Deep neural network-based speech recognition with combination of speaker-class models.
Tetsuo KosakaKazuki Kon'noMasaharu KatoPublished in: APSIPA (2015)
Keyphrases
- speech recognition
- acoustic models
- automatic speech recognition
- hidden markov models
- pattern recognition
- language model
- speech recognizer
- speech signal
- speaker identification
- speech understanding
- speech processing
- noisy environments
- speaker independent
- speech synthesis
- speaker dependent
- speech recognizers
- speaker diarization
- probabilistic model
- keyword spotting
- speech recognition systems
- isolated word
- neural network
- speech recognition technology
- audio visual speech recognition
- speech retrieval
- digit recognition
- model selection
- image processing
- data mining