SA-Paraformer: Non-autoregressive End-to-End Speaker-Attributed ASR.
Yangze LiFan YuYuhao LiangPengcheng GuoMohan ShiZhihao DuShiliang ZhangLei XiePublished in: CoRR (2023)
Keyphrases
- end to end
- autoregressive
- automatic speech recognition
- speech recognition
- simulated annealing
- non stationary
- speech signal
- gaussian markov random field
- hidden markov models
- moving average
- admission control
- random fields
- congestion control
- sar images
- noisy environments
- random field models
- spontaneous speech
- artificial neural networks
- application layer
- autoregressive moving average
- computer vision