SNDCNN: Self-Normalizing Deep CNNs with Scaled Exponential Linear Units for Speech Recognition.
Zhen HuangTim NgLeo LiuHenry MasonXiaodan ZhuangDaben LiuPublished in: ICASSP (2020)
Keyphrases
- digital video library
- speech recognition
- hidden markov models
- speech synthesis
- pattern recognition
- speech recognizer
- speech recognition technology
- automatic speech recognition
- speech processing
- language model
- speech retrieval
- speech signal
- speech recognition systems
- speaker identification
- handwriting recognition
- speech understanding
- face recognition
- noisy environments
- linear prediction
- speaker dependent
- non stationary
- bayesian networks
- speech recognizers
- feature extraction