Name
Title | ||
|---|---|---|
Neural Networks Using Full-Band and Subband Spatial Features for Mask Based Source Separation |
Abstract | ||
|---|---|---|
With a microphone array, spatial diversity can be exploited to estimate time-frequency masks that effectively suppress interfering speakers as well as noise. Here, we propose a deep learning approach where the signal components are distinguished based on the associated directions of arrival. To capture the target signal spectrogram more accurately, the estimation can be performed for each subband ... |
Year | DOI | Venue |
|---|---|---|
2021 | 10.23919/EUSIPCO54536.2021.9616138 | 2021 29th European Signal Processing Conference (EUSIPCO) |
Keywords | DocType | ISSN |
source separation,speech enhancement,time-frequency masking,neural networks,direction-of-arrival | Conference | 2076-1465 |
ISBN | Citations | PageRank |
978-9-0827-9706-0 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Alexander Bohlender | 1 | 0 | 1.35 |
| Ann Spriet | 2 | 0 | 0.34 |
| Wouter Tirry | 3 | 0 | 0.34 |
| Nilesh Madhu | 4 | 0 | 0.34 |