Speech recognition with a new hybrid architecture combining neural networks and continuous HMM.
Daniel WillettGerhard RigollPublished in: ESANN (1998)
Keyphrases
- speech recognition
- neural network
- hidden markov models
- pattern recognition
- speech signal
- speech synthesis
- language model
- automatic speech recognition
- keyword spotting
- speech recognition systems
- speaker independent
- speech processing
- noisy environments
- speech recognizer
- speech understanding
- handwriting recognition
- speaker dependent
- isolated word recognition
- speaker identification
- speech recognition technology
- speech recognizers
- isolated word
- acoustic models
- feature selection
- speech recognition errors
- speech retrieval
- noisy speech
- machine learning