Evaluasi Kinerja Plugin AI Clarity Vx dalam Mereduksi Microphone Bleeding pada Multitrack Vocal Live Sound Berdasarkan SNR
Keywords:
Artificial Intelligence, Clarity Vx, Live Sound, Microphone Bleeding, Signal-to-Noise RatioAbstract
Menjaga kejernihan sinyal vokal pada sistem suara pertunjukan langsung (live sound) sering kali terkendala oleh fenomena microphone bleeding, terutama akibat instrumen berdinamika keras. Keterbatasan perangkat konvensional dalam menyaring kebocoran tersebut mendorong pemanfaatan algoritma kecerdasan buatan melalui plugin Waves Clarity Vx. Penelitian ini bertujuan untuk mengevaluasi kinerja plugin tersebut dalam mereduksi microphone bleeding pada kanal vokal multitrack guna menentukan batas optimal terhadap intensitas pemrosesan. Dengan menggunakan pendekatan kuantitatif eksperimental melalui simulasi Virtual Soundcheck, pengujian dilakukan pada 15 sampel vokal dengan menerapkan variasi tingkat reduksi mulai dari 0%, 50%, 75%, hingga 100%. Tingkat kejernihan sinyal dievaluasi secara objektif berdasarkan pengukuran nilai amplitudo Root Mean Square (RMS) yang dikonversi menjadi Signal-to-Noise Ratio (SNR). Hasil analisis menunjukkan bahwa intensitas pemrosesan 50% adalah sebagai titik optimal karena mampu meredam kebisingan latar secara signifikan tanpa mengurangi kualitas sinyal vokal, sedangkan intensitas 100% terbukti stagnan dan justru berisiko mereduksi energi vokal utama. Dengan demikian, plugin AI Clarity Vx dinilai efisien untuk diimplementasikan secara langsung pada sistem live sound selama pengaturannya dikunci pada batas aman 50%.
References
[1] Y. Hashizume, L. Li, A. Miyashita, and T. Toda, "Learning Separated Representations for Instrument-based Music Similarity," APSIPA Trans. Signal Inf. Process., vol. 14, no. 1, pp. 1-36, 2025, doi: 10.1561/116.20250013.
[2] G. Plaja-Roglans, X. Serra, and M. Rocamora, "Leveraging Carnatic Live Recordings for Singing Voice Separation Using Regression-Guided Latent Diffusion," Proc. Int. Soc. Music Inf. Retr. Conf., vol. 2025, pp. 830-838, 2025, doi: 10.5281/zenodo.17706605.
[3] L. A. A. R. Putri, I. G. E. W. Pratama, I Dewa Made Bayu Atmaja Darmawan, A. A. I. N. Eka Karyawati, Ida Bagus Made Mahendra, and I Ketut Gede Suhartana, "Penerapan Metode Fast Independent Component Analysis (FastICA) dalam Memisahkan Vokal dan Instrumen Seni Geguntangan," J. Buana Inform., vol. 13, no. 1, pp. 77-84, 2022, doi: 10.24002/jbi.v13i1.5693.
[4] R. Rajesh and P. Rajan, "Neural Networks for Interference Reduction in Multi-Track Recordings," IEEE Work. Appl. Signal Process. to Audio Acoust., vol. 2023-Octob, pp. 1-5, 2023, doi: 10.1109/WASPAA58266.2023.10248133.
[5] Dewi Nurdiyah, Eko Mulyanto Yuniarno, Yoyon Kusnendar Suprapto, and Mauridhi Hery Purnomo, "IRAWNET: A Method for Transcribing Indonesian Classical Music Notes Directly from Multichannel Raw Audio," Emit. Int. J. Eng. Technol., vol. 11, no. 2, pp. 246-264, 2023, doi: 10.24003/emitter.v11i2.827.
[6] R. A. Amin, "ANALISIS PERBANDINGAN KEBISINGAN TERHADAP SISTEM SUARA AKUSTIK DENGAN EFEK SURROUND DAN TANPA EFEK SURROUND," J. Elektro Kontrol, vol. 5, no. 1, pp. 36-48, Jul. 2025, doi: 10.24176/elkon.v5i1.14811.
[7] C. J. Steinmetz et al., "Audio Signal Processing in the Artificial Intelligence Era: Challenges and Directions," AES J. Audio Eng. Soc., vol. 73, no. 8, pp. 406-428, 2025, doi: 10.17743/jaes.2022.0209.
[8] E. In, R. Chandrakumar, F. Soria, and W. W. W. V. Com, "Lightweight Deep Neural Networks for Real-Time Speech Enhancement on Edge Devices Comparator With Low Offset Voltage Implemented in 45nm CMOS Technology," vol. 1, no. 3, pp. 1-8, 2025, doi: https://doi.org/10.17051/NJSAP/01.03.01.
[9] C. J. Steinmetz, J. Pons, S. Pascual, and J. Serrà, "Automatic multitrack mixing with a differentiable mixing console of neural audio effects," ICASSP, IEEE Int. Conf. Acoust. Speech Signal Process. - Proc., vol. 2021-June, pp. 71-75, 2021, doi: 10.1109/ICASSP39728.2021.9414364.
[10] A. Défossez, "Hybrid Spectrogram and Waveform Source Separation," pp. 1-13, 2021. doi: 10.48550/arXiv.2111.03600
[11] S. Rouard, F. Massa, and A. Defossez, "Hybrid Transformers for Music Source Separation," ICASSP, IEEE Int. Conf. Acoust. Speech Signal Process. - Proc., vol. 2023-June, pp. 2-6, 2023, doi: 10.1109/ICASSP49357.2023.10096956.
[12] H. Dubey et al., "ICASSP 2023 Deep Noise Suppression Challenge," IEEE Open J. Signal Process., vol. 5, pp. 725-737, 2024, doi: 10.1109/OJSP.2024.3378602.
[13] Waves.com," Clarity Vx Pro". https://www.waves.com/plugins/clarity-vx- pro#tab-product
[14] K. Zhen, M. S. Lee, J. Sung, S. Beack, and M. Kim, "Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding," IEEE Signal Process. Lett., vol. 27, pp. 2159-2163, 2020, doi: 10.1109/LSP.2020.3039765.
