End-to-end ASR to jointly predict transcriptions and linguistic annotations

21725

Knowledge Triples

Source Entity	Relationship	Target Entity
Automatic Speech Recognition Method	creates	Linguistic Annotations Material
English Dataset Material	evaluatedIn	Automatic Speech Recognition Method
Japanese Dataset Material	evaluatedIn	Automatic Speech Recognition Method
Linguistic Annotations Material	includes	Phonemic Transcripts OtherEntity
Linguistic Annotations Material	includes	POS Tags Material
Speech Interfaces OtherEntity	includes	Speech Translation Task
Speech Interfaces OtherEntity	includes	Spoken Dialogue Systems Task