# Improved Normalizing Flow-Based Speech Enhancement using an All-pole Gammatone Filterbank for Conditional Input Representation

arXiv: https://arxiv.org/abs/2210.11654 · HTML: https://mlsanity.com/paper/2210.11654/

## Key facts

- Cited by 3 papers in the map (data through 19 Oct 2026).
- Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models.
- Builds on 24 of its 41 references that are in the map.
- First posted on arXiv 21 Oct 2022.

## Placed in

- Speech and audio language models / [Speech enhancement and noise suppression](https://mlsanity.com/speech/speech-enhancement-and-noise-suppression/)

## Builds on (most cited first, 24 of 24)

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Normalizing Flows for Probabilistic Modeling and Inference](https://mlsanity.com/paper/1912.02762/) (2019)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [WaveGlow: A Flow-based Generative Network for Speech Synthesis](https://mlsanity.com/paper/1811.00002/) (2018)
- [Supervised Speech Separation Based on Deep Learning: An Overview](https://mlsanity.com/paper/1708.07524/) (2017)
- [Analyzing Inverse Problems with Invertible Neural Networks](https://mlsanity.com/paper/1808.04730/) (2018)
- [Unrolled Generative Adversarial Networks](https://mlsanity.com/paper/1611.02163/) (2016)
- [Conditional Diffusion Probabilistic Model for Speech Enhancement](https://mlsanity.com/paper/2202.05256/) (2022)
- [MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement](https://mlsanity.com/paper/2104.03538/) (2021)
- [Far-Field Automatic Speech Recognition](https://mlsanity.com/paper/2009.09395/) (2020)
- [A Recurrent Variational Autoencoder for Speech Enhancement](https://mlsanity.com/paper/1910.10942/) (2019)
- [StyleMelGAN: An Efficient High-Fidelity Adversarial Vocoder with Temporal Adaptive Normalization](https://mlsanity.com/paper/2011.01557/) (2020)
- [ESPnet-se: end-to-end speech enhancement and separation toolkit designed for asr integration](https://mlsanity.com/paper/2011.03706/) (2020)
- [DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement](https://mlsanity.com/paper/2106.15813/) (2021)
- [Objective Measures of Perceptual Audio Quality Reviewed: An Evaluation of Their Application Domain Dependence](https://mlsanity.com/paper/2110.11438/) (2021)
- [A Flow-Based Neural Network for Time Domain Speech Enhancement](https://mlsanity.com/paper/2106.09008/) (2021)
- [Dual Application of Speech Enhancement for Automatic Speech Recognition](https://mlsanity.com/paper/2011.03840/) (2020)
- [A Conformer-based ASR Frontend for Joint Acoustic Echo Cancellation, Speech Enhancement and Speech Separation](https://mlsanity.com/paper/2111.09935/) (2021)
- [A Hands-on Comparison of DNNs for Dialog Separation Using Transfer Learning from Music Source Separation](https://mlsanity.com/paper/2106.09093/) (2021)

## Built on by (most cited first, 3 of 3)

- [SEFGAN: Harvesting the Power of Normalizing Flows and GANs for Efficient High-Quality Speech Enhancement](https://mlsanity.com/paper/2312.01744/) (2023)
- [What do neural networks listen to? Exploring the crucial bands in Speech Enhancement using Sinc-convolution](https://mlsanity.com/paper/2403.01785/) (2024)
- [Adapting Speech Language Model to Singing Voice Synthesis](https://mlsanity.com/paper/2512.14657/) (2025)

## Abstract (arXiv)

Deep generative models for Speech Enhancement (SE) received increasing attention in recent years. The most prominent example are Generative Adversarial Networks (GANs), while normalizing flows (NF) received less attention despite their potential. Building on previous work, architectural modifications are proposed, along with an investigation of different conditional input representations. Despite being a common choice in related works, Mel-spectrograms demonstrate to be inadequate for the given scenario. Alternatively, a novel All-Pole Gammatone filterbank (APG) with high temporal resolution is proposed. Although computational evaluation metric results would suggest that state-of-the-art GAN-based methods perform best, a perceptual evaluation via a listening test indicates that the presented NF approach (based on time domain and APG) performs best, especially at lower SNRs. On average, APG outputs are rated as having good quality, which is unmatched by the other methods, including GAN.