Machine Learning Algorithms for Environmental Sound Recognition: Towards Soundscape Semantics

Vasileios Bountourakis; Lazaros Vrysis; George V. Papanikolaou

doi:10.1145/2814895.2814905

Machine Learning Algorithms for Environmental Sound Recognition: Towards Soundscape Semantics

Vasileios Bountourakis, Lazaros Vrysis, George V. Papanikolaou

Not published at Aalto University

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

22 Citations (Scopus)

Abstract

This paper investigates methods aiming at the automatic recognition and classification of discrete environmental sounds, for the purpose of subsequently applying these methods to the recognition of soundscapes. Research in audio recognition has traditionally focused on the domains of speech and music. Comparatively little research has been done towards recognizing non-speech environmental sounds. For this reason, in this paper, we apply existing techniques that have been proved efficient in the other two domains. These techniques are comprehensively compared to determine the most appropriate one for addressing the problem of environmental sound recognition.

Original language	English
Title of host publication	Proceedings of the 10th Audio Mostly
Subtitle of host publication	A Conference on Interaction With Sound
Publisher	ACM
Number of pages	7
ISBN (Print)	9781450338967
DOIs	https://doi.org/10.1145/2814895.2814905
Publication status	Published - 2015
MoE publication type	A4 Article in a conference publication
Event	Audio Mostly Conference: A Conference on Interaction with Sound - Thessaloniki, Greece Duration: 7 Oct 2015 → 9 Oct 2015

Conference

Conference	Audio Mostly Conference
Country/Territory	Greece
City	Thessaloniki
Period	07/10/2015 → 09/10/2015

Access to Document

10.1145/2814895.2814905

Cite this

@inproceedings{f94209aa114d457e8fa58c10aa087da4,

title = "Machine Learning Algorithms for Environmental Sound Recognition: Towards Soundscape Semantics",

abstract = "This paper investigates methods aiming at the automatic recognition and classification of discrete environmental sounds, for the purpose of subsequently applying these methods to the recognition of soundscapes. Research in audio recognition has traditionally focused on the domains of speech and music. Comparatively little research has been done towards recognizing non-speech environmental sounds. For this reason, in this paper, we apply existing techniques that have been proved efficient in the other two domains. These techniques are comprehensively compared to determine the most appropriate one for addressing the problem of environmental sound recognition.",

author = "Vasileios Bountourakis and Lazaros Vrysis and Papanikolaou, {George V.}",

year = "2015",

doi = "10.1145/2814895.2814905",

language = "English",

isbn = "9781450338967",

booktitle = "Proceedings of the 10th Audio Mostly",

publisher = "ACM",

note = "Audio Mostly Conference : A Conference on Interaction with Sound ; Conference date: 07-10-2015 Through 09-10-2015",

}

Machine Learning Algorithms for Environmental Sound Recognition : Towards Soundscape Semantics. / Bountourakis, Vasileios; Vrysis, Lazaros; Papanikolaou, George V.

Proceedings of the 10th Audio Mostly: A Conference on Interaction With Sound. ACM, 2015. 5.

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

TY - GEN

T1 - Machine Learning Algorithms for Environmental Sound Recognition

T2 - Audio Mostly Conference

AU - Bountourakis, Vasileios

AU - Vrysis, Lazaros

AU - Papanikolaou, George V.

PY - 2015

Y1 - 2015

N2 - This paper investigates methods aiming at the automatic recognition and classification of discrete environmental sounds, for the purpose of subsequently applying these methods to the recognition of soundscapes. Research in audio recognition has traditionally focused on the domains of speech and music. Comparatively little research has been done towards recognizing non-speech environmental sounds. For this reason, in this paper, we apply existing techniques that have been proved efficient in the other two domains. These techniques are comprehensively compared to determine the most appropriate one for addressing the problem of environmental sound recognition.

AB - This paper investigates methods aiming at the automatic recognition and classification of discrete environmental sounds, for the purpose of subsequently applying these methods to the recognition of soundscapes. Research in audio recognition has traditionally focused on the domains of speech and music. Comparatively little research has been done towards recognizing non-speech environmental sounds. For this reason, in this paper, we apply existing techniques that have been proved efficient in the other two domains. These techniques are comprehensively compared to determine the most appropriate one for addressing the problem of environmental sound recognition.

U2 - 10.1145/2814895.2814905

DO - 10.1145/2814895.2814905

M3 - Conference contribution

SN - 9781450338967

BT - Proceedings of the 10th Audio Mostly

PB - ACM

Y2 - 7 October 2015 through 9 October 2015

ER -

Machine Learning Algorithms for Environmental Sound Recognition: Towards Soundscape Semantics

Abstract

Conference

Access to Document

Fingerprint

Cite this