Towards single pass discriminative training for speech recognition.
Roger HsiaoTanja SchultzPublished in: ICASSP (2012)
Keyphrases
- single pass
- discriminative training
- speech recognition
- automatic speech recognition
- hidden markov models
- speech signal
- speech synthesis
- speech recognition technology
- speech recognizer
- maximum likelihood
- probabilistic interpretation
- language model
- broadcast news
- acoustic models
- pattern recognition
- posterior probability
- support vector machine
- speech recognition systems
- speaker adaptation
- neural network
- denoising
- probability distribution
- training data
- computer vision
- information retrieval