# Efficient Trainable Front-Ends for Neural Speech Enhancement

arXiv: https://arxiv.org/abs/2002.09286 · HTML: https://mlsanity.com/paper/2002.09286/

## Key facts

- Cited by 2 papers in the map (data through 19 Oct 2026).
- First posted on arXiv 20 Feb 2020.

## Built on by (most cited first, 2 of 2)

- [Ultra-Low Latency Speech Enhancement - A Comprehensive Study](https://mlsanity.com/paper/2409.10358/) (2024)
- [A Multiscale Autoencoder (MSAE) Framework for End-to-End Neural Network Speech Enhancement](https://mlsanity.com/paper/2309.12121/) (2023)

## Abstract (arXiv)

Many neural speech enhancement and source separation systems operate in the time-frequency domain. Such models often benefit from making their Short-Time Fourier Transform (STFT) front-ends trainable. In current literature, these are implemented as large Discrete Fourier Transform matrices; which are prohibitively inefficient for low-compute systems. We present an efficient, trainable front-end based on the butterfly mechanism to compute the Fast Fourier Transform, and show its accuracy and efficiency benefits for low-compute neural speech enhancement models. We also explore the effects of making the STFT window trainable.