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: APSIPA ASC (2021)
Keyphrases
- speaker independent
- speech recognition
- hidden markov models
- speaker dependent
- speaker identification
- speech recognizer
- digit recognition
- acoustic models
- speech signal
- speech synthesis
- automatic speech recognition
- speech recognition systems
- language model
- speaker adaptation
- emotion classification
- pattern recognition
- spoken language
- noisy environments
- language independent
- hand written
- broadcast news
- vocal tract
- speaker recognition
- cross lingual
- em algorithm
- probabilistic model
- information retrieval