用概率模型实现自适应语音增强，让助听器能实时学习用户偏好。
A Probabilistic Generative Model for Spectral Speech Enhancement
- 构建统一概率生成模型，通过贝叶斯推断实现参数自适应。
- 在VoiceBank+DEMAND数据集上仅用85个参数即达竞争性降噪效果。
- 适合需要可解释、低资源、持续学习的智能助听器研发者。
助听器在非平稳声学环境下的语音增强仍具挑战，因现有信号处理算法依赖固定的手动调参，无法实时适应不同用户或听觉场景。本文提出一种统一模块化框架，将信号处理、学习与个性化建模为带有显式不确定性追踪的贝叶斯推断。该框架以单一概率生成模型替代传统启发式设计，可连续适应声学条件与用户偏好。模型扩展了谱减法，引入原则性机制实现现场个性化与上下文自适应。系统以互联的概率状态空间模型实现，使用RxInfer.jl概率编程环境进行变分消息传递推断，满足助听器实时贝叶斯处理需求。在VoiceBank+DEMAND语料库上的概念验证实验表明，仅需85个有效参数即可达到具有竞争力的语音质量和噪声抑制性能。该框架为不确定性感知、自适应助听处理提供了可解释且数据高效的基础，指向可通过概率推断持续学习的智能设备未来。
原文摘要 · Abstract (English)
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 \texttt{RxInfer.jl} probabilistic programming environment, enabling real-time Bayesian processing under hearing-aid constraints. Proof-of-concept experiments on the \emph{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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。