Exploring Lexicon-Free Modeling Units for End-to-End Korean and Korean-English Code-Switching Speech Recognition.
Jisung WangJihwan KimSangki KimYeha LeePublished in: INTERSPEECH (2020)
Keyphrases
- end to end
- speech recognition
- speech recognition technology
- speech synthesis
- hidden markov models
- speech processing
- language model
- machine translation system
- pattern recognition
- congestion control
- speech signal
- natural language
- automatic speech recognition
- isolated word
- noisy environments
- speech recognizer
- english text
- handwriting recognition
- text to speech
- machine translation
- speech recognition systems
- students with learning disabilities
- speaker identification
- machine learning
- query translation
- speaker dependent
- speech retrieval
- learning styles
- feature extraction