[논문] FVTTS: Face Based Voice Synthesis for Text-to-Speech
https://www.isca-archive.org/interspeech_2024/lee24_interspeech.html ISCA Archive - FVTTS : Face Based Voice Synthesis for Text-to-SpeechFVTTS : Face Based Voice Synthesis for Text-to-Speech Minyoung Lee, Eunil Park, Sungeun Hong A face is expressive of individual identity and used in various studies such as identification, authentication, and personalization. Similarly, a voice is a meanswww.is..
연구실 공부
2024. 10. 28.