Audio Classification in Speech and Music: A Comparison between a Statistical and a Neural Approach.
Alessandro BugattiAlessandra FlamminiPierangelo MiglioratiPublished in: EURASIP J. Adv. Signal Process. (2002)
Keyphrases
- speech music discrimination
- audio signals
- audio features
- music genre classification
- audio visual
- gaussian mixture model
- genre classification
- digital audio
- statistical analysis
- classification accuracy
- classification scheme
- audio recordings
- support vector machine svm
- classification algorithm
- image classification
- speech corpus
- pattern recognition
- text to speech
- music retrieval
- feature selection
- audio stream
- music score
- acoustic signals
- multimedia
- decision trees
- support vector
- training set
- text classification
- speaker identification
- machine learning
- feature set
- acoustic features
- speech processing
- broadcast news
- mel frequency cepstral coefficients
- feature vectors
- emotion recognition
- network architecture
- supervised learning
- speech recognition
- maximum entropy modeling
- cepstral features
- multi modal