{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/music-source-separation-based-on-a","title":"Music Source Separation Based on a Lightweight Deep Learning Framework (DTTNET: DUAL-PATH TFC-TDF UNET)","arxiv_id":"2309.08684","date":"2023-09-15","proceeding":null,"authors":["Junyu Chen","Susmitha Vekkot","Pancham Shukla"],"abstract":"Music source separation (MSS) aims to extract 'vocals', 'drums', 'bass' and 'other' tracks from a piece of mixed music. While deep learning methods have shown impressive results, there is a trend toward larger models. In our paper, we introduce a novel and lightweight architecture called DTTNet, which is based on Dual-Path Module and Time-Frequency Convolutions Time-Distributed Fully-connected UNet (TFC-TDF UNet). DTTNet achieves 10.12 dB cSDR on 'vocals' compared to 10.01 dB reported for Bandsplit RNN (BSRNN) but with 86.7% fewer parameters. We also assess pattern-specific performance and model generalization for intricate audio patterns.","url_abs":"https://arxiv.org/abs/2309.08684v2","url_pdf":"https://arxiv.org/pdf/2309.08684v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"music-source-separation-based-on-a","repo_url":"https://github.com/junyuchen-cjy/dttnet-pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"music-source-separation-based-on-a","repo_url":"https://github.com/FaceOnLive/Spleeter-Android-iOS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"music-source-separation","task_name":"Music Source Separation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/music-source-separation-on-musdb18-hq","task":"Music Source Separation","dataset":"MUSDB18-HQ","model":"Dual-Path TFC-TDF UNet (DTTNet)","rank_in_archive_order":10,"of":14,"metrics":{"SDR (avg)":"8.15","SDR (bass)":"7.55","SDR (drums)":"7.82","SDR (others)":"7.02","SDR (vocals)":"10.21"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}