Deep Convex Representations: Feature Representations for Bioacoustics Classification

Anshul Thakur, Vinayak Abrol, Pulkit Sharma, Padmanabhan Rajan

In this paper, a deep convex matrix factorization framework is proposed for bioacoustics classification. Archetypal analysis, a form of convex non-negative matrix factorization, is used for acoustic modelling at each level of this framework. At first level, the input feature matrix is factorized into an archetypal dictionary and corresponding convex representations. The representation matrix obtained at the first level is further factorized into a dictionary and convex representations at second level. This hierarchical factorization continues until a desired depth is achieved. We observe that the dictionaries at different levels model complimentary information present in the data. The atoms of the dictionary learned at the first layer lie on convex hull of the data, thus try to model the extremal behaviour. On the contrary, atoms of the deeper dictionaries lie on the convex hull as well as inside the convex hull. Hence, these dictionaries can simultaneously model the extremal and average behaviour of the data. The convex representations obtained from these deeper dictionaries are referred as deep convex representations. Due to inherent sparsity, they result in efficient classification performance. Through experiments on two available bioacoustics datasets, we show that the proposed approach yield comparable or better results than state-of-art approaches.

 DOI: 10.21437/Interspeech.2018-1705

Cite as: Thakur, A., Abrol, V., Sharma, P., Rajan, P. (2018) Deep Convex Representations: Feature Representations for Bioacoustics Classification. Proc. Interspeech 2018, 2127-2131, DOI: 10.21437/Interspeech.2018-1705.

  author={Anshul Thakur and Vinayak Abrol and Pulkit Sharma and Padmanabhan Rajan},
  title={Deep Convex Representations: Feature Representations for Bioacoustics Classification},
  booktitle={Proc. Interspeech 2018},