Automatic Instrument and Environmental Sound Recognition for Media Annotation of TV Content

Sofia Carmen Faria Maia Cavaco; Nuno Manuel Robalo Correia

doi:10.1109/ICALIP.2012.6376785

Automatic Instrument and Environmental Sound Recognition for Media Annotation of TV Content

Sofia Carmen Faria Maia Cavaco, Nuno Manuel Robalo Correia

DI - Departamento de Informática

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

2 Citations (Scopus)

Abstract

Due to the lack of annotation of their large videoarchives, multimedia content provider companies andtelevision channels do not use the data in their archivesto their full extent. In order to contribute with a solutionto this problem, we have developed a tool that combinesaudio and visual information to annotate video.In particular, this tool has been used by a video productioncompany that has given us positive feedback. Themain innovation of this tool is the use of environmentalsound recognition to annotate video. Here we focus onthe tool's audio information extraction method, whichconsists of a sound recognizer that learns a small set ofspectral features from the data using non-negative matrixfactorization. The recognizer can be used for differentpurposes such as to classify musical instruments, toidentify the notes that are played and to distinguish environmentalsounds like water, traffic, trains and people.

Original language	Unknown
Title of host publication	Proceedings of the IEEE International Conference on Audio, Language and Image Processing
Pages	1125-1130
DOIs	https://doi.org/10.1109/ICALIP.2012.6376785
Publication status	Published - 1 Jan 2012
Event	IEEE International Conference on Audio, Language and Image Processing - Duration: 1 Jan 2012 → …

Conference

Conference	IEEE International Conference on Audio, Language and Image Processing
Period	1/01/12 → …

Access to Document

10.1109/ICALIP.2012.6376785

Cite this

@inproceedings{706cdde9cb6d4ce7a566220a918c8a04,

title = "Automatic Instrument and Environmental Sound Recognition for Media Annotation of TV Content",

abstract = "Due to the lack of annotation of their large videoarchives, multimedia content provider companies andtelevision channels do not use the data in their archivesto their full extent. In order to contribute with a solutionto this problem, we have developed a tool that combinesaudio and visual information to annotate video.In particular, this tool has been used by a video productioncompany that has given us positive feedback. Themain innovation of this tool is the use of environmentalsound recognition to annotate video. Here we focus onthe tool's audio information extraction method, whichconsists of a sound recognizer that learns a small set ofspectral features from the data using non-negative matrixfactorization. The recognizer can be used for differentpurposes such as to classify musical instruments, toidentify the notes that are played and to distinguish environmentalsounds like water, traffic, trains and people.",

author = "Cavaco, {Sofia Carmen Faria Maia} and Correia, {Nuno Manuel Robalo}",

year = "2012",

month = jan,

day = "1",

doi = "10.1109/ICALIP.2012.6376785",

language = "Unknown",

isbn = "978-1-4673-0173-2",

pages = "1125--1130",

booktitle = "Proceedings of the IEEE International Conference on Audio, Language and Image Processing",

note = "IEEE International Conference on Audio, Language and Image Processing ; Conference date: 01-01-2012",

}

Automatic Instrument and Environmental Sound Recognition for Media Annotation of TV Content. / Cavaco, Sofia Carmen Faria Maia ; Correia, Nuno Manuel Robalo.
Proceedings of the IEEE International Conference on Audio, Language and Image Processing. 2012. p. 1125-1130.

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

TY - GEN

T1 - Automatic Instrument and Environmental Sound Recognition for Media Annotation of TV Content

AU - Cavaco, Sofia Carmen Faria Maia

AU - Correia, Nuno Manuel Robalo

PY - 2012/1/1

Y1 - 2012/1/1

N2 - Due to the lack of annotation of their large videoarchives, multimedia content provider companies andtelevision channels do not use the data in their archivesto their full extent. In order to contribute with a solutionto this problem, we have developed a tool that combinesaudio and visual information to annotate video.In particular, this tool has been used by a video productioncompany that has given us positive feedback. Themain innovation of this tool is the use of environmentalsound recognition to annotate video. Here we focus onthe tool's audio information extraction method, whichconsists of a sound recognizer that learns a small set ofspectral features from the data using non-negative matrixfactorization. The recognizer can be used for differentpurposes such as to classify musical instruments, toidentify the notes that are played and to distinguish environmentalsounds like water, traffic, trains and people.

AB - Due to the lack of annotation of their large videoarchives, multimedia content provider companies andtelevision channels do not use the data in their archivesto their full extent. In order to contribute with a solutionto this problem, we have developed a tool that combinesaudio and visual information to annotate video.In particular, this tool has been used by a video productioncompany that has given us positive feedback. Themain innovation of this tool is the use of environmentalsound recognition to annotate video. Here we focus onthe tool's audio information extraction method, whichconsists of a sound recognizer that learns a small set ofspectral features from the data using non-negative matrixfactorization. The recognizer can be used for differentpurposes such as to classify musical instruments, toidentify the notes that are played and to distinguish environmentalsounds like water, traffic, trains and people.

U2 - 10.1109/ICALIP.2012.6376785

DO - 10.1109/ICALIP.2012.6376785

M3 - Conference contribution

SN - 978-1-4673-0173-2

SP - 1125

EP - 1130

BT - Proceedings of the IEEE International Conference on Audio, Language and Image Processing

T2 - IEEE International Conference on Audio, Language and Image Processing

Y2 - 1 January 2012

ER -