Acoustic Scene Classification: A Competition Review

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gharib, Shayan, Derrar, Honain, Niizumi, Daisuke, Senttula, Tuukka, Tommola, Janne, Heittola, Toni, Virtanen, Tuomas, Huttunen, Heikki
Format: Preprint
Veröffentlicht: 2018
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913566221664256
author Gharib, Shayan
Derrar, Honain
Niizumi, Daisuke
Senttula, Tuukka
Tommola, Janne
Heittola, Toni
Virtanen, Tuomas
Huttunen, Heikki
author_facet Gharib, Shayan
Derrar, Honain
Niizumi, Daisuke
Senttula, Tuukka
Tommola, Janne
Heittola, Toni
Virtanen, Tuomas
Huttunen, Heikki
contents In this paper we study the problem of acoustic scene classification, i.e., categorization of audio sequences into mutually exclusive classes based on their spectral content. We describe the methods and results discovered during a competition organized in the context of a graduate machine learning course; both by the students and external participants. We identify the most suitable methods and study the impact of each by performing an ablation study of the mixture of approaches. We also compare the results with a neural network baseline, and show the improvement over that. Finally, we discuss the impact of using a competition as a part of a university course, and justify its importance in the curriculum based on student feedback.
format Preprint
id arxiv_https___arxiv_org_abs_1808_02357
institution arXiv
publishDate 2018
record_format arxiv
spellingShingle Acoustic Scene Classification: A Competition Review
Gharib, Shayan
Derrar, Honain
Niizumi, Daisuke
Senttula, Tuukka
Tommola, Janne
Heittola, Toni
Virtanen, Tuomas
Huttunen, Heikki
Audio and Speech Processing
Computer Vision and Pattern Recognition
Machine Learning
Sound
In this paper we study the problem of acoustic scene classification, i.e., categorization of audio sequences into mutually exclusive classes based on their spectral content. We describe the methods and results discovered during a competition organized in the context of a graduate machine learning course; both by the students and external participants. We identify the most suitable methods and study the impact of each by performing an ablation study of the mixture of approaches. We also compare the results with a neural network baseline, and show the improvement over that. Finally, we discuss the impact of using a competition as a part of a university course, and justify its importance in the curriculum based on student feedback.
title Acoustic Scene Classification: A Competition Review
topic Audio and Speech Processing
Computer Vision and Pattern Recognition
Machine Learning
Sound
url https://arxiv.org/abs/1808.02357