Batch-normalized joint training for DNN-based distant speech recognition.
Mirco RavanelliPhilemon BrakelMaurizio OmologoYoshua BengioPublished in: SLT (2016)
Keyphrases
- speech recognition
- wall street journal corpus
- training process
- isolated word
- language model
- acoustic models
- hidden markov models
- speech signal
- speech processing
- automatic speech recognition
- pattern recognition
- speech synthesis
- speech recognizer
- noisy environments
- speech recognition technology
- speech understanding
- speaker independent
- speech recognition systems
- speaker identification
- training set
- keyword spotting
- speech recognition errors
- training data
- neural network
- speaker adaptation
- speaker dependent
- speech retrieval
- speech recognizers
- audio visual speech recognition
- digital video library