Point Cloud Audio Processing
arXiv:2105.02469 · doi:10.1109/WASPAA52581.2021.9632668
Abstract
Most audio processing pipelines involve transformations that act on fixed-dimensional input representations of audio. For example, when using the Short Time Fourier Transform (STFT) the DFT size specifies a fixed dimension for the input representation. As a consequence, most audio machine learning models are designed to process fixed-size vector inputs which often prohibits the repurposing of learned models on audio with different sampling rates or alternative representations. We note, however, that the intrinsic spectral information in the audio signal is invariant to the choice of the input representation or the sampling rate. Motivated by this, we introduce a novel way of processing audio signals by treating them as a collection of points in feature space, and we use point cloud machine learning models that give us invariance to the choice of representation parameters, such as DFT size or the sampling rate. Additionally, we observe that these methods result in smaller models, and allow us to significantly subsample the input representation with minimal effects to a trained model performance.
arXiv commentAccepted at WASPAA 2021, Code: https://github.com/SubramaniKrishna/point-cloud-audio
References in corpus (6)
- Adam: A Method for Stochastic Optimization
- Semi-Supervised Classification with Graph Convolutional Networks
- Improving neural networks by preventing co-adaptation of feature detectors
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
- PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
- PointCNN: Convolution On -Transformed Points