Next Article in Journal
Archaeoacoustic Examination of Lazarica Church
Next Article in Special Issue
Commissioning the Acoustical Performance of an Open Office Space Following the Latest Healthy Building Standard: A Case Study
Previous Article in Journal
Self Noise Reduction and Aerodynamics of Airfoils with Porous Trailing Edges
Open AccessArticle

An Enhanced Temporal Feature Integration Method for Environmental Sound Recognition

1
Department of Signal Processing and Acoustics, Aalto University, 02150 Otakaari 5, Espoo, Finland
2
School of Electrical and Computer Engineering, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece
3
Information Technologies Institute of Thessaloniki, 60361 Thessaloniki, Greece
4
School of Journalism and Mass Media Communication, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece
*
Author to whom correspondence should be addressed.
Acoustics 2019, 1(2), 410-422; https://doi.org/10.3390/acoustics1020023
Received: 30 December 2018 / Revised: 4 April 2019 / Accepted: 29 April 2019 / Published: 8 May 2019
(This article belongs to the Special Issue Indoor Soundscape: Integrating Sound, Experience and Architecture)
Temporal feature integration refers to a set of strategies attempting to capture the information conveyed in the temporal evolution of the signal. It has been extensively applied in the context of semantic audio showing performance improvements against the standard frame-based audio classification methods. This paper investigates the potential of an enhanced temporal feature integration method to classify environmental sounds. The proposed method utilizes newly introduced integration functions that capture the texture window shape in combination with standard functions like mean and standard deviation in a classification scheme of 10 environmental sound classes. The results obtained from three classification algorithms exhibit an increase in recognition accuracy against a standard temporal integration with simple statistics, which reveals the discriminative ability of the new metrics. View Full-Text
Keywords: environmental sound recognition; temporal feature integration; statistical feature integration; semantic audio analysis; audio classification environmental sound recognition; temporal feature integration; statistical feature integration; semantic audio analysis; audio classification
Show Figures

Figure 1

MDPI and ACS Style

Bountourakis, V.; Vrysis, L.; Konstantoudakis, K.; Vryzas, N. An Enhanced Temporal Feature Integration Method for Environmental Sound Recognition. Acoustics 2019, 1, 410-422.

Show more citation formats Show less citations formats

Article Access Map by Country/Region

1
Back to TopTop