.png){kind=icon}
返回
Group Communication With Context Codec for Lightweight Source Separation
.png){kind=icon}
OA
AI
DOI：10.1109/TASLP.2021.3078640.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Despite the recent progress on neural network architectures for speech separation, the balance between the model size, model complexity and model performance is still an important and challenging problem for the deployment of such models to low-resource platforms. In this paper, we propose two simple modules, group communication and context codec, that can be easily applied to a wide range of architectures to jointly decrease the model size and complexity without sacrificing the performance. A group communication module splits a high-dimensional feature into groups of low-dimensional features and captures the inter-group dependency. A separation module with a significantly smaller model size can then be shared by all the groups. A context codec module, containing a context encoder and a context decoder, is designed as a learnable downsampling and upsampling module to decrease the length of a sequential feature processed by the separation module. The combination of the group communication and the context codec modules is referred to as the GC3 design. Experimental results show that applying GC3 on multiple network architectures for speech separation can achieve on-par or better performance with as small as 2.5% model size and 17.6% model complexity, respectively.
Keyword:
Codecs
Context modeling
Decoding
Complexity theory
Pipelines
Neural networks
Convolutional codes
Source separation
deep learning
lightweight
group communication
context codec
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
I
IF:
5.1
论文数:
2.6K
被引数:
1.1W
机构
引用论文
分享收藏A Comparison of the Effectiveness of Sodium Stibogluconate Monotherapy to Sodium Stibogluconate and Paromomycin Combination for the Treatment of Severe Post Kala Azar Dermal Leishmaniasis in South Sudan – A Retrospective Cohort Study.png)
PLOS ONEOAAI
PLOS ONEIF0
OAAI分享收藏Shape analysis of the neostriatum in frontotemporal lobar degeneration, Alzheimer's disease, and controlsNeuroImage
NeuroImageIF0
PREAI
分享收藏
查看更多内容