Paper Review/Generative models
2024. 11. 1.
[Paper Review] WAVENET: A GENERATIVE MODEL FOR RAW AUDIO 2016 arXiv
WAVENET: A GENERATIVE MODEL FOR RAW AUDIO 목차AbstractIntroduction WaveNet Dilated Causal Convolutions Softmax distributions Gated Activation Units Conditional WavenetsExperiments 다중 화자 음성 생성 TTS : 텍스트-음성 변환 음악 오디오 모델링Speech RecognitionConclusion Abstractraw audio waveforms 생성을 위한 deep neural networkfully probabilisticautoregressive⇒ 각 오디오 샘플의 예측 분포는 이전 모든 샘플에 조건화가 된다그럼에도 초..
![[Paper Review] WAVENET: A GENERATIVE MODEL FOR RAW AUDIO 2016 arXiv](http://i1.daumcdn.net/thumb/C480x320/?fname=https://blog.kakaocdn.net/dn/VRfL8/btsKtsYK2oQ/KPJEmXkKuKLGJK2yylp3Mk/img.png)