DeepAI AI Chat
Log In Sign Up

Sparse Mixture of Local Experts for Efficient Speech Enhancement

by   Aswin Sivaraman, et al.
Indiana University Bloomington

In this paper, we investigate a deep learning approach for speech denoising through an efficient ensemble of specialist neural networks. By splitting up the speech denoising task into non-overlapping subproblems and introducing a classifier, we are able to improve denoising performance while also reducing computational complexity. More specifically, the proposed model incorporates a gating network which assigns noisy speech signals to an appropriate specialist network based on either speech degradation level or speaker gender. In our experiments, a baseline recurrent network is compared against an ensemble of similarly-designed smaller recurrent networks regulated by the auxiliary gating network. Using stochastically generated batches from a large noisy speech corpus, the proposed model learns to estimate a time-frequency masking matrix based on the magnitude spectrogram of an input mixture signal. Both baseline and specialist networks are trained to estimate the ideal ratio mask, while the gating network is trained to perform subproblem classification. Our findings demonstrate that a fine-tuned ensemble network is able to exceed the speech denoising capabilities of a generalist network, doing so with fewer model parameters.


page 1

page 2

page 3

page 4


Speech denoising by parametric resynthesis

This work proposes the use of clean speech vocoder parameters as the tar...

VoiceID Loss: Speech Enhancement for Speaker Verification

In this paper, we propose VoiceID loss, a novel loss function for traini...

Deep Interaction between Masking and Mapping Targets for Single-Channel Speech Enhancement

The most recent deep neural network (DNN) models exhibit impressive deno...

Boosted Locality Sensitive Hashing: Discriminative Binary Codes for Source Separation

Speech enhancement tasks have seen significant improvements with the adv...

Speech enhancement with mixture-of-deep-experts with clean clustering pre-training

In this study we present a mixture of deep experts (MoDE) neural-network...

Quality Resilient Deep Neural Networks

We study deep neural networks for classification of images with quality ...