Multi-source neural networks for speech recognition.
Roberto GemelloDario AlbesanoFranco ManaPublished in: IJCNN (1999)
Keyphrases
- data model
- speech recognition
- multi source
- data integration
- neural network
- data sources
- pattern recognition
- information fusion
- hidden markov models
- databases
- data fusion
- speech synthesis
- database systems
- language model
- automatic speech recognition
- speech processing
- speech recognition technology
- speech signal
- speech recognition systems
- fuzzy logic
- artificial neural networks
- speaker independent
- multiple sources
- speech recognizer
- speaker identification
- feature extraction
- information integration
- data sets
- speech recognizers
- noisy environments
- information retrieval
- genetic algorithm
- machine learning
- speaker dependent
- soft computing