用神经网络预测语音未来信号，实现更精准的主动降噪
Feedforward Active Speech Suppression Based on Time Series Prediction of Speech Signals Using Neural Networks
- 基于神经网络预测语音未来波形，动态更新降噪滤波器
- 实验证明，使用真实或神经网络预测信号均能提升降噪效果
- 适合需要实时抑制非平稳语音噪声的应用场景
提出一种基于时间序列预测的前馈主动语音抑制方法。尽管现有主动降噪（ANC）技术对平稳噪声效果显著，但对高度非平稳的语音信号抑制仍具挑战。本文提出一种基于神经网络对未来信号进行时间序列预测的自适应滤波算法，控制滤波器的更新值由预测信号及当前和历史信号共同决定。数值实验表明，在使用真实预测信号和神经网络预测信号两种情况下，噪声抑制性能均得到提升。
原文摘要 · Abstract (English)
A feedforward active noise control (ANC) method based on time-series prediction for speech signals is proposed. Although current ANC techniques are highly effective against stationary noise, suppressing highly non-stationary speech signals remains a challenging task. We propose an adaptive filtering algorithm for active speech suppression based on neural-network-based time-series prediction of future signals. The update value for the linear control filter is calculated based on the predicted signal, as well as the current and past signals. Numerical experiments indicated that the noise reduction can be improved in both cases: when using the true predicted signal and when using a signal predicted by neural networks.
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。