Low-Rank Adaptation of Large Language Models
LORA: LOW-RANK ADAPTATION OF LARGE LANGUAGE MODELS
Paper Reading
End-to-End Trainable Self-Attentive Shallow Network for Text-Independent Speaker Verification
Abstract
Speaker Embedding + Attention 조사
End-to-End Trainable Self-Attentive Shallow Network for Text-Independent Speaker Verification - 2020 [Link]
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
🗣 **overall** 표현력 향상을 위해 conditional prior 분포, 적대적 학습 과정에 normalizing flow 추가 text에 대한 다양한 one-to-many 관계를 표현할 수 있는 stochastic duration predictor 사용 Latent ...