Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks.
Ying ZhangMohammad PezeshkiPhilemon BrakelSaizheng ZhangCésar LaurentYoshua BengioAaron C. CourvillePublished in: CoRR (2017)
Keyphrases
- end to end
- speech recognition
- convolutional neural networks
- hidden markov models
- speech processing
- speech signal
- automatic speech recognition
- language model
- pattern recognition
- speech synthesis
- speech recognizer
- noisy environments
- congestion control
- speech recognition technology
- speech recognition systems
- video sequences
- speaker identification
- speaker dependent
- real world
- speech retrieval
- text localization and recognition
- speaker independent
- maximum likelihood
- multiscale
- machine learning