# A Probabilistic Generative Model for Spectral Speech Enhancement

arXiv: https://arxiv.org/abs/2603.28436 · HTML: https://mlsanity.com/paper/2603.28436/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models.
- Builds on 12 of its 75 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## 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, 12 of 12)

- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [Real Time Speech Enhancement in the Waveform Domain](https://mlsanity.com/paper/2006.12847/) (2020)
- [SEGAN: Speech Enhancement Generative Adversarial Network](https://mlsanity.com/paper/1703.09452/) (2017)
- [Conditional Diffusion Probabilistic Model for Speech Enhancement](https://mlsanity.com/paper/2202.05256/) (2022)
- [TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids](https://mlsanity.com/paper/2005.11138/) (2020)
- [Universal Score-based Speech Enhancement with High Content Preservation](https://mlsanity.com/paper/2406.12194/) (2024)
- [WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-end Speech Enhancement](https://mlsanity.com/paper/2004.04098/) (2020)
- [A Factor Graph Approach to Automated Design of Bayesian Signal Processing Algorithms](https://mlsanity.com/paper/1811.03407/) (2018)
- [Metric-oriented Speech Enhancement using Diffusion Probabilistic Model](https://mlsanity.com/paper/2302.11989/) (2023)
- [Overview Of The 2023 Icassp Sp Clarity Challenge: Speech Enhancement For Hearing Aids](https://mlsanity.com/paper/2311.14490/) (2023)
- [A Probabilistic Modeling Approach to Hearing Loss Compensation](https://mlsanity.com/paper/1602.01345/) (2016)
- [AIDA: An Active Inference-based Design Agent for Audio Processing Algorithms](https://mlsanity.com/paper/2112.13366/) (2021)

## Abstract (arXiv)

Speech enhancement in hearing aids remains a difficult task in nonstationary acoustic environments, mainly because current signal processing algorithms rely on fixed, manually tuned parameters that cannot adapt in situ to different users or listening contexts. This paper introduces a unified modular framework that formulates signal processing, learning, and personalization as Bayesian inference with explicit uncertainty tracking. The proposed framework replaces ad hoc algorithm design with a single probabilistic generative model that continuously adapts to changing acoustic conditions and user preferences. It extends spectral subtraction with principled mechanisms for in-situ personalization and adaptation to acoustic context. The system is implemented as an interconnected probabilistic state-space model, and inference is performed via variational message passing in the textttRxInfer.jl probabilistic programming environment, enabling real-time Bayesian processing under hearing-aid constraints. Proof-of-concept experiments on the VoiceBank+DEMAND corpus show competitive speech quality and noise reduction with 85 effective parameters. The framework provides an interpretable, data-efficient foundation for uncertainty-aware, adaptive hearing-aid processing and points toward devices that learn continuously through probabilistic inference.