수신된 패킷만을 활용해 기존 패킷 손실 복구(PLC) 모델을 테스트 시점에 자기지도(self-supervised) 방식으로 적응시키는 TTT-PLC 프레임워크를 제안하며, 수신 패킷의 일부를 합성적으로 마스킹해 생성한 보조 PLC 태스크로 모델을 파인튜닝한 뒤 실제 손실 패킷 복구에 활용한다. 비인과적(non-causal) 및 인과적(causal) 스트리밍 환경 모두에서 FRN과 PARCnet 백본에 적용한 실험 결과, 추가 학습 데이터나 클린 레퍼런스 없이도 사전학습된 PLC 시스템의 성능을 향상시킬 수 있음을 보였다.
Music source restoration (MSR) requires jointly addressing source unmixing and the inversion of non-linear production effects. Current methods struggle to achieve accurate target signal reconstruction while maintaining semantic consistency. To address this limitation, we propose DTT-BSR+, a two-stage cascade MSR system that decouples distribution fitting from signal reconstruction into separate stages. A generative DTT-BSR separator in the first stage produces stems matching the prior of clean sources, and a modified Demucs network in the second stage enhances the first stage output using time-domain and multi-resolution spectral losses. DTT-BSR+ improves multi-mel signal-to-noise ratio (MMSNR) over the single-stage DTT-BSR across all stems, and surpasses the state-of-the-art X-LANCE MSR system on five stems. We also reveal through Fréchet Audio Distance (FAD) decomposition an implicit trade-off between signal reconstruction accuracy and semantic distribution fitting across stems.