Other Open Access

Binaural Source Separation with Convolutional Neural Networks

Erruz, Gerard

Thesis supervisor(s)

Miron, Marius; Garriga, Adan

This work is a study on source separation techniques for binaural music mixtures. The chosen framework uses a Convolutional Neural Network (CNN) to estimate time-frequency soft masks. This masks are used to extract the different sources from the original two-channel mixture signal. Its baseline single-channel architecture performed state-of-the-art results on monaural music mixtures under low-latency conditions. It has been extended to perform separation in two-channel signals, being the first two-channel CNN joint estimation architecture. This means that filters are learned for each source by taking in account both channels information. Furthermore, a specific binaural condition is included during training stage. It uses Interaural Level Difference (ILD) information to improve spatial images of extracted sources. Concurrently, we present a novel tool to create binaural scenes for testing purposes. Multiple binaural scenes are rendered from a music dataset of four instruments (voice, drums, bass and others). The CNN framework have been tested for these binaural scenes and compared with monaural and stereo results. The system showed a great amount of adaptability and good separation results in all the scenarios. These results are used to evaluate spatial information impact on separation performance.

Files (4.6 MB)
Name Size
ErruzG_mthesis.pdf
md5:d9744762d1ae9d99afda967749046ff9
4.6 MB Download
221
592
views
downloads
All versions This version
Views 221221
Downloads 592592
Data volume 2.7 GB2.7 GB
Unique views 210210
Unique downloads 554554

Share

Cite as