Intermediate-layer output Regularization for Attention-based Speech Recognition with Shared Decoder.
Jicheng ZhangYizhou PengHaihua XuYi HeEng Siong ChngHao HuangPublished in: CoRR (2022)
Keyphrases
- speech recognition
- hidden markov models
- language model
- speech signal
- automatic speech recognition
- speech recognizer
- noisy environments
- speech synthesis
- speech recognition systems
- pattern recognition
- speech understanding
- speaker independent
- speech recognition technology
- speaker identification
- motion estimation
- keyword spotting
- speech processing
- background noise
- isolated word
- video sequences
- neural network
- speech recognizers
- audio visual speech recognition
- speaker diarization
- speaker recognition
- signal processing
- information retrieval