Unsupervised Adversarial Domain Adaptation Based on The Wasserstein Distance For Acoustic Scene Classification

A challenging problem in deep learning-based machine listening field is the degradation of the performance when using data from unseen conditions. In this paper we focus on the acoustic scene classification (ASC) task and propose an adversarial deep learning method to allow adapting an acoustic scene classification system to deal with a new acoustic channel resulting from data captured with a different recording device. We build upon the theoretical model of ℋΔℋ-distance and previous adversarial discriminative deep learning method for ASC unsupervised domain adaptation, and we present an adversarial training based method using the Wasserstein distance. We improve the state-of-the-art mean accuracy on the data from the unseen conditions from 32% to 45%, using the TUT Acoustic Scenes dataset.

[1]  José M. F. Moura,et al.  Adversarial Multiple Source Domain Adaptation , 2018, NeurIPS.

[2]  François Laviolette,et al.  Domain-Adversarial Training of Neural Networks , 2015, J. Mach. Learn. Res..

[3]  Marc-Christoph Gerasch,et al.  Acoustic Scene Classification , 2015 .

[4]  Alexei A. Efros,et al.  Unbiased look at dataset bias , 2011, CVPR 2011.

[5]  Jianmin Wang,et al.  Multi-Adversarial Domain Adaptation , 2018, AAAI.

[6]  Koby Crammer,et al.  A theory of learning from different domains , 2010, Machine Learning.

[7]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[8]  Victor S. Lempitsky,et al.  Unsupervised Domain Adaptation by Backpropagation , 2014, ICML.

[9]  Mehryar Mohri,et al.  Sample Selection Bias Correction Theory , 2008, ALT.

[10]  Yiannis Andreopoulos,et al.  Improving Adversarial Discriminative Domain Adaptation , 2018, ArXiv.

[11]  D. A. Edwards.  On the Kantorovich–Rubinstein theorem , 2011 .

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

[13]  R. Stephenson.  A and V , 1962, The British journal of ophthalmology.

[14]  Koby Crammer,et al.  Learning Bounds for Domain Adaptation , 2007, NIPS.

[15]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[16]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[17]  Barbara Caputo,et al.  A Deeper Look at Dataset Bias , 2015, Domain Adaptation in Computer Vision Applications.

[18]  Trevor Darrell,et al.  Adversarial Discriminative Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Taesung Park,et al.  CyCADA: Cycle-Consistent Adversarial Domain Adaptation , 2017, ICML.

[20]  Ievgen Redko,et al.  Theoretical Analysis of Domain Adaptation with Optimal Transport , 2016, ECML/PKDD.

[21]  Kyogu Lee,et al.  Convolutional Neural Networks with Binaural Representations and Background Subtraction for Acoustic Scene Classification , 2017, DCASE.

[22]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[23]  W. Marsden.  I and J , 2012 .

[24]  Shao-Hu Peng,et al.  Acoustic Scene Classification Using Deep Convolutional Neural Network and Multiple Spectrograms Fusion , 2017, DCASE.

[25]  Dmitriy Serdyuk,et al.  Unsupervised adversarial domain adaptation for acoustic scene classification , 2018, ArXiv.