# End-to-end Source Separation with Adaptive Front-Ends

arXiv: https://arxiv.org/abs/1705.02514 · HTML: https://mlsanity.com/paper/1705.02514/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2017.

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

- [Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation](https://mlsanity.com/paper/2403.18257/) (2024)
- [Efficient Personalized Speech Enhancement through Self-Supervised Learning](https://mlsanity.com/paper/2104.02017/) (2021)
- [Deep neural network techniques for monaural speech enhancement: state of the art analysis](https://mlsanity.com/paper/2212.00369/) (2022)
- [The Radio-Frequency Transformer for Signal Separation](https://mlsanity.com/paper/2603.09201/) (2026)
- [A Time-domain Real-valued Generalized Wiener Filter for Multi-channel Neural Separation Systems](https://mlsanity.com/paper/2112.03533/) (2021)
- [Online Self-Attentive Gated RNNs for Real-Time Speaker Separation](https://mlsanity.com/paper/2106.13493/) (2021)

## Abstract (arXiv)

Source separation and other audio applications have traditionally relied on the use of short-time Fourier transforms as a front-end frequency domain representation step. The unavailability of a neural network equivalent to forward and inverse transforms hinders the implementation of end-to-end learning systems for these applications. We present an auto-encoder neural network that can act as an equivalent to short-time front-end transforms. We demonstrate the ability of the network to learn optimal, real-valued basis functions directly from the raw waveform of a signal and further show how it can be used as an adaptive front-end for supervised source separation. In terms of separation performance, these transforms significantly outperform their Fourier counterparts. Finally, we also propose a novel source to distortion ratio based cost function for end-to-end source separation.