Graph based manifold regularized deep neural networks for automatic speech recognition.
Vikrant Singh TomarRichard C. RosePublished in: CoRR (2016)
Keyphrases
- automatic speech recognition
- neural network
- speech recognition
- speech signal
- pattern recognition
- hidden markov models
- word error rate
- broadcast news
- spoken words
- speech retrieval
- noisy environments
- conversational speech
- recognition errors
- word recognition
- low dimensional
- speech corpus
- semi supervised
- spontaneous speech
- high dimensional
- speaker adaptation
- speech recognizer
- question answering
- speech synthesis
- acoustic features
- maximum likelihood
- speech sounds
- multi modal