Advances on neural networks for speech and audio processing.
Rodrigo Capobianco GuidoJose Carlos PereiraJan Frans Willem SlaetsPublished in: Neurocomputing (2007)
Keyphrases
- neural network
- audio visual
- audio stream
- pattern recognition
- emotion recognition
- audio signals
- text to speech
- cepstral features
- speaker identification
- real time
- digital audio
- artificial intelligence
- multimedia
- multi layer
- multi modal
- broadcast news
- visual information
- speech recognition
- back propagation
- human language
- signal processing
- fuzzy logic
- audio features
- acoustic features
- recent advances
- self organizing maps
- audio recordings
- prosodic features
- speaker verification
- automatic transcription
- linear predictive coding
- automatic speech recognition
- neural nets
- learning algorithm
- data processing
- multilayer perceptron
- audio video
- speech synthesis
- artificial neural networks
- spoken language
- language acquisition
- recurrent neural networks