Speaker Independent and Multilingual/Mixlingual Speech-Driven Talking Head Generation Using Phonetic Posteriorgrams.
Huirong HuangZhiyong WuShiyin KangDongyang DaiJia JiaTianxiao FuDeyi TuoGuangzhi LeiPeng LiuDan SuDong YuHelen MengPublished in: CoRR (2020)
Keyphrases
- speaker independent
- speech recognition
- speaker identification
- hidden markov models
- speaker dependent
- speech recognizer
- acoustic models
- speech recognition systems
- digit recognition
- speech signal
- speaker adaptation
- speech synthesis
- automatic speech recognition
- language model
- broadcast news
- pattern recognition
- spoken language
- neural network
- noisy environments
- speaker recognition
- gaussian mixture model
- feature vectors
- feature selection