Abstract
This paper represents a framework for speech/music classification by using statistical neural networks. Zero crossing rate, root mean square power and spectral centroid were used as features. A dataset including 150 audio instances was labeled manually and 105 of them were used to train different networks, which are the probabilistic neural network (PNN), the generalised regression neural network (GRNN) and the radial basis functions (RBF). The remainder of the dataset was used as test item. Training and test performance of these three network types were discussed.
Keywords
Artificial neural network
Probabilistic neural network
Computer science
Artificial intelligence
Pattern recognition (psychology)
Probabilistic logic
Centroid
Statistical analysis
Speech recognition
Mathematics
Statistics
Time delay neural network
Subject Areas
Music and Audio Processing
·Signal Processing ·Physical Sciences
Speech and Audio Processing
·Signal Processing ·Physical Sciences
Speech Recognition and Synthesis
·Artificial Intelligence ·Physical Sciences
Loading…
Loading…