Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition.
Ye BaiJie LiWenjing HanHao NiKaituo XuZhuo ZhangCheng YiXiaorui WangPublished in: CoRR (2022)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- pattern recognition
- speech signal
- congestion control
- speech processing
- speech synthesis
- language model
- audio visual speech recognition
- speech recognition technology
- speech recognition systems
- speech recognizer
- noisy environments
- automatic speech recognition
- speaker identification
- speech retrieval
- speech recognizers
- speaker dependent
- computer vision
- text to speech
- word recognition
- neural network