Lattice based transcription loss for end-to-end speech recognition.
Jian KangWei-Qiang ZhangJia LiuPublished in: ISCSLP (2016)
Keyphrases
- end to end
- speech recognition
- speech recognition technology
- speech recognition systems
- handwriting recognition
- hidden markov models
- speech synthesis
- pattern recognition
- speech signal
- speech recognizer
- speech processing
- language model
- noisy environments
- speaker independent
- speaker dependent
- automatic speech recognition
- congestion control
- students with learning disabilities
- speech recognizers
- computer vision
- speaker diarization
- speaker identification
- image processing
- real world
- isolated word