This paper introduces the NWPU Team's entry to the ICASSP 2022 AEC Challenge. We take a hybrid approach that cascades a linear AEC with a neural post-filter. The former is used to deal with the linear echo components while the latter suppresses the residual non-linear echo components. We use gated convolutional F-T-LSTM neural network (GFTNN) as the backbone and shape the post-filter by a multi-task learning (MTL) framework, where a voice activity detection (VAD) module is adopted as an auxiliary task along with echo suppression, with the aim to avoid over suppression that may cause speech distortion. Moreover, we adopt an echo-aware loss function, where the mean square error (MSE) loss can be optimized particularly for every time-frequency bin (TF-bin) according to the signal-to-echo ratio (SER), leading to further suppression on the echo. Extensive ablation study shows that the time delay estimation (TDE) module in neural post-filter leads to better perceptual quality, and an adaptive filter with better convergence will bring consistent performance gain for the post-filter. Besides, we find that using the linear echo as the input of our neural post-filter is a better choice than using the reference signal directly. In the ICASSP 2022 AEC-Challenge, our approach has ranked the 1st place on word accuracy (WAcc) (0.817) and the 3rd place on both mean opinion score (MOS) (4.502) and the final score (0.864).
翻译:本文介绍 NWPU 团队进入 ICASSP 2022 AEC 挑战 。 我们采取混合方法, 将线性 AEC 与神经过滤器连成一个神经过滤器, 前者用于处理线性回声组件, 而后者则压制剩余非线性回声组件 。 我们使用门状F- T- LSTM 神经网络( GFTNNN) 作为主干, 并用多任务学习( MTL) 框架塑造过滤后过滤器, 该框架将语音活动检测模块作为辅助任务, 并同时进行回声抑制, 目的是避免超过抑制, 从而可能导致言语扭曲。 此外, 我们采用回声- 觉损失功能功能功能, 平均平差( MSE) 损失可以优化每个时频 bin( TF- bin) 。 我们使用信号- TF- LS 的比例, 从而进一步压制回声学 。 广义过滤器中的时间估计( TDE) 模块会提高感官- 质量,, 并且 将 IMS IMVER 进行更精确的升级 。