Learning Environmental Sounds with Multi-scale Convolutional Neural Network
This work addresses environmental sound classification, offering a novel method for better audio representation, but it is incremental as it builds on existing waveform-based models.
The paper tackled the challenge of learning acoustic models from raw waveforms by proposing a multi-scale convolutional neural network (WaveMsNet) that improves frequency resolution and fuses waveform and spectrogram features, achieving classification accuracies of 93.75% on ESC-10 and 79.10% on ESC-50.
Deep learning has dramatically improved the performance of sounds recognition. However, learning acoustic models directly from the raw waveform is still challenging. Current waveform-based models generally use time-domain convolutional layers to extract features. The features extracted by single size filters are insufficient for building discriminative representation of audios. In this paper, we propose multi-scale convolution operation, which can get better audio representation by improving the frequency resolution and learning filters cross all frequency area. For leveraging the waveform-based features and spectrogram-based features in a single model, we introduce two-phase method to fuse the different features. Finally, we propose a novel end-to-end network called WaveMsNet based on the multi-scale convolution operation and two-phase method. On the environmental sounds classification datasets ESC-10 and ESC-50, the classification accuracies of our WaveMsNet achieve 93.75% and 79.10% respectively, which improve significantly from the previous methods.