Abstract
With the proliferation of video platforms on the internet, the recording of musical performances by mobile devices has become commonplace. However, these recordings are often distorted by noise and reverberation, reducing the listening experience. To address this issue, we propose a music enhancement system based on the conformer architecture that has demonstrated outstanding performance in speech enhancement tasks. Our approach explores the attention mechanisms of the conformer and examines their performance to discover the best approach for the music enhancement task. Our experimental results show that our proposed model achieves state-of-the-art performance on single-stem music enhancement. Furthermore, our system can perform general music enhancement with multi-track mixtures, which has not been examined in previous work.