AclNet: efficient end-to-end audio classification CNN

We propose an efficient end-to-end convolutional neural network architecture, AclNet, for audio classification. When trained with our data augmentation and regularization, we achieved state-of-the-art performance on the ESC-50 corpus with 85:65% accuracy. Our network allows configurations such that memory and compute requirements are drastically reduced, and a tradeoff analysis of accuracy and complexity is presented. The analysis shows high accuracy at significantly reduced computational complexity compared to existing solutions. For example, a configuration with only 155k parameters and 49:3 million multiply-adds per second is 81:75%, exceeding human accuracy of 81:3%. This improved efficiency can enable always-on inference in energy-efficient platforms.

[1]  Tatsuya Harada,et al.  Learning from Between-class Examples for Deep Sound Recognition , 2017, ICLR.

[2]  Gerhard Widmer,et al.  ACOUSTIC SCENE CLASSIFICATION WITH FULLY CONVOLUTIONAL NEURAL NETWORKS AND I-VECTORS Technical Report , 2018 .

[3]  Lukás Burget,et al.  Convolutional Neural Networks and x-vector Embedding for DCASE2018 Acoustic Scene Classification Challenge , 2018, ArXiv.

[4]  Karol J. Piczak.  ESC: Dataset for Environmental Sound Classification , 2015, ACM Multimedia.

[5]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[6]  David Gregg,et al.  The Movidius Myriad Architecture's Potential for Scientific Computing , 2015, IEEE Micro.

[7]  Yifan Gong,et al.  Singular value decomposition based low-footprint speaker adaptation and personalization for deep neural network , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[8]  Anurag Kumar,et al.  Knowledge Transfer from Weakly Labeled Audio Using Convolutional Neural Network for Sound Events and Scenes , 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[9]  Hemant A. Patil,et al.  Unsupervised Filterbank Learning Using Convolutional Restricted Boltzmann Machine for Environmental Sound Classification , 2017, INTERSPEECH.

[10]  Hemant A. Patil,et al.  Novel Phase Encoded Mel Filterbank Energies for Environmental Sound Classification , 2017, PReMI.

[11]  Song Han,et al.  Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding , 2015, ICLR.

[12]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[13]  Bhiksha Raj,et al.  A Closer Look at Weak Label Learning for Audio Events , 2018, ArXiv.

[14]  Hongyi Zhang,et al.  mixup: Beyond Empirical Risk Minimization , 2017, ICLR.

[15]  Aren Jansen,et al.  CNN architectures for large-scale audio classification , 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[16]  Antonio Torralba,et al.  SoundNet: Learning Sound Representations from Unlabeled Video , 2016, NIPS.

[17]  Tuomas Virtanen,et al.  A multi-device dataset for urban acoustic scene classification , 2018, DCASE.

[18]  Michael Deisher,et al.  Implementation of efficient, low power deep neural networks on next-generation intel client platforms , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[19]  Wei Dai,et al.  Very deep convolutional neural networks for raw waveforms , 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[20]  Tatsuya Harada,et al.  Learning environmental sounds with end-to-end convolutional neural network , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).