# MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation

arXiv: https://arxiv.org/abs/1802.00300 · HTML: https://mlsanity.com/paper/1802.00300/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Feb 2018.

## Built on by (most cited first, 6 of 6)

- [Real-time Low-latency Music Source Separation using Hybrid Spectrogram-TasNet](https://mlsanity.com/paper/2402.17701/) (2024)
- [Listen, Read, and Identify: Multimodal Singing Language Identification of Music](https://mlsanity.com/paper/2103.01893/) (2021)
- [DeepSRGM -- Sequence Classification and Ranking in Indian Classical Music with Deep Learning](https://mlsanity.com/paper/2402.10168/) (2024)
- [Carnatic Raga Identification System using Rigorous Time-Delay Neural Network](https://mlsanity.com/paper/2405.16000/) (2024)
- [The Costs of Reproducibility in Music Separation Research: a Replication of Band-Split RNN](https://mlsanity.com/paper/2603.09187/) (2026)
- [Automatic Contextual Audio Denoising](https://mlsanity.com/paper/2605.22262/) (2026)

## Abstract (arXiv)

Monaural singing voice separation task focuses on the prediction of the singing voice from a single channel music mixture signal. Current state of the art (SOTA) results in monaural singing voice separation are obtained with deep learning based methods. In this work we present a novel deep learning based method that learns long-term temporal patterns and structures of a musical piece. We build upon the recently proposed Masker-Denoiser (MaD) architecture and we enhance it with the Twin Networks, a technique to regularize a recurrent generative network using a backward running copy of the network. We evaluate our method using the Demixing Secret Dataset and we obtain an increment to signal-to-distortion ratio (SDR) of 0.37 dB and to signal-to-interference ratio (SIR) of 0.23 dB, compared to previous SOTA results.