Group Communication with Context Codec for Ultra-Lightweight Source Separation

12/14/2020
by   Yi Luo, et al.
0

Ultra-lightweight model design is an important topic for the deployment of existing speech enhancement and source separation techniques on low-resource platforms. Various lightweight model design paradigms have been proposed in recent years; however, most models still suffer from finding a balance between model size, model complexity, and model performance. In this paper, we propose the group communication with context codec (GC3) design to decrease both model size and complexity without sacrificing the model performance. Group communication splits a high-dimensional feature into groups of low-dimensional features and applies a module to capture the inter-group dependency. A model can then be applied to the groups in parallel with a significantly smaller width. A context codec is applied to decrease the length of a sequential feature, where a context encoder compresses the temporal context of local features into a single feature representing the global characteristics of the context, and a context decoder decompresses the transformed global features back to the context features. Experimental results show that GC3 can achieve on par or better performance than a wide range of baseline architectures with as small as 2.5

READ FULL TEXT
research
11/17/2020

Ultra-Lightweight Speech Separation via Group Communication

Model size and complexity remain the biggest challenges in the deploymen...
research
11/07/2021

LiMuSE: Lightweight Multi-modal Speaker Extraction

The past several years have witnessed significant progress in modeling t...
research
09/11/2023

Addressing Feature Imbalance in Sound Source Separation

Neural networks often suffer from a feature preference problem, where th...
research
03/06/2023

Scaling strategies for on-device low-complexity source separation with Conv-Tasnet

Recently, several very effective neural approaches for single-channel sp...
research
11/24/2021

LightSAFT: Lightweight Latent Source Aware Frequency Transform for Source Separation

Conditioned source separations have attracted significant attention beca...
research
06/07/2019

Lightweight Parallel Foundations: a model-compliant communication layer

We present the Lightweight Parallel Foundations (LPF), an interoperable ...
research
01/19/2023

THLNet: two-stage heterogeneous lightweight network for monaural speech enhancement

In this paper, we propose a two-stage heterogeneous lightweight network ...

Please sign up or login with your details

Forgot password? Click here to reset