让助听器降噪模型在训练时就面对不稳状态，提升高增益下的稳定性。
In-the-Loop Training of Deep Feedback Cancellation for Hearing Aids
- 将反馈消除模型嵌入优化闭环，训练时模拟不稳场景
- 高增益下性能显著优于传统开环训练方法，可防啸叫
- 适合追求高音量输出且需稳定性的助听器研发人员
声学反馈限制了助听器的最大增益。尽管已有基于自适应滤波的方法，近期也出现了基于深度神经网络的反馈消除（DFC）方法，但其采用开环框架训练，在高增益推理时可能不稳定。本文提出一种闭环训练的DFC（DFC-IL），将模型直接融入优化循环中，使模型在训练阶段就能接触不稳定的运行条件。通过先在稳定系统上预训练、再在更宽增益范围内微调的两阶段策略，DFC-IL能够学习到鲁棒的啸叫抑制能力。在实测反馈路径上的实验表明：在小增益场景下，DFC-IL与DFC-OL表现相当，均优于自适应滤波器；而在高增益场景下，DFC-IL明显优于DFC-OL，保持系统稳定。
原文摘要 · Abstract (English)
Acoustic feedback limits the maximum gain in hearing aids. In addition to several approaches based on adaptive filtering, recently a deep-neural-network-based feedback cancellation (DFC) approach has been proposed, which is trained via an open-loop framework. Since open-loop-trained DFC (DFC-OL) can become unstable during inference at high gains, in this paper we propose an in-the-loop-trained DFC (DFC-IL) that integrates the DFC directly into the optimisation loop. This allows the model to be exposed to unstable conditions during training. A two-stage training strategy involving pre-training on stable systems and fine-tuning on a wider gain range enables DFC-IL to learn robust howling reduction. Experimental results on measured feedback paths demonstrate that in scenarios with small gains, the proposed DFC-IL performs similarly to DFC-OL, and both exceed the performance of adaptive filters. In scenarios with high amplification gains, DFC-IL clearly outperforms DFC-OL by maintaining system stability.
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。