Towards Lightweight Controllable Audio Synthesis with Conditional Implicit Neural Representations
This work addresses the challenge of real-time, controllable audio synthesis for applications requiring efficient processing, but it is incremental as it builds on existing implicit neural representation methods with specific optimizations.
The paper tackled the problem of high computational cost in audio synthesis by exploring Conditional Implicit Neural Representations (CINRs) as lightweight backbones, finding that small Periodic CINRs learn faster and produce better audio reconstructions than Transposed Convolutional Neural Networks with equal parameters, though they are sensitive to hyperparameters and introduce artificial high-frequency noise.
The high temporal resolution of audio and our perceptual sensitivity to small irregularities in waveforms make synthesizing at high sampling rates a complex and computationally intensive task, prohibiting real-time, controllable synthesis within many approaches. In this work we aim to shed light on the potential of Conditional Implicit Neural Representations (CINRs) as lightweight backbones in generative frameworks for audio synthesis. Our experiments show that small Periodic Conditional INRs (PCINRs) learn faster and generally produce quantitatively better audio reconstructions than Transposed Convolutional Neural Networks with equal parameter counts. However, their performance is very sensitive to activation scaling hyperparameters. When learning to represent more uniform sets, PCINRs tend to introduce artificial high-frequency components in reconstructions. We validate this noise can be minimized by applying standard weight regularization during training or decreasing the compositional depth of PCINRs, and suggest directions for future research.