Far-field speech recognition using CNN-DNN-HMM with convolution in time.
Takuya YoshiokaShigeki KaritaTomohiro NakataniPublished in: ICASSP (2015)
Keyphrases
- speech recognition
- hidden markov models
- speech signal
- multi stream
- automatic speech recognition systems
- automatic speech recognition
- cellular neural networks
- keyword spotting
- phoneme recognition
- recognition engine
- speaker independent
- speech synthesis
- speaker adaptation
- audio visual
- pattern recognition
- speech recognizer
- language model
- training process
- noisy speech
- image processing
- speech processing
- speaker identification
- handwritten word recognition
- speaker recognition
- convolutional neural network
- acoustic features
- finite state transducers
- speech recognition systems
- mesh connected
- convolution kernel
- broadcast news
- information retrieval
- neural network
- speech enhancement
- handwriting recognition
- noisy environments
- endpoint detection