Two-Stream Joint-Training for Speaker Independent Acoustic-to-Articulatory Inversion.
Jianrong WangJinyu LiuXuewei LiMei YuJie GaoQiang FangLi LiuPublished in: ICASSP (2023)
Keyphrases
- speech recognition
- speaker independent
- acoustic models
- hidden markov models
- speaker dependent
- speech recognition systems
- language model
- speaker identification
- multi stream
- speech recognizer
- automatic speech recognition
- pattern recognition
- speaker adaptation
- digit recognition
- speech synthesis
- speech signal
- discriminative training
- training process
- vocal tract
- speaker recognition
- training set
- machine learning