Time–frequency audio feature extraction based on tensor representation of sparse coding

A time–frequency audio feature extraction scheme is proposed, in which features are decomposed from a frequency–time–scale tensor. The tensor, derived from a weight vector and a Gabor dictionary in sparse coding, represents the frequency, time centre and scale of transient time–frequency components...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Electronics letters Ročník 51; číslo 2; s. 131 - 132
Hlavní autori: Zhang, Xue-Yuan, He, Qian-Hua
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: The Institution of Engineering and Technology 22.01.2015
Predmet:
Acoustical engineering
audio coding
Classification
Coding
Dictionaries
Feature extraction
frequency time scale tensor
Gabor atoms
Gabor dictionary
Mathematical analysis
Sound effects
sound effects classification
sparse coding features
tensor element values
tensor representation
Tensors
time frequency audio feature extraction scheme
transient time frequency components
Vectors (mathematics)
transient time frequency components
feature extraction
tensor representation
sparse coding features
Gabor atoms
tensor element values
frequency time scale tensor
sound effects classification
Gabor dictionary
time frequency audio feature extraction scheme
audio coding
ISSN:0013-5194, 1350-911X, 1350-911X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:A time–frequency audio feature extraction scheme is proposed, in which features are decomposed from a frequency–time–scale tensor. The tensor, derived from a weight vector and a Gabor dictionary in sparse coding, represents the frequency, time centre and scale of transient time–frequency components with different dimensions. The distinguishing Gabor atoms are represented by individual tensor elements, and their associated coding weights are represented by tensor element values. The experimental results of sound effects classification showed performance improvement against that of sparse coding features.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0013-5194
1350-911X
1350-911X
DOI:10.1049/el.2014.3333