# A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation

arXiv: https://arxiv.org/abs/2309.02539 · HTML: https://mlsanity.com/paper/2309.02539/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 5 Sep 2023.

## Builds on (most cited first, 28 of 28)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [Deep clustering: Discriminative embeddings for segmentation and separation](https://mlsanity.com/paper/1508.04306/) (2015)
- [Attention is All You Need in Speech Separation](https://mlsanity.com/paper/2010.13154/) (2020)
- [Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation](https://mlsanity.com/paper/1910.06379/) (2019)
- [Equivariance Through Parameter-Sharing](https://mlsanity.com/paper/1702.08389/) (2017)
- [Hybrid Transformers for Music Source Separation](https://mlsanity.com/paper/2211.08553/) (2022)
- [Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation](https://mlsanity.com/paper/1806.03185/) (2018)
- [TasNet: time-domain audio separation network for real-time, single-channel speech separation](https://mlsanity.com/paper/1711.00541/) (2017)
- [Music Source Separation in the Waveform Domain](https://mlsanity.com/paper/1911.13254/) (2019)
- [Hybrid Spectrogram and Waveform Source Separation](https://mlsanity.com/paper/2111.03600/) (2021)
- [Music Source Separation with Band-split RNN](https://mlsanity.com/paper/2209.15174/) (2022)
- [TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation](https://mlsanity.com/paper/2211.12433/) (2022)
- [The 2018 Signal Separation Evaluation Campaign](https://mlsanity.com/paper/1804.06267/) (2018)
- [KUIELab-MDX-Net: A Two-Stream Neural Network for Music Demixing](https://mlsanity.com/paper/2111.12203/) (2021)
- [Densely connected multidilated convolutional networks for dense prediction tasks](https://mlsanity.com/paper/2011.11844/) (2020)
- [The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World Soundtracks](https://mlsanity.com/paper/2110.09958/) (2021)
- [On The Compensation Between Magnitude and Phase in Speech Separation](https://mlsanity.com/paper/2108.05470/) (2021)
- [A Simultaneous Denoising and Dereverberation Framework with Target Decoupling](https://mlsanity.com/paper/2106.12743/) (2021)
- [The Sound Demixing Challenge 2023 unicodex2013 Cinematic Demixing Track](https://mlsanity.com/paper/2308.06981/) (2023)
- [Learning to Denoise Historical Music](https://mlsanity.com/paper/2008.02027/) (2020)
- [DESNet: A Multi-channel Network for Simultaneous Speech Dereverberation, Enhancement and Separation](https://mlsanity.com/paper/2011.02131/) (2020)
- [End-to-End Complex-Valued Multidilated Convolutional Neural Network for Joint Acoustic Echo Cancellation and Noise Suppression](https://mlsanity.com/paper/2110.00745/) (2021)
- [Sampling Frequency Independent Dialogue Separation](https://mlsanity.com/paper/2206.02124/) (2022)
- [Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks](https://mlsanity.com/paper/2212.07327/) (2022)
- [Multi-path RNN for hierarchical modeling of long sequential data and its application to speaker stream separation](https://mlsanity.com/paper/2006.13579/) (2020)
- [Egocentric Audio-Visual Noise Suppression](https://mlsanity.com/paper/2211.03643/) (2022)

## Built on by (most cited first, 8 of 8)

- [A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems](https://mlsanity.com/paper/2406.18747/) (2024)
- [Remastering Divide and Remaster: A Cinematic Audio Source Separation Dataset with Multilingual Support](https://mlsanity.com/paper/2407.07275/) (2024)
- [Conditional Flow Matching for Visually-Guided Acoustic Highlighting](https://mlsanity.com/paper/2602.03762/) (2026)
- [Facing the Music: Tackling Singing Voice Separation in Cinematic Audio Source Separation](https://mlsanity.com/paper/2408.03588/) (2024)
- [ConcateNet: Dialogue Separation Using Local And Global Feature Concatenation](https://mlsanity.com/paper/2408.08729/) (2024)
- [SoundCompass: Navigating Target Sound Extraction With Effective Directional Clue Integration In Complex Acoustic Scenes](https://mlsanity.com/paper/2509.18561/) (2025)
- [A Knowledge-Driven Approach to Music Segmentation, Music Source Separation and Cinematic Audio Source Separation](https://mlsanity.com/paper/2602.21476/) (2026)
- [The Costs of Reproducibility in Music Separation Research: a Replication of Band-Split RNN](https://mlsanity.com/paper/2603.09187/) (2026)

## Abstract (arXiv)

Cinematic audio source separation is a relatively new subtask of audio source separation, with the aim of extracting the dialogue, music, and effects stems from their mixture. In this work, we developed a model generalizing the Bandsplit RNN for any complete or overcomplete partitions of the frequency axis. Psychoacoustically motivated frequency scales were used to inform the band definitions which are now defined with redundancy for more reliable feature extraction. A loss function motivated by the signal-to-noise ratio and the sparsity-promoting property of the 1-norm was proposed. We additionally exploit the information-sharing property of a common-encoder setup to reduce computational complexity during both training and inference, improve separation performance for hard-to-generalize classes of sounds, and allow flexibility during inference time with detachable decoders. Our best model sets the state of the art on the Divide and Remaster dataset with performance above the ideal ratio mask for the dialogue stem.