2018/12/15 by Oren Barkan, David Tsiris, Barkan, Oren +5 · 2 citations
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (stat.ML) #Music Technology and Sound Studies #Music and Audio Processing #Sound (cs.SD) #Speech and Audio Processing #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1812.06349
openalex publication_date 2018/12/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Sound synthesis is a complex field that requires domain expertise. Manual\ntuning of synthesizer parameters to match a specific sound can be an exhaustive\ntask, even for experienced sound engineers. In this paper, we introduce\nInverSynth - an automatic method for synthesizer parameters tuning to match a\ngiven input sound. InverSynth is based on strided convolutional neural networks\nand is capable of inferring the synthesizer parameters configuration from the\ninput spectrogram and even from the raw audio. The effectiveness InverSynth is\ndemonstrated on a subtractive synthesizer with four frequency modulated\noscillators, envelope generator and a gater effect. We present extensive\nquantitative and qualitative results that showcase the superiority InverSynth\nover several baselines. Furthermore, we show that the network depth is an\nimportant factor that contributes to the prediction accuracy.\n