Sample Mixed-Based Data Augmentation for Domestic Audio Tagging

Audio tagging has attracted increasing attention since last decade and has various potential applications in many fields. The objective of audio tagging is to predict the labels of an audio clip. Recently deep learning methods have been applied to audio tagging and have achieved state-of-the-art performance, which provides a poor generalization ability on new data. However due to the limited size of audio tagging data such as DCASE data, the trained models tend to result in overfitting of the network. Previous data augmentation methods such as pitch shifting, time stretching and adding background noise do not show much improvement in audio tagging. In this paper, we explore the sample mixed data augmentation for the domestic audio tagging task, including mixup, SamplePairing and extrapolation. We apply a convolutional recurrent neural network (CRNN) with attention module with log-scaled mel spectrum as a baseline system. In our experiments, we achieve an state-of-the-art of equal error rate (EER) of 0.10 on DCASE 2016 task4 dataset with mixup approach, outperforming the baseline system without data augmentation.

[1]  Hiroshi Inoue,et al.  Data Augmentation by Pairing Samples for Images Classification , 2018, ArXiv.

[2]  Jon Barker,et al.  Chime-home: A dataset for sound source recognition in a domestic environment , 2015, 2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA).

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

[4]  Karol J. Piczak.  Environmental sound classification with convolutional neural networks , 2015, 2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP).

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

[6]  Qiang Huang,et al.  Convolutional gated recurrent neural network incorporating spatial features for audio tagging , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[7]  Xavier Gastaldi,et al.  Shake-Shake regularization , 2017, ArXiv.

[8]  Yann LeCun,et al.  Transformation Invariance in Pattern Recognition - Tangent Distance and Tangent Propagation , 2012, Neural Networks: Tricks of the Trade.

[9]  Mark B. Sandler,et al.  Automatic Tagging Using Deep Convolutional Neural Networks , 2016, ISMIR.

[10]  Zied Lachiri,et al.  Audio sounds classification using scattering features and support vectors machines for medical surveillance , 2018 .

[11]  Charu C. Aggarwal,et al.  Neural Networks and Deep Learning , 2018, Springer International Publishing.

[12]  Nojun Kwak,et al.  Analysis on the Dropout Effect in Convolutional Neural Networks , 2016, ACCV.

[13]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[14]  Tuomas Virtanen,et al.  TUT database for acoustic scene classification and sound event detection , 2016, 2016 24th European Signal Processing Conference (EUSIPCO).

[15]  Bernard Victorri,et al.  Transformation invariance in pattern recognition: Tangent distance and propagation , 2000 .

[16]  Tuomas Virtanen,et al.  Sound event detection using weakly labeled dataset with stacked convolutional and recurrent neural network , 2017, ArXiv.

[17]  Douglas M. Hawkins,et al.  The Problem of Overfitting , 2004, J. Chem. Inf. Model..

[18]  Thomas Hofmann,et al.  Audio Based Bird Species Identification using Deep Learning Techniques , 2016, CLEF.

[19]  Graham W. Taylor,et al.  Dataset Augmentation in Feature Space , 2017, ICLR.

[20]  Gerald Penn,et al.  Convolutional Neural Networks for Speech Recognition , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[21]  Qiang Huang,et al.  Attention and Localization Based on a Deep Convolutional Recurrent Model for Weakly Supervised Audio Tagging , 2017, INTERSPEECH.

[22]  Markus Koppenberger,et al.  Content-based music audio recommendation , 2005, ACM Multimedia.

[23]  Takuya Akiba,et al.  Shakedrop Regularization for Deep Residual Learning , 2018, IEEE Access.

[24]  Masakazu Iwamura,et al.  ShakeDrop regularization , 2018, ICLR.

[25]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[26]  Qiang Huang,et al.  Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging , 2016, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[27]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[28]  Haibo Mi,et al.  Mixup-Based Acoustic Scene Classification Using Multi-Channel Convolutional Neural Network , 2018, PCM.

[29]  Justin Salamon,et al.  Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification , 2016, IEEE Signal Processing Letters.