Acoustic scene classification: An overview of dcase 2017 challenge entries

Annamaria Mesaros; Toni Heittola; Tuomas Virtanen

doi:10.1109/IWAENC.2018.8521242

Acoustic scene classification: An overview of dcase 2017 challenge entries

Annamaria Mesaros, Toni Heittola, Tuomas Virtanen

Tutkimustuotos: Konferenssiartikkeli › Tieteellinen › vertaisarvioitu

58 Sitaatiot (Scopus)

21 Lataukset (Pure)

Abstrakti

We present an overview of the challenge entries for the Acoustic Scene Classification task of DCASE 2017 Challenge. Being the most popular task of the challenge, acoustic scene classification entries provide a wide variety of approaches for comparison, with a wide performance gap from top to bottom. Analysis of the submissions confirms once more the popularity of deep-learning approaches and mel frequency representations. Statistical analysis indicates that the top ranked system performed significantly better than the others, and that combinations of top systems are capable of reaching close to perfect performance on the given data.

Alkuperäiskieli	Englanti
Otsikko	16th International Workshop on Acoustic Signal Enhancement, IWAENC 2018
Kustantaja	IEEE
Sivut	411-415
Sivumäärä	5
ISBN (elektroninen)	9781538681510
DOI - pysyväislinkit	https://doi.org/10.1109/IWAENC.2018.8521242
Tila	Julkaistu - 2 marrask. 2018
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisussa
Tapahtuma	International Workshop on Acoustic Signal Enhancement - Tokyo, Japani Kesto: 17 syysk. 2018 → 20 syysk. 2018

Conference

Conference	International Workshop on Acoustic Signal Enhancement
Maa/Alue	Japani
Kaupunki	Tokyo
Ajanjakso	17/09/18 → 20/09/18

Julkaisufoorumi-taso

Jufo-taso 1

!!ASJC Scopus subject areas

Signal Processing
Acoustics and Ultrasonics

Pääsy asiakirjaan

10.1109/IWAENC.2018.8521242

mesaros-iwaenc2018-asc-in-dcase2017
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Accepted author manuscript, 474 KB

http://urn.fi/URN:NBN:fi:tuni-202105104705

Siteeraa tätä

@inproceedings{61fd5e524f844e37a1f82ea09e0c1d12,

title = "Acoustic scene classification: An overview of dcase 2017 challenge entries",

abstract = "We present an overview of the challenge entries for the Acoustic Scene Classification task of DCASE 2017 Challenge. Being the most popular task of the challenge, acoustic scene classification entries provide a wide variety of approaches for comparison, with a wide performance gap from top to bottom. Analysis of the submissions confirms once more the popularity of deep-learning approaches and mel frequency representations. Statistical analysis indicates that the top ranked system performed significantly better than the others, and that combinations of top systems are capable of reaching close to perfect performance on the given data.",

keywords = "Acoustic scene classification, Audio classb ification, DCASE challenge",

author = "Annamaria Mesaros and Toni Heittola and Tuomas Virtanen",

year = "2018",

month = nov,

day = "2",

doi = "10.1109/IWAENC.2018.8521242",

language = "English",

pages = "411--415",

booktitle = "16th International Workshop on Acoustic Signal Enhancement, IWAENC 2018",

publisher = "IEEE",

address = "United States",

note = "International Workshop on Acoustic Signal Enhancement ; Conference date: 17-09-2018 Through 20-09-2018",

}

TY - GEN

T1 - Acoustic scene classification

T2 - International Workshop on Acoustic Signal Enhancement

AU - Mesaros, Annamaria

AU - Heittola, Toni

AU - Virtanen, Tuomas

PY - 2018/11/2

Y1 - 2018/11/2

N2 - We present an overview of the challenge entries for the Acoustic Scene Classification task of DCASE 2017 Challenge. Being the most popular task of the challenge, acoustic scene classification entries provide a wide variety of approaches for comparison, with a wide performance gap from top to bottom. Analysis of the submissions confirms once more the popularity of deep-learning approaches and mel frequency representations. Statistical analysis indicates that the top ranked system performed significantly better than the others, and that combinations of top systems are capable of reaching close to perfect performance on the given data.

AB - We present an overview of the challenge entries for the Acoustic Scene Classification task of DCASE 2017 Challenge. Being the most popular task of the challenge, acoustic scene classification entries provide a wide variety of approaches for comparison, with a wide performance gap from top to bottom. Analysis of the submissions confirms once more the popularity of deep-learning approaches and mel frequency representations. Statistical analysis indicates that the top ranked system performed significantly better than the others, and that combinations of top systems are capable of reaching close to perfect performance on the given data.

KW - Acoustic scene classification

KW - Audio classb ification

KW - DCASE challenge

U2 - 10.1109/IWAENC.2018.8521242

DO - 10.1109/IWAENC.2018.8521242

M3 - Conference contribution

AN - SCOPUS:85057432865

SP - 411

EP - 415

BT - 16th International Workshop on Acoustic Signal Enhancement, IWAENC 2018

PB - IEEE

Y2 - 17 September 2018 through 20 September 2018

ER -

Acoustic scene classification: An overview of dcase 2017 challenge entries

Abstrakti

Conference

Julkaisufoorumi-taso

!!ASJC Scopus subject areas

Pääsy asiakirjaan

Sormenjälki

Siteeraa tätä