Simplifying very deep convolutional neural network architectures for robust speech recognition.
Joanna RownickaSteve RenalsPeter BellPublished in: ASRU (2017)
Keyphrases
- speech recognition
- noisy environments
- speech processing
- automatic speech recognition
- language model
- speech synthesis
- hidden markov models
- speech understanding
- pattern recognition
- speech recognizer
- speech recognition systems
- speaker identification
- speech signal
- deep learning
- handwriting recognition
- keyword spotting
- speaker dependent
- speech recognition technology
- speech retrieval
- speech recognizers
- information retrieval
- maximum likelihood
- cepstral coefficients