Keyphrases
Acoustic Scene
40%
Acoustic Scene Classification
66%
Audio Classification
66%
Audio Recording
13%
Cepstral Coefficients
13%
Class-incremental Learning
66%
Classification System
13%
Classification Task
80%
Convolutional Neural Network
13%
Cosine Similarity
33%
DCASE
53%
Distillation Loss
66%
Encoder
26%
F1 Score
66%
Feature Extraction
13%
Feature Reduction
13%
Feature Representation
33%
Feature Vector
13%
Fisher Layer
26%
Fisher Network
66%
Fisher Vector
66%
Five-phase
33%
Gammatone
13%
Kullback-Leibler Divergence
33%
Mel-spectrogram
13%
Multi-label Classification
33%
Normalization Layer
13%
Overall Classification Accuracy
13%
Overlapping Sound
33%
Performance Degradation
33%
Phase Range
33%
Principal Coordinate Analysis (PCoA)
26%
Semantic Label
13%
Similarity-based
33%
Succeeding
13%
Surrounding Environment
13%
Temporal Normalization
13%
Temporal Pyramid
53%
Urban Acoustics
40%
Vector Representation
13%
Working Mechanism
13%
Engineering
Audio Label
66%
Audio Recording
33%
Classification Accuracy
33%
Classification Task
100%
Component Analysis
66%
Convolutional Neural Network
33%
Feature Extraction
33%
Feature Vector
33%
Feedforward
33%
Initial Classification
33%
Kullback-Leibler Divergence
33%
Performance Degradation
33%
Principal Components
66%
Representation Vector
33%
Similarities
33%
Spectrogram
33%
Surrounding Environment
33%
Temporal Information
33%
Computer Science
Audio Classification
66%
Audio Recording
13%
Average Performance
33%
Base Class
33%
Cepstral Coefficient
13%
Class-Incremental Learning
66%
Classification Accuracy
13%
Classification Task
80%
Component Analysis
26%
Convolutional Neural Network
13%
Cosine Similarity
33%
Feature Extraction
13%
Feature Reduction
13%
Feature Vector
13%
Fisher Vector
66%
Leibler Divergence
33%
Normalization Layer
13%
Performance Degradation
33%
Principal Components
26%
Semantic Label
13%
Surrounding Environment
13%
Temporal Information
13%
