Learning to Inference with Early Exit in the Progressive Speech Enhancement

06/22/2021
by   Andong Li, et al.
0

In real scenarios, it is often necessary and significant to control the inference speed of speech enhancement systems under different conditions. To this end, we propose a stage-wise adaptive inference approach with early exit mechanism for progressive speech enhancement. Specifically, in each stage, once the spectral distance between adjacent stages lowers the empirically preset threshold, the inference will terminate and output the estimation, which can effectively accelerate the inference speed. To further improve the performance of existing speech enhancement systems, PL-CRN++ is proposed, which is an improved version over our preliminary work PL-CRN and combines stage recurrent mechanism and complex spectral mapping. Extensive experiments are conducted on the TIMIT corpus, the results demonstrate the superiority of our system over state-of-the-art baselines in terms of PESQ, ESTOI and DNSMOS. Moreover, by adjusting the threshold, we can easily control the inference efficiency while sustaining the system performance.

READ FULL TEXT
research
03/22/2020

A Time-domain Monaural Speech Enhancement with Recursive Learning

In this paper, we propose a type of neural network with recursive learni...
research
03/22/2020

Monaural Speech Enhancement with Recursive Learning in the Time Domain

In this paper, we propose a type of neural network with recursive learni...
research
02/24/2021

Speech Enhancement Using Multi-Stage Self-Attentive Temporal Convolutional Networks

Multi-stage learning is an effective technique to invoke multiple deep-l...
research
04/08/2021

Phoneme-based Distribution Regularization for Speech Enhancement

Existing speech enhancement methods mainly separate speech from noises a...
research
01/15/2020

Improving GANs for Speech Enhancement

Generative adversarial networks (GAN) have recently been shown to be eff...
research
07/28/2021

CycleGAN-based Non-parallel Speech Enhancement with an Adaptive Attention-in-attention Mechanism

Non-parallel training is a difficult but essential task for DNN-based sp...
research
10/25/2021

Multichannel Speech Enhancement without Beamforming

Deep neural networks are often coupled with traditional spatial filters,...

Please sign up or login with your details

Forgot password? Click here to reset