DiffMoog: a Differentiable Modular Synthesizer for Sound Matching
This paper presents DiffMoog - a differentiable modular synthesizer with a comprehensive set of modules typically found in commercial instruments. Being differentiable, it allows integration into neural networks, enabling automated sound matching, to replicate a given audio input. Notably, DiffMoog facilitates modulation capabilities (FM/AM), low-frequency oscillators (LFOs), filters, envelope shapers, and the ability for users to create custom signal chains. We introduce an open-source platform that comprises DiffMoog and an end-to-end sound matching framework. This framework utilizes a novel signal-chain loss and an encoder network that self-programs its outputs to predict DiffMoogs parameters based on the user-defined modular architecture. Moreover, we provide insights and lessons learned towards sound matching using differentiable synthesis. Combining robust sound capabilities with a holistic platform, DiffMoog stands as a premier asset for expediting research in audio synthesis and machine learning.
Code (1)
Tasks
Audio SynthesisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Synthesizer Sound Matching Using Audio Spectrogram Transformers
Systems for synthesizer sound matching, which automatically set the parameters of a synthesizer to emulate an input sound, have the potential to make the process of synthesizer programming faster and easier for novice an…
Modulation Discovery with Differentiable Digital Signal Processing
Modulations are a critical part of sound design and music production, enabling the creation of complex and evolving audio. Modern synthesizers provide envelopes, low frequency oscillators (LFOs), and more parameter autom…
NAS-FM: Neural Architecture Search for Tunable and Interpretable Sound Synthesis based on Frequency Modulation
Developing digital sound synthesizers is crucial to the music industry as it provides a low-cost way to produce high-quality sounds with rich timbres. Existing traditional synthesizers often require substantial expertise…
Neural Architecture SearchOne Billion Audio Sounds from GPU-enabled Modular Synthesis
We release synth1B1, a multi-modal audio corpus consisting of 1 billion 4-second synthesized sounds, paired with the synthesis parameters used to generate them. The dataset is 100x larger than any audio dataset in the li…
GPUHyperparameter OptimizationCreative Text-to-Audio Generation via Synthesizer Programming
Neural audio synthesis methods now allow specifying ideas in natural language. However, these methods produce results that cannot be easily tweaked, as they are based on large latent spaces and up to billions of uninterp…
Audio GenerationAudio Synthesis