Neural network for multi-exponential sound energy decay analysis

05/19/2022
by   Georg Götz, et al.
0

An established model for sound energy decay functions (EDFs) is the superposition of multiple exponentials and a noise term. This work proposes a neural-network-based approach for estimating the model parameters from EDFs. The network is trained on synthetic EDFs and evaluated on two large datasets of over 20000 EDF measurements conducted in various acoustic environments. The evaluation shows that the proposed neural network architecture robustly estimates the model parameters from large datasets of measured EDFs, while being lightweight and computationally efficient. An implementation of the proposed neural network is publicly available.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/27/2023

Deep sound-field denoiser: optically-measured sound-field denoising using deep neural network

This paper proposes a deep sound-field denoiser, a deep neural network (...
research
07/21/2019

Adaptive Weight Decay for Deep Neural Networks

Regularization in the optimization of deep neural networks is often crit...
research
10/27/2017

Direction of arrival estimation for multiple sound sources using convolutional recurrent neural network

This paper proposes a deep neural network for estimating the directions ...
research
10/18/2016

Small-footprint Highway Deep Neural Networks for Speech Recognition

State-of-the-art speech recognition systems typically employ neural netw...
research
06/21/2018

CaloriNet: From silhouettes to calorie estimation in private environments

We propose a novel deep fusion architecture, CaloriNet, for the online e...
research
01/12/2018

Not All Ops Are Created Equal!

Efficient and compact neural network models are essential for enabling t...
research
12/25/2020

Neural Network Training With Homomorphic Encryption

We introduce a novel method and implementation architecture to train neu...

Please sign up or login with your details

Forgot password? Click here to reset