Monoaural audio source separation using deep convolutional neural networks

Citació

  • Chandna P, Miron M, Janer J, Gómez E. Monoaural audio source separation using deep convolutional neural networks. In: Tichavsky P, Babaie-Zadeh M, Michel OJ, Thirion-Moreau N, editors. Latent variable analysis and signal separation. 13th International Conference, LVA/ICA 2017; 2017 Feb 21-23; Grenoble, France. [place unknown]: Springer; 2017. p. 258-66. DOI: 10.1007/978-3-319-53547-0_25

Enllaç permanent

Descripció

  • Resum

    In this paper we introduce a low-latency monaural source separation framework using a Convolutional Neural Network (CNN). We use a CNN to estimate time-frequency soft masks which are applied for source separation. We evaluate the performance of the neural network on a database comprising of musical mixtures of three instruments: voice, drums, bass as well as other instruments which vary from song to song. The proposed architecture is compared to a Multilayer Perceptron (MLP), achieving on-par results and a significant improvement in processing time. The algorithm was submitted to source separation evaluation campaigns to test efficiency, and achieved competitive results.
  • Descripció

    Comunicació presentada a 13th International Conference on Latent Variable Analysis and Signal Separation, celebrada a Grenoble (França) els dies 21 a 23 de febrer de 2017.
  • Mostra el registre complet