摘要
在实际应用中,语音分离模型往往受到未知噪声的干扰,从而出现泛化性能严重退化的问题。据此本文提出了基于分离结果信噪比估计与自适应调频网络的单通道语音分离方法。该方法首先通过预测网络对测试信号分离结果的尺度不变信噪比进行估计,以此计算模型的认知不确定性;然后,设计自适应调频网络针对不确定性较高的信号进行自适应频谱调节,以降低模型认知不确定性,从而提升模型在面对未知噪声时的泛化能力。实验结果表明:本文提出的方法相比于单独的时域卷积语音分离网络,将SI-SNR指标从2.72 dB提升至4.57 dB,增幅达到67.94%,在泛化能力上具有较大的改善;相比于增加了软掩膜过滤机制的时域卷积语音分离网络,将SI-SNR指标从3.32d B提升至4.57 dB,增幅达到37.65%,表明该方法在提高泛化能力方面的能力优于软掩膜过滤机制。
In practical applications,speech separation models are often disturbed by unknown noise,resulting in serious degradation of generalization performance.To solve this problem,Single channel speech separation method based on separate SNR regression estimation and adaptive frequency modulation network is proposed.Firstly,the scale invariant SNR of test signal separation results is estimated by prediction network to calculate the cognitive uncertainty of the model;Then,an adaptive frequency modulation network is designed to adjust the spectrum of signals with high uncertainty to reduce the cognitive uncertainty of the model,so as to improve the generalization ability of the model in the face of unknown noise.The experimental results show that compared with the Conv-Tasnet,the proposed method improves the SI-SNR(Scale Invariant SNR)from 2.72 dB to 4.57 dB,with an increase of 67.94%,and has a great improvement in generalization ability.Compared with Conv-Tasnet with Soft-Mask,the SI-SNR is increased from 3.32 dB to 4.57 dB,with an increase of 37.65%,indicating that this method has better generalization ability than soft mask mechanism.It effectively alleviates the serious degradation of generalization ability of speech separation network in the face of unknown noise.
作者
张锐
吕俊
Zhang Rui;Lyu Jun(School of Automation,Guangdong University of Technology,Guangzhou 510006,China)
出处
《广东工业大学学报》
CAS
2023年第2期45-54,共10页
Journal of Guangdong University of Technology
基金
国家自然科学基金资助面上项目(62073086)。
关键词
语音分离
不确定性度量
噪声鲁棒
神经网络
speech separation
uncertainty measurement
noise robustness
neural network