3 accepted papers
Integrating large language models (LLMs) into text-to-speech (TTS) systems has improved speech expressiveness, yet controllable emotional expression remains challenging. Existing approaches primarily rely on external conditioning or global activation steering, offering limited insight into how emoti…
Sentiment analysis of historical literature provides valuable insights for humanities research, yet remains challenging due to scarce annotations and limited generalization of models trained on modern texts. Prior work has primarily focused on two directions: using sentiment lexicons or leveraging l
Despite the popularity of Convolutional Neural Networks (CNN), the problem of uncertainty quantification (UQ) of CNN has been largely overlooked. Lack of efficient UQ tools severely limits the application of CNN in certain areas, such as medicine, where prediction uncertainty is critically important…