Combining different models is a common strategy to build a good audio source separation system. In this work we combine two powerful deep neural networks for audio single channel source separation (SCSS). Namely, we combine fully convolutional neural networks (FCNs) and recurrent neural networks, specifically, bidirectional long short-term memory recurrent neural networks (BLSTMs). FCNs are good at extracting useful features from the audio data and BLSTMs are good at modeling the temporal structure of the audio signals. Our experimental results show that combining FCNs and BLSTMs achieves better separation performance than using each model individually.
Grais, Emad M.; Plumbley, Mark D.
Affiliation: University of Surrey, Guildford, Surrey, UK
AES Convention: 144 (May 2018) Paper Number: 9990
Publication Date: May 14, 2018
Subject: Posters: Audio Processing/Audio Education
No AES members have commented on this paper yet.
If you are not yet an AES member and have something important to say about this paper then we urge you to join the AES today and make your voice heard. You can join online today by clicking here.