← Search

Wenzhong Yang

2 accepted papers

2025

A Singing Melody Extraction Network Via Self-Distillation and Multi-Level Supervision

ICASSP 2025accepted

Extracting singing melody from polyphonic music is an important topic in the field of music information retrieval. In this paper, we propose a singing melody extraction network consisting of five stacked multi-scale feature time-frequency aggregation (MF-TFA) modules. In the same network, deeper lay…

Cited by 0Source ↗Scholar ↗
2025

Enhancing Medical Dialogue Generation through Knowledge Refinement and Dynamic Prompt Adjustment

ACL 2025finding

Medical dialogue systems (MDS) have emerged as crucial online platforms for enabling multi-turn, context-aware conversations with patients. However, existing MDS often struggle to (1) identify relevant medical knowledge and (2) generate personalized, medically accurate responses. To address these ch…