubhai, R., et al. (2016). Deep speech 2: End-to-end speech recognition in English and Mandarin. Proceedings of the International Conference on Machine Learning (ICML).
Balam, J., Huang, J., Lavrukhin, V., Deng, S., Majumdar, S., & Ginsburg, B. (2020). Improving Noise Robustness of an End-to-End Neural Model for Automatic Speech Recognition. arXiv preprint arXiv:2010.12715.
Eickhoff, P., Möller, M., Pekarek Rosin, T., Twiefel, J., & Wermter, S. (2023). Bring the Noise: Introducing Noise Robustness to Pretrained Automatic Speech Recognition. arXiv preprint arXiv:2309.02145.
Hewitt, M., Cunningham, H., 2022. Taxonomic Classification of IoT Smart Home Voice Control. arXiv preprint arXiv:2210.15656.
Purwar, P., Singh, S., 2017. Smart Home Automation System based on IoT through Speech. International Journal of Computer Applications, 172(6), 1–5.
Sagar, S., Choudary, U., Diwivedi, R., 2020. Smart Home Automation Using IoT and Raspberry Pi. Journal of IoT Applications, 7(3), 233–241.
Sainath, T.N., Parada, C., 2015. Convolutional neural networks for small-footprint keyword spotting. In Sixteenth Annual Conference of the International Speech Communication Association.
Sørensen, P.M., Epp, B., May, T., 2020. A Depthwise Separable Convolutional Neural Network for Keyword Spotting on an Embedded System. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 1879–1890.
Warden, P., 2018. Speech commands: A dataset for limited-vocabulary speech recognition. arXiv preprint arXiv:1804.03209.
Xu, M., Zhang, X.-L., 2020. Depthwise Separable Convolutional ResNet with Squeeze-and-Excitation Blocks for Small-Footprint Keyword Spotting. arXiv preprint arXiv:2004.12200.
Afaq, N., Saleem, M., Khan, J. T., & Abbasi, I. H. (2021). Convolutional Neural Networks for Deep Spoken Keyword Spotting. IEEE Transactions on Audio, Speech, and Language Processing, 29, 1009-1018.
Amodei, D., Ananthanarayanan, S., Anubhai, R., et al. (2016). Deep speech 2: End-to-end speech recognition in English and Mandarin. Proceedings of the International Conference on Machine Learning (ICML).
Balam, J., Huang, J., Lavrukhin, V., Deng, S., Majumdar, S., & Ginsburg, B. (2020). Improving Noise Robustness of an End-to-End Neural Model for Automatic Speech Recognition. arXiv preprint arXiv:2010.12715.
Eickhoff, P., Möller, M., Pekarek Rosin, T., Twiefel, J., & Wermter, S. (2023). Bring the Noise: Introducing Noise Robustness to Pretrained Automatic Speech Recognition. arXiv preprint arXiv:2309.02145.
Hewitt, M., Cunningham, H., 2022. Taxonomic Classification of IoT Smart Home Voice Control. arXiv preprint arXiv:2210.15656.
Purwar, P., Singh, S., 2017. Smart Home Automation System based on IoT through Speech. International Journal of Computer Applications, 172(6), 1–5.
Sagar, S., Choudary, U., Diwivedi, R., 2020. Smart Home Automation Using IoT and Raspberry Pi. Journal of IoT Applications, 7(3), 233–241.
Sainath, T.N., Parada, C., 2015. Convolutional neural networks for small-footprint keyword spotting. In Sixteenth Annual Conference of the International Speech Communication Association.
Sørensen, P.M., Epp, B., May, T., 2020. A Depthwise Separable Convolutional Neural Network for Keyword Spotting on an Embedded System. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 1879–1890.
Warden, P., 2018. Speech commands: A dataset for limited-vocabulary speech recognition. arXiv preprint arXiv:1804.03209.
Xu, M., Zhang, X.-L., 2020. Depthwise Separable Convolutional ResNet with Squeeze-and-Excitation Blocks for Small-Footprint Keyword Spotting. arXiv preprint arXiv:2004.12200.
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2025 Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Artikel ini berlisensiCreative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
