# DTT-BSR+: A Generative-Regression Cascade for Music Source Restoration

arXiv: https://arxiv.org/abs/2606.24127 · HTML: https://mlsanity.com/paper/2606.24127/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Modeling with Gated Convolutional Networks](https://mlsanity.com/paper/1612.08083/) (2016)
- [Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram](https://mlsanity.com/paper/1910.11480/) (2019)
- [Hybrid Transformers for Music Source Separation](https://mlsanity.com/paper/2211.08553/) (2022)
- [Music Source Separation in the Waveform Domain](https://mlsanity.com/paper/1911.13254/) (2019)
- [Music Source Separation with Band-split RNN](https://mlsanity.com/paper/2209.15174/) (2022)
- [Music Source Separation with Band-Split RoPE Transformer](https://mlsanity.com/paper/2309.02612/) (2023)
- [Music Source Separation Based on a Lightweight Deep Learning Framework (DTTNET: DUAL-PATH TFC-TDF UNET)](https://mlsanity.com/paper/2309.08684/) (2023)
- [TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement](https://mlsanity.com/paper/2408.03440/) (2024)
- [Music Separation Enhancement with Generative Modeling](https://mlsanity.com/paper/2208.12387/) (2022)
- [Mel-RoFormer for Vocal Separation and Vocal Melody Transcription](https://mlsanity.com/paper/2409.04702/) (2024)
- [Zimtohrli: An Efficient Psychoacoustic Audio Similarity Metric](https://mlsanity.com/paper/2509.26133/) (2025)
- [Music Source Restoration](https://mlsanity.com/paper/2505.21827/) (2025)
- [MSRBench: A Benchmarking Dataset for Music Source Restoration](https://mlsanity.com/paper/2510.10995/) (2025)
- [Towards Practical Real-Time Low-Latency Music Source Separation](https://mlsanity.com/paper/2511.13146/) (2025)
- [Summary of The Inaugural Music Source Restoration Challenge](https://mlsanity.com/paper/2601.04343/) (2026)
- [The SJTU X-LANCE Lab System for MSR Challenge 2025](https://mlsanity.com/paper/2602.09042/) (2026)
- [DTT-BSR: GAN-based DTTNet with RoPE Transformer Enhancement for Music Source Restoration](https://mlsanity.com/paper/2602.19825/) (2026)

## Abstract (arXiv)

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 Fr'echet Audio Distance (FAD) decomposition an implicit trade-off between signal reconstruction accuracy and semantic distribution fitting across stems.