Penerapan Gerbang Spektrum untuk Mengurangi Noise pada Sistem Penghitung Pembicara
Kata Kunci:
gerbang spektrum, noise, reduksi noise, penghitung pembicaraAbstrak
Penghitung pembicara (speaker counting) merupakan teknologi atau metodologi yang digunakan dalam mengidentifikasi dan menghitung jumlah pembicara dalam suatu berkas audio atau rekaman. Akan tetapi, dalam berkas audio atau rekaman terdapat noise yang dapat menganggu hasil penghitungan pembicara. Dengan adanya reduksi noise, kualitas berkas audio dapat meningkat karena noise pada audio berkurang dan dapat lebih jelas didengar. Penelitian ini bertujuan untuk memastikan bahwa gerbang spektrum dapat mereduksi noise pada berkas audio serta meningkatkan akurasi dan penghitungan jumlah pembicara. Dalam hal ini, menggunakan aplikasi komputer yang telah dibuat untuk mereduksi noise pada berkas audio dan menghitung jumlah pembicara dari berkas audio yang sudah tereduksi. Hasil dari pengujian menunjukkan kegagalan penerapan gerbang spektrum untuk mengurangi noise pada sistem penghitung pembicara. Gerbang spektrum mampu untuk mereduksi noise pada berkas audio, tetapi menyebabkan sumber suara pembicara ikut tereduksi. Peranan gerbang spektrum juga tidak mampu membantu meningkatkan hasil penghitungan jumlah pembicara yang bagus atau akurat. Tingkat akurasi dari penghitungan jumlah pembicara adalah 35%.
Referensi
Butarbutar, M., Sachio, K., Nugroho, M., David, D. dan Ari Saputra, P., 2023. Adaptive Wiener filtering method for noise reduction in speech recognition system.
Cornell, S., Omologo, M., Squartini, S. dan Vincent, E., 2022. Overlapped speech detection and speaker counting using distant microphone arrays. Computer Speech & Language, 72, p.101306
Kanda, N., Gaur, Y., Wang, X., Meng, Z., Chen, Z., Zhou, T., dan Yoshioka, T., 2020. Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakers. Audio and Speech Processing. arXiv:2006.10930.
Kumar, M.A. dan Chari, K.M., 2019. Noise reduction using modified wiener filter in digital hearing aid for Speech Signal Enhancement. Journal of Intelligent Systems, 29(1), pp.1360–1378.
Laxmi, V. 2014. Audio Noise Reduction from Audio Signals and Speech Signals. International Journal of Computer Science Trends and Technology (IJCST).
Naik, S.S., Bhatikar, G dan Ugam Gaude, 2021. Analysis of Best Algorithm for Noise Reduction in Podcasting. International Journal of Scientific Research in Science and Technology, pp.246-250
Narangale, S. dan Shinde, G., 2017. Supervised Learning for Predictive Audio Noise Filter using Look-Back Method. The 2017 IAENG Internatinal Conference on Computer Science.
Park, T.J., Kanda, N., Dimitriadis, D., Han, K.J., Watanabe, S. dan Narayanan, S., 2022. A review of speaker diarization: Recent advances with deep learning. Computer Speech & Language, 72, p.101317.
Prasadh, S.K., Natrajan, S.S. dan Kalaivani, S., 2017. Efficiency analysis of noise reduction algorithms: Analysis of the best algorithm of noise reduction from a set of algorithms. 2017 International Conference on Inventive Computing and Informatics (ICICI).
Shah, D. dan Shah, B., 2023. Comparison of spectral subtraction noise reduction algorithms. Journal of Emerging Investigators.
Singla, M. dan Singh, Harpal., 2015. Paper on Frequency based Audio Noise Reduction using Butter Worth, Chebyshev, & Elliptical Filters. International Journal on Recent and Innovation Trends in Computing and Communication.
Sudheer Kumar, E., Jai Surya, K., Yaswanth Varma, K., Akash, A., dan Nithish Reddy, K., 2023. Noise reduction in audio file using spectral gatting and FFT by Python modules. Advances in Transdisciplinary Engineering.
Wang, W., Seraj, F., Meratnia, N. dan Havinga, P.J.M., 2020. Speaker counting model based on transfer learning from SincNet Bottleneck layer. 2020 IEEE International Conference on Pervasive Computing and Communications (PerCom).
Wang, Z.-Q. dan Wang, D., 2021. Count and separate: Incorporating speaker counting for continuous speaker separation. ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Yousefi, M. dan Hansen, J.H.L., 2021. Real-time speaker counting in a cocktail party scenario using attention-guided convolutional neural network. Interspeech 2021
Butarbutar, M., Sachio, K., Nugroho, M., David, D. dan Ari Saputra, P., 2023. Adaptive Wiener filtering method for noise reduction in speech recognition system.
Cornell, S., Omologo, M., Squartini, S. dan Vincent, E., 2022. Overlapped speech detection and speaker counting using distant microphone arrays. Computer Speech & Language, 72, p.101306
Kanda, N., Gaur, Y., Wang, X., Meng, Z., Chen, Z., Zhou, T., dan Yoshioka, T., 2020. Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakers. Audio and Speech Processing. arXiv:2006.10930.
Kumar, M.A. dan Chari, K.M., 2019. Noise reduction using modified wiener filter in digital hearing aid for Speech Signal Enhancement. Journal of Intelligent Systems, 29(1), pp.1360–1378.
Laxmi, V. 2014. Audio Noise Reduction from Audio Signals and Speech Signals. International Journal of Computer Science Trends and Technology (IJCST).
Naik, S.S., Bhatikar, G dan Ugam Gaude, 2021. Analysis of Best Algorithm for Noise Reduction in Podcasting. International Journal of Scientific Research in Science and Technology, pp.246-250
Narangale, S. dan Shinde, G., 2017. Supervised Learning for Predictive Audio Noise Filter using Look-Back Method. The 2017 IAENG Internatinal Conference on Computer Science.
Park, T.J., Kanda, N., Dimitriadis, D., Han, K.J., Watanabe, S. dan Narayanan, S., 2022. A review of speaker diarization: Recent advances with deep learning. Computer Speech & Language, 72, p.101317.
Prasadh, S.K., Natrajan, S.S. dan Kalaivani, S., 2017. Efficiency analysis of noise reduction algorithms: Analysis of the best algorithm of noise reduction from a set of algorithms. 2017 International Conference on Inventive Computing and Informatics (ICICI).
Shah, D. dan Shah, B., 2023. Comparison of spectral subtraction noise reduction algorithms. Journal of Emerging Investigators.
Singla, M. dan Singh, Harpal., 2015. Paper on Frequency based Audio Noise Reduction using Butter Worth, Chebyshev, & Elliptical Filters. International Journal on Recent and Innovation Trends in Computing and Communication.
Sudheer Kumar, E., Jai Surya, K., Yaswanth Varma, K., Akash, A., dan Nithish Reddy, K., 2023. Noise reduction in audio file using spectral gatting and FFT by Python modules. Advances in Transdisciplinary Engineering.
Wang, W., Seraj, F., Meratnia, N. dan Havinga, P.J.M., 2020. Speaker counting model based on transfer learning from SincNet Bottleneck layer. 2020 IEEE International Conference on Pervasive Computing and Communications (PerCom).
Wang, Z.-Q. dan Wang, D., 2021. Count and separate: Incorporating speaker counting for continuous speaker separation. ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Yousefi, M. dan Hansen, J.H.L., 2021. Real-time speaker counting in a cocktail party scenario using attention-guided convolutional neural network. Interspeech 2021
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2024 Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Artikel ini berlisensiCreative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
