Deep Neural Networks-based Classification Methodologies of Speech, Audio and Music, and its Integration for Audio Metadata Tagging.
Hosung ParkYoonseo ChungJi-Hwan KimPublished in: J. Web Eng. (2023)
Keyphrases
- databases
- speech music discrimination
- metadata
- audio signals
- audio features
- audio content
- neural network
- music genre classification
- audio recordings
- automatic music genre classification
- pattern recognition
- digital audio
- audio stream
- music score
- multimedia
- music information retrieval
- gaussian mixture model
- genre classification
- audio visual
- feature set
- speech corpus
- audio signal
- speaker identification
- multimedia content
- music scores
- acoustic signals
- digital libraries
- classification accuracy
- emotion recognition
- feature extraction
- multi modal
- multi layer perceptron
- cepstral features
- acoustic features
- feature selection
- signal processing
- feature vectors
- feature space
- mel frequency cepstral coefficients
- image classification
- digital music
- musical instruments
- rule extraction
- statistical knowledge network
- music collections
- machine learning