End-to-End Articulatory Attribute Modeling for Low-Resource Multilingual Speech Recognition.
Sheng LiChenchen DingXugang LuPeng ShenTatsuya KawaharaHisashi KawaiPublished in: INTERSPEECH (2019)
Keyphrases
- speech recognition
- end to end
- hidden markov models
- speech synthesis
- speech signal
- pattern recognition
- automatic speech recognition
- speech recognizer
- language model
- speech recognition technology
- speech processing
- speech recognition systems
- noisy environments
- speaker independent
- speaker identification
- congestion control
- speech recognizers
- multimedia
- speech retrieval
- isolated word