Gated Recurrent Context: Softmax-Free Attention for Online Encoder-Decoder Speech Recognition.
Hyeonseung LeeWoo Hyun KangSung Jun CheonHyeongju KimNam Soo KimPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2021)
Keyphrases
- speech recognition
- hidden markov models
- automatic speech recognition
- language model
- speech processing
- speech signal
- pattern recognition
- speech synthesis
- speech recognizer
- low complexity
- speech recognition technology
- speaker identification
- distributed video coding
- decoding process
- video codec
- speech recognition systems
- motion estimation
- noisy environments
- speaker independent
- speech recognition errors
- speech recognizers
- image processing
- bit rate
- error control
- image coding
- speaker dependent
- feature extraction
- machine learning
- audio visual speech recognition