Acoustic scene classification using time-frequency representations as texture images

Shamsiah Abidin

Research output: ThesisDoctoral Thesis

108 Downloads (Pure)

Abstract

Acoustic scene classification (ASC) is important for context-aware applications to recognise the environment based on the available acoustic information. Despite its promising application prospects, ASC is a challenging problem due to both the similar characteristics of some scenes and complexity of sounds present in other scenes. This dissertation presents findings in the field of ASC utilising hand-crafted visually inspired features extracted from a 2D time-frequency image representation. The time-­frequency visual representations of the temporal and spectral structures for each acoustic scene with suitable feature extraction methods were shown to enhance the identification of the different scene classes.
Original languageEnglish
QualificationDoctor of Philosophy
Awarding Institution
  • The University of Western Australia
Award date30 Oct 2019
DOIs
Publication statusUnpublished - 2019

Fingerprint

Textures
Acoustics
Feature extraction
Acoustic waves

Cite this

@phdthesis{2edcc9c1f36c4c31b5ac9a8d3a7ea45f,
title = "Acoustic scene classification using time-frequency representations as texture images",
abstract = "Acoustic scene classification (ASC) is important for context-aware applications to recognise the environment based on the available acoustic information. Despite its promising application prospects, ASC is a challenging problem due to both the similar characteristics of some scenes and complexity of sounds present in other scenes. This dissertation presents findings in the field of ASC utilising hand-crafted visually inspired features extracted from a 2D time-frequency image representation. The time-­frequency visual representations of the temporal and spectral structures for each acoustic scene with suitable feature extraction methods were shown to enhance the identification of the different scene classes.",
keywords = "acoustic scene, fusion, local binary patterns, time-frequency analysis, Feature extraction",
author = "Shamsiah Abidin",
year = "2019",
doi = "10.26182/5dd4b9db0cafb",
language = "English",
school = "The University of Western Australia",

}

Acoustic scene classification using time-frequency representations as texture images. / Abidin, Shamsiah.

2019.

Research output: ThesisDoctoral Thesis

TY - THES

T1 - Acoustic scene classification using time-frequency representations as texture images

AU - Abidin, Shamsiah

PY - 2019

Y1 - 2019

N2 - Acoustic scene classification (ASC) is important for context-aware applications to recognise the environment based on the available acoustic information. Despite its promising application prospects, ASC is a challenging problem due to both the similar characteristics of some scenes and complexity of sounds present in other scenes. This dissertation presents findings in the field of ASC utilising hand-crafted visually inspired features extracted from a 2D time-frequency image representation. The time-­frequency visual representations of the temporal and spectral structures for each acoustic scene with suitable feature extraction methods were shown to enhance the identification of the different scene classes.

AB - Acoustic scene classification (ASC) is important for context-aware applications to recognise the environment based on the available acoustic information. Despite its promising application prospects, ASC is a challenging problem due to both the similar characteristics of some scenes and complexity of sounds present in other scenes. This dissertation presents findings in the field of ASC utilising hand-crafted visually inspired features extracted from a 2D time-frequency image representation. The time-­frequency visual representations of the temporal and spectral structures for each acoustic scene with suitable feature extraction methods were shown to enhance the identification of the different scene classes.

KW - acoustic scene

KW - fusion

KW - local binary patterns

KW - time-frequency analysis

KW - Feature extraction

U2 - 10.26182/5dd4b9db0cafb

DO - 10.26182/5dd4b9db0cafb

M3 - Doctoral Thesis

ER -