Automatic organisation, segmentation, and filtering of user-generated audio content

Gonçalo Mordido; João Magalhães; Sofia Cavaco

doi:10.1109/MMSP.2017.8122276

Automatic organisation, segmentation, and filtering of user-generated audio content

Gonçalo Mordido, João Magalhães, Sofia Cavaco

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Using solely the information retrieved by audio fingerprinting techniques, we propose methods to treat a possibly large dataset of user-generated audio content, that (1) enable the grouping of several audio files that contain a common audio excerpt (i.e. are relative to the same event), and (2) give information about how those files are correlated in terms of time and quality inside each event. Furthermore, we use supervised learning to detect incorrect matches that may arise from the audio fingerprinting algorithm itself, whilst ensuring our model learns with previous predictions. All the presented methods were further validated by user-generated recordings of several different concerts manually crawled from YouTube.

Original language	English
Title of host publication	2017 IEEE 19th International Workshop on Multimedia Signal Processing, MMSP 2017
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1-6
Number of pages	6
Volume	2017-January
ISBN (Electronic)	9781509036493
DOIs	https://doi.org/10.1109/MMSP.2017.8122276
Publication status	Published - 27 Nov 2017
Event	19th IEEE International Workshop on Multimedia Signal Processing, MMSP 2017 - Luton, United Kingdom Duration: 16 Oct 2017 → 18 Oct 2017

Conference

Conference	19th IEEE International Workshop on Multimedia Signal Processing, MMSP 2017
Country/Territory	United Kingdom
City	Luton
Period	16/10/17 → 18/10/17

Keywords

Audio fingerprinting
Audio synchronisation
Supervised learning
User-generated content

Access to Document

10.1109/MMSP.2017.8122276

Cite this

@inproceedings{5f2a3d610b4d494f97dec77bc5ada692,

title = "Automatic organisation, segmentation, and filtering of user-generated audio content",

abstract = "Using solely the information retrieved by audio fingerprinting techniques, we propose methods to treat a possibly large dataset of user-generated audio content, that (1) enable the grouping of several audio files that contain a common audio excerpt (i.e. are relative to the same event), and (2) give information about how those files are correlated in terms of time and quality inside each event. Furthermore, we use supervised learning to detect incorrect matches that may arise from the audio fingerprinting algorithm itself, whilst ensuring our model learns with previous predictions. All the presented methods were further validated by user-generated recordings of several different concerts manually crawled from YouTube.",

keywords = "Audio fingerprinting, Audio synchronisation, Supervised learning, User-generated content",

author = "Gon{\c c}alo Mordido and Jo{\~a}o Magalh{\~a}es and Sofia Cavaco",

note = "Sem PDF.; 19th IEEE International Workshop on Multimedia Signal Processing, MMSP 2017 ; Conference date: 16-10-2017 Through 18-10-2017",

year = "2017",

month = nov,

day = "27",

doi = "10.1109/MMSP.2017.8122276",

language = "English",

volume = "2017-January",

pages = "1--6",

booktitle = "2017 IEEE 19th International Workshop on Multimedia Signal Processing, MMSP 2017",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

Mordido, G, Magalhães, J & Cavaco, S 2017, Automatic organisation, segmentation, and filtering of user-generated audio content. in 2017 IEEE 19th International Workshop on Multimedia Signal Processing, MMSP 2017. vol. 2017-January, Institute of Electrical and Electronics Engineers (IEEE), pp. 1-6, 19th IEEE International Workshop on Multimedia Signal Processing, MMSP 2017, Luton, United Kingdom, 16/10/17. https://doi.org/10.1109/MMSP.2017.8122276

Automatic organisation, segmentation, and filtering of user-generated audio content. / Mordido, Gonçalo; Magalhães, João ; Cavaco, Sofia.
2017 IEEE 19th International Workshop on Multimedia Signal Processing, MMSP 2017. Vol. 2017-January Institute of Electrical and Electronics Engineers (IEEE), 2017. p. 1-6.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Automatic organisation, segmentation, and filtering of user-generated audio content

AU - Mordido, Gonçalo

AU - Magalhães, João

AU - Cavaco, Sofia

N1 - Sem PDF.

PY - 2017/11/27

Y1 - 2017/11/27

N2 - Using solely the information retrieved by audio fingerprinting techniques, we propose methods to treat a possibly large dataset of user-generated audio content, that (1) enable the grouping of several audio files that contain a common audio excerpt (i.e. are relative to the same event), and (2) give information about how those files are correlated in terms of time and quality inside each event. Furthermore, we use supervised learning to detect incorrect matches that may arise from the audio fingerprinting algorithm itself, whilst ensuring our model learns with previous predictions. All the presented methods were further validated by user-generated recordings of several different concerts manually crawled from YouTube.

AB - Using solely the information retrieved by audio fingerprinting techniques, we propose methods to treat a possibly large dataset of user-generated audio content, that (1) enable the grouping of several audio files that contain a common audio excerpt (i.e. are relative to the same event), and (2) give information about how those files are correlated in terms of time and quality inside each event. Furthermore, we use supervised learning to detect incorrect matches that may arise from the audio fingerprinting algorithm itself, whilst ensuring our model learns with previous predictions. All the presented methods were further validated by user-generated recordings of several different concerts manually crawled from YouTube.

KW - Audio fingerprinting

KW - Audio synchronisation

KW - Supervised learning

KW - User-generated content

UR - http://www.scopus.com/inward/record.url?scp=85043516627&partnerID=8YFLogxK

U2 - 10.1109/MMSP.2017.8122276

DO - 10.1109/MMSP.2017.8122276

M3 - Conference contribution

AN - SCOPUS:85043516627

VL - 2017-January

SP - 1

EP - 6

BT - 2017 IEEE 19th International Workshop on Multimedia Signal Processing, MMSP 2017

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 19th IEEE International Workshop on Multimedia Signal Processing, MMSP 2017

Y2 - 16 October 2017 through 18 October 2017

ER -

Automatic organisation, segmentation, and filtering of user-generated audio content

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this