.png){kind=icon}
Return
Multi-layer encoder-decoder time-domain single channel speech separation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patrec.2024.03.020.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
With the emergence of more advanced separation networks, significant progress has been made in timedomain speech separation methods. These methods typically use a temporal encoder-decoder structure to encode speech feature sequences, thereby accomplishing the separation task. However, due to the limitation of traditional encoder-decoder structure, the separation performance decreases sharply when the encoded sequence is short, and when encoded sequence is sufficiently long, the separation performance improves, but which leads to an increase in computational complexity and training cost. Therefore, this paper compresses and reconstructs the speech feature sequence through a multi-layer convolution structure, and proposes a multilayer encoder-decoder time-domain speech separation model (MLED). In this model, our encoder-decoder structure can compress speech sequence to a short length while ensuring the separation performance does not decrease. And combined with our multi-scale temporal attention (MSTA) separation network, MLED achieves efficient and precise separation of short encoded sequences. Therefore, compared to previous advanced timedomain separation methods, our experiments show that MLED achieves competitive separation performance with smaller model size, lower computational complexity, and training cost.
Keywords:
Time-domain speech separation
Attention mechanism
Multi-layer encoder-decoder
Training cost
Journal
IF:
3.3
Papers:
8.0K
Citations:
1.6W
Organization
Cited Papers
Solution structure of the Lewis x oligosaccharide determined by NMR spectroscopy and molecular dynamics simulations.png)
Biochemistry
BiochemistryIF0
PREAI
ShareSaveNeonatal caffeine administration causes a permanent increase in the dendritic length of prefrontal cortical neurons of ratsSynapse
SynapseIF0
PREAI
ShareSaveShape analysis of the neostriatum in frontotemporal lobar degeneration, Alzheimer's disease, and controlsNeuroImage
NeuroImageIF0
PREAI
ShareSaveShareSaveU2-Net: Going deeper with nested U-structure for salient object detectionPATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAIShareSaveShareSave
View more