HiTNet: Byte-to-BPE Hierarchical Transcription Network for End-to-End Speech Recognition.
Dhananjaya GowdaAbhinav GargJiyeon KimMehul KumarSachin SinghAshutosh GuptaAnkur KumarNauman DawalatabadAman MaghanShatrughan SinghChanwoo KimPublished in: ASRU (2021)
Keyphrases
- end to end
- speech recognition
- speech recognition technology
- speech recognition systems
- congestion control
- handwriting recognition
- wireless ad hoc networks
- internet protocol
- hidden markov models
- speech processing
- speech synthesis
- automatic speech recognition
- noisy environments
- language model
- transport layer
- packet loss rate
- speech signal
- admission control
- speech recognizer
- differentiated services
- pattern recognition
- speaker identification
- peer to peer
- application layer
- students with learning disabilities
- ad hoc networks
- speaker diarization
- computer vision
- speaker dependent
- speaker independent
- wireless sensor networks
- neural network
- network traffic
- communication networks
- network layer
- scalable video