paper-with-me

홈 › Papers

Hybrid Transformers for Music Source Separation

2022-11-15 · Simon Rouard, Francisco Massa, Alexandre Défossez

A natural question arising in Music Source Separation (MSS) is whether long range contextual information is useful, or whether local acoustic features are sufficient. In other fields, attention based Transformers have shown their ability to integrate information over long sequences. In this work, we introduce Hybrid Transformer Demucs (HT Demucs), an hybrid temporal/spectral bi-U-Net based on Hybrid Demucs, where the innermost layers are replaced by a cross-domain Transformer Encoder, using self-attention within one domain, and cross-attention across domains. While it performs poorly when trained only on MUSDB, we show that it outperforms Hybrid Demucs (trained on the same data) by 0.45 dB of SDR when using 800 extra training songs. Using sparse attention kernels to extend its receptive field, and per source fine-tuning, we achieve state-of-the-art results on MUSDB with extra training data, with 9.20 dB of SDR.

📄 PDF Abstract BibTeX arXiv:2211.08553

Code (2)

facebookresearch/demucs 공식 구현 pytorch
zhaozhipeng1997/demucs_ascend910_pytorch pytorch

Tasks

Music Source SeparationSpeech Enhancement

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Residual Connection 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Hybrid Y-Net Architecture for Singing Voice Separation

2023-03-05 · Rashen Fernando, Pamudu Ranasinghe, Udula Ranasinghe, Janaka Wijayakulasooriya 외

This research paper presents a novel deep learning-based neural network architecture, named Y-Net, for achieving music source separation. The proposed architecture performs end-to-end hybrid source separation by extracti…

Music Source Separation

Sanidha: A Studio Quality Multi-Modal Dataset for Carnatic Music

2025-01-12 · Venkatakrishnan Vaidyanathapuram Krishnan, Noel Alben, Anish Nair, Nathaniel Condit-Schultz

Music source separation demixes a piece of music into its individual sound sources (vocals, percussion, melodic instruments, etc.), a task with no simple mathematical solution. It requires deep learning methods involving…

Music Source Separation

Hybrid Spectrogram and Waveform Source Separation

2021-11-05 · Alexandre Défossez

Source separation models either work on the spectrogram or waveform domain. In this work, we show how to perform end-to-end hybrid source separation, letting the model decide which domain is best suited for each source, …

Music Source Separation

A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems

2024-06-26 · Karn N. Watcharasupat, Alexander Lerch

Despite significant recent progress across multiple subtasks of audio source separation, few music source separation systems support separation beyond the four-stem vocals, drums, bass, and other (VDBO) setup. Of the ver…

Audio Source SeparationDecoderInstrument RecognitionMusic Source Separation

Real-time Low-latency Music Source Separation using Hybrid Spectrogram-TasNet

2024-02-27 · Satvik Venkatesh, Arthur Benilov, Philip Coleman, Frederic Roskam

There have been significant advances in deep learning for music demixing in recent years. However, there has been little attention given to how these neural networks can be adapted for real-time low-latency applications,…

Music Source Separation