End-to-End Rich Transcription-Style Automatic Speech Recognition with Semi-Supervised Learning.
Tomohiro TanakaRyo MasumuraMana IhoriAkihiko TakashimaShota OrihashiNaoki MakishimaPublished in: CoRR (2021)
Keyphrases
- end to end
- semi supervised learning
- automatic speech recognition
- speech recognition
- semi supervised
- unlabeled data
- labeled data
- speech signal
- word error rate
- hidden markov models
- supervised learning
- handwriting recognition
- machine learning
- unsupervised learning
- semi supervised classification
- active learning
- label propagation
- broadcast news
- co training
- text categorization
- pattern recognition
- training data
- spontaneous speech
- neural network
- pairwise
- transfer learning
- non stationary
- labeled and unlabeled data
- real world