Music Source Separation Based on a Lightweight Deep Learning Framework (DTTNET: DUAL-PATH TFC-TDF UNET)
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910372392337408 |
|---|---|
| author | Chen, Junyu Vekkot, Susmitha Shukla, Pancham |
| author_facet | Chen, Junyu Vekkot, Susmitha Shukla, Pancham |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_08684 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Music Source Separation Based on a Lightweight Deep Learning Framework (DTTNET: DUAL-PATH TFC-TDF UNET) Chen, Junyu Vekkot, Susmitha Shukla, Pancham Audio and Speech Processing Sound 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. |
| title | Music Source Separation Based on a Lightweight Deep Learning Framework (DTTNET: DUAL-PATH TFC-TDF UNET) |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2309.08684 |