On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition.
Jinyu LiYu WuYashesh GaurChengyi WangRui ZhaoShujie LiuPublished in: CoRR (2020)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- acoustic models
- language model
- pattern recognition
- automatic speech recognition
- speech synthesis
- speech recognizer
- probabilistic model
- speech processing
- signal processing
- speech signal
- video sequences
- audio visual speech recognition
- isolated word
- speech retrieval
- speaker independent
- text localization and recognition
- speaker diarization
- speaker identification
- congestion control
- feature vectors