Cascaded CNN-resBiLSTM-CTC: An End-to-End Acoustic Model For Speech Recognition.
Xinpei ZhouJiwei LiXi ZhouPublished in: CoRR (2018)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- automatic speech recognition
- language model
- speech signal
- speech synthesis
- speech processing
- pattern recognition
- face detection
- speech recognition systems
- speech recognition technology
- speech retrieval
- congestion control
- noisy environments
- speaker independent
- speaker identification
- speech recognizer
- isolated word
- feature space
- speech recognizers
- real world
- image coding
- non stationary