Speaker Adaptive Training Localizing Speaker Modules in DNN for Hybrid DNN-HMM Speech Recognizers.
Tsubasa OchiaiShigeki MatsudaHideyuki WatanabeXugang LuChiori HoriHisashi KawaiShigeru KatagiriPublished in: IEICE Trans. Inf. Syst. (2016)
Keyphrases
- speech recognition
- speech recognizers
- automatic speech recognition
- training process
- speech recognizer
- hidden markov models
- acoustic models
- speaker adaptation
- audio visual
- speech signal
- training data
- speaker identification
- language model
- speaker independent
- pattern recognition
- neural network
- multi modal
- knowledge representation