Unsupervised Feature Learning for Audio Analysis

12/11/2017
by   Matthias Meyer, et al.
0

Identifying acoustic events from a continuously streaming audio source is of interest for many applications including environmental monitoring for basic research. In this scenario neither different event classes are known nor what distinguishes one class from another. Therefore, an unsupervised feature learning method for exploration of audio data is presented in this paper. It incorporates the two following novel contributions: First, an audio frame predictor based on a Convolutional LSTM autoencoder is demonstrated, which is used for unsupervised feature extraction. Second, a training method for autoencoders is presented, which leads to distinct features by amplifying event similarities. In comparison to standard approaches, the features extracted from the audio frame predictor trained with the novel approach show 13 results when used with a classifier and 36 clustering.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/05/2020

Multi-level Feature Learning on Embedding Layer of Convolutional Autoencoders and Deep Inverse Feature Learning for Image Clustering

This paper introduces Multi-Level feature learning alongside the Embeddi...
research
09/02/2020

Unsupervised Feature Learning by Autoencoder and Prototypical Contrastive Learning for Hyperspectral Classification

Unsupervised learning methods for feature extraction are becoming more a...
research
03/18/2016

Comparing Time and Frequency Domain for Audio Event Recognition Using Deep Learning

Recognizing acoustic events is an intricate problem for a machine and an...
research
07/13/2016

Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging

Environmental audio tagging aims to predict only the presence or absence...
research
02/26/2019

Acoustic scene classification using multi-layer temporal pooling based on convolutional neural network

The temporal dynamics and the discriminative information in the audio si...
research
08/25/2023

Deep Active Audio Feature Learning in Resource-Constrained Environments

The scarcity of labelled data makes training Deep Neural Network (DNN) m...
research
06/06/2014

Unsupervised Feature Learning through Divergent Discriminative Feature Accumulation

Unlike unsupervised approaches such as autoencoders that learn to recons...

Please sign up or login with your details

Forgot password? Click here to reset