Keyphrases
Sound Events
41%
Audio Captioning
40%
Crowdsourcing
39%
Sound Event Detection
38%
Annotator
33%
Strong Labels
27%
Acoustic Scene Classification
27%
Log Loss
22%
Weak Labels
20%
Captioning System
20%
Audio
19%
Audio Content
16%
Reference Annotation
15%
Multi-device
13%
Residual Block
13%
Audio Classification
13%
Envelope Estimation
13%
Multiply-accumulate
13%
Crowdsourced Annotations
13%
Large Amount of Data
13%
Audio Analysis
13%
Comparative Analysis
13%
Multi-annotator Data
13%
Soft Labels
13%
Audio Tagging
13%
DCASE
13%
K Parameter
13%
Residual Analysis
13%
DCASE 2021
13%
Summarization Technique
13%
Acoustic Scene
13%
Semiotic Conceptualization
13%
Artificial Intelligence
13%
Text Production
13%
Soft Metric
13%
Urban Monitoring
13%
Data Label
13%
Clotho
13%
Paid Crowdsourcing
13%
Post-training Quantization
11%
Classification Task
11%
Audio Caption
11%
Soundscape
10%
Convolutional Neural Network
10%
Audio Tag
10%
Multiple Annotators
10%
Amplitude Envelope
9%
Fluency
9%
Content-based
9%
Target Sound
9%
Computer Science
Annotation
100%
Event Detection
58%
Convolutional Neural Network
49%
Classification Task
40%
Training Data
35%
Residual Neural Network
18%
Linear Combination
13%
Text Summarization
13%
Syntactics
13%
Relevance Score
13%
Audio Classification
13%
Audio Analysis
13%
Machine Translation
13%
Image Captioning
13%
Comparative Analysis
13%
Real-World Problem
13%
Recording Device
13%
Vision Impairment
13%
Heterogeneous Data
13%
Data Type
13%
spam
13%
User Interface
13%
Mechanical Turk
13%
Complex Task
13%
Considerable Amount
13%
Image Classification
9%
Auxiliary Information
6%
Detection Result
6%
Textual Information
6%
Data Reliability
6%
Deep Learning Method
6%
Granularity
5%
