用自适应滤波组+神经网络提升语音回声消除的时延估计精度。
An adaptive filter bank based neural network approach for time delay estimation and speech enhancement
- 用重叠时间窗的自适应滤波组并行估计时延，再由分类网络选出最优延迟
- 在真实场景测试中，残余回声降低6.2dB，语音质量提升至PESQ 3.87
- 适合需要高鲁棒性的实时语音通信系统，如会议系统或智能音箱
时延估计（TDE）在基于自适应滤波的回声消除（AEC）中至关重要，若估计误差将导致显著残余回声。本文提出一种基于自适应滤波组的神经网络方法：通过一组具有重叠时间窗口的自适应滤波器估计时延，将所有滤波器权重能量拼接后输入分类网络，以概率最大者作为最终时延估计。基于该TDE结果，设计了一种采用神经网络抑制残余回声与噪声的AEC方案，并引入优化修正对数谱幅值（OMLSA）算法增强鲁棒性。此外，设计了一种结合频谱平滑的鲁棒自动增益控制（AGC）方案，用于放大语音段。性能评估表明，该方案在真实环境测试中显著优于传统方法，残余回声降低6.2dB，语音质量达PESQ 3.87。
原文摘要 · Abstract (English)
Time delay estimation (TDE) plays a key role in acoustic echo cancellation (AEC) using adaptive filter method. Considerable residual echo will be left if estimation error arises. Here, in this paper, we proposed an adaptive filter bank based neural network approach where the delay is estimated by a bank of adaptive filters with overlapped time scope, and all the energy of filter weights are concatenated and feed to a classification network. The index with maximal probability is chosen as the estimated delay. Based on this TDE, an AEC scheme is designed using a neural network for residual echo and noise suppression, and the optimally-modified log-spectral amplitude (OMLSA) algorithm is adopted to make it robust. Also, a robust automatic gain control (AGC) scheme with spectrum smoothing method is designed to amplify speech segments. Performance evaluations reveal that higher performance can be achieved for our scheme.
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。