An Improved Speech / Nonspeech Classification Based on Feature Combination for Audio Indexing.
Ji-Soo KeumHyon-Soo LeeMasafumi HagiwaraPublished in: IEICE Trans. Fundam. Electron. Commun. Comput. Sci. (2010)
Keyphrases
- feature set
- feature vectors
- cepstral features
- acoustic signals
- speech music discrimination
- feature extraction
- audio features
- classification accuracy
- audio visual
- text classification
- support vector machine
- image classification
- support vector machine svm
- decision trees
- audio stream
- feature selection
- image features
- spectral features
- emotion recognition
- classification scheme
- machine learning
- classification algorithm
- feature space
- speaker identification
- multiple classifier systems
- text to speech
- audio signals
- acoustic signal
- support vector
- audio visual content