Phoneme-to-Grapheme Conversion Based Large-Scale Pre-Training for End-to-End Automatic Speech Recognition.
Ryo MasumuraNaoki MakishimaMana IhoriAkihiko TakashimaTomohiro TanakaShota OrihashiPublished in: INTERSPEECH (2020)
Keyphrases
- end to end
- automatic speech recognition
- speech recognition
- hidden markov models
- word error rate
- speech signal
- acoustic models
- spoken words
- acoustic features
- broadcast news
- conversational speech
- admission control
- spontaneous speech
- noisy environments
- speech retrieval
- word recognition
- recognition errors
- phoneme recognition
- congestion control
- maximum likelihood
- speech corpus
- multimedia
- application layer
- real world
- handwriting recognition
- language model
- speaker adaptation