Prototype-based discriminative training for various speech units.
Erik McDermottShigeru KatagiriPublished in: ICASSP (1992)
Keyphrases
- discriminative training
- automatic speech recognition
- speech recognition
- hidden markov models
- probabilistic interpretation
- maximum likelihood
- speech signal
- acoustic models
- spelling correction
- posterior probability
- co training
- discriminatively trained
- support vector machine
- broadcast news
- text to speech
- speech recognizer
- language model
- co occurrence
- information retrieval
- machine learning