2 papers
cs.SD2025
KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio Generation
Yoonjin Chung, Pilsun Eu, Junwon Lee +3
Although being widely adopted for evaluating generated audio signals, the Fréchet Audio Distance (FAD) suffers from significant limitations, including reliance on Gaussian assumpti…
cs.SD2024
Music Discovery Dialogue Generation Using Human Intent Analysis and Large Language Models
SeungHeon Doh, Keunwoo Choi, Daeyong Kwon +2
A conversational music retrieval system can help users discover music that matches their preferences through dialogue. To achieve this, a conversational music retrieval system shou…