Spectrograms Fusion-based End-to-end Robust Automatic Speech Recognition.
Hao ShiLongbiao WangSheng LiCunhang FanJianwu DangTatsuya KawaharaPublished in: APSIPA ASC (2021)
Keyphrases
- end to end
- automatic speech recognition
- speech signal
- speech recognition
- noisy environments
- admission control
- speech retrieval
- conversational speech
- congestion control
- text localization and recognition
- word error rate
- wireless ad hoc networks
- hidden markov models
- application layer
- spontaneous speech
- transport layer
- word recognition
- spoken words
- recognition errors
- scalable video
- speech corpus
- acoustic features
- broadcast news
- face recognition
- language model
- pattern recognition