2011 8th International Conference on Information, Communications &Amp; Signal Processing 2011
DOI: 10.1109/icics.2011.6173513
|View full text |Cite
|
Sign up to set email alerts
|

Environmental sound classification using spectral dynamic features

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
10
0

Year Published

2013
2013
2024
2024

Publication Types

Select...
3
3
1

Relationship

0
7

Authors

Journals

citations
Cited by 19 publications
(18 citation statements)
references
References 9 publications
0
10
0
Order By: Relevance
“…On the on hand, most of the sound-based recognizers are limited in recognizing human speech, together with some of its characteristics like speaker recognition and his emotional state in order to obtain detailed information about their subject of interest. On the other hand, there are very few studies, which aim to examine in an abstract way the daily human activities in a home environment according to their acoustic characteristics [9,10,12,16,18,20,21]. Despite their generalized way of analyzing sounds, they are all developed in a healthcare perspective and often make the implication that certain sound implies certain activity, which is not necessarily true.…”
Section: Sound-based Activity Recognitionmentioning
confidence: 98%
“…On the on hand, most of the sound-based recognizers are limited in recognizing human speech, together with some of its characteristics like speaker recognition and his emotional state in order to obtain detailed information about their subject of interest. On the other hand, there are very few studies, which aim to examine in an abstract way the daily human activities in a home environment according to their acoustic characteristics [9,10,12,16,18,20,21]. Despite their generalized way of analyzing sounds, they are all developed in a healthcare perspective and often make the implication that certain sound implies certain activity, which is not necessarily true.…”
Section: Sound-based Activity Recognitionmentioning
confidence: 98%
“…, y N ] be a matrix with columns y i of feature vectors for N sub-frames. For each row of Y, the N-point FFT is applied followed by the logarithmic filter bank, and [25] that the combined features of MFCC and MFCC give the performance bound of static features, which is not improved by adding more conventional features. A system with a feature vector consisting of ZCR, Band-Energy, LPC, LPCC, MFCC, and MFCC, performs poorly as compared to that with only MFCC and MFCC under the SVM or GMM classifiers.…”
Section: I I S T a T I O N A R Y E S R T E C H N I Q U E Smentioning
confidence: 99%
“…Another example was recently proposed by Karbasi et al . [25], which attempted to capture the temporal variation among sub-frames in a new set of features called “Spectral Dynamic Features (SDF)” as detailed below.…”
Section: Stationary Esr Techniquesmentioning
confidence: 99%
“…One variation to exploit the temporal structure is when a signal-model is learned based on features from all ordered sub-frames such as HMM. Another example was recently proposed by Karbasi et al [14], which attempted to capture the temporal variation among sub-frames in a new set of features called "Spectral Dynamic Features (SDF)" as detailed below.…”
Section: Stationary Esr Techniquesmentioning
confidence: 99%
“…The superior performance of SDF against several conventional features such as ZCR, LPC, MFCC under three classifiers (i.e., KNN, GMM and SVM) was demonstrated. It was shown in [14] that the combined features of MFCC and ∆MFCC give the performance bound of static features, which is not improved by adding more conventional features. A system with a feature vector consisting of ZCR, Band-Energy, LPC, LPCC, MFCC and ∆MFCC, performs poorly as compared to that with only MFCC and ∆MFCC under the SVM or GMM classifiers.…”
Section: Stationary Esr Techniquesmentioning
confidence: 99%