Multi-resolution linear prediction based features for audio onset detection with bidirectional LSTM neural networks.
Erik MarchiGiacomo FerroniFlorian EybenLeonardo GabrielliStefano SquartiniBjörn W. SchullerPublished in: ICASSP (2014)
Keyphrases
- linear prediction
- neural network
- multiresolution
- color texture segmentation
- feature extraction
- recurrent neural networks
- multimedia
- image coding
- feature set
- pattern recognition
- gray level
- prediction error
- cepstral coefficients
- image compression
- speech recognition
- feature vectors
- artificial neural networks
- speech signal
- audio features
- high quality