Convolutional recurrent networks (CRN) integrating a convolutional encoder-decoder (CED) structure and a recurrent structure have achieved promising performance for monaural speech enhancement. However, feature representation across frequency context is highly constrained due to limited receptive fields in the convolutions of CED. In this paper, we propose a convolutional recurrent encoder-decoder (CRED) structure to boost feature representation along the frequency axis. The CRED applies frequency recurrence on 3D convolutional feature maps along the frequency axis following each convolution, therefore, it is capable of catching long-range frequency correlations and enhancing feature representations of speech inputs. The proposed frequency recurrence is realized efficiently using a feedforward sequential memory network (FSMN). Besides the CRED, we insert two stacked FSMN layers between the encoder and the decoder to model further temporal dynamics. We name the proposed framework as Frequency Recurrent CRN (FRCRN). We design FRCRN to predict complex Ideal Ratio Mask (cIRM) in complex-valued domain and optimize FRCRN using both time-frequency-domain and time-domain losses. Our proposed approach achieved state-of-the-art performance on wideband benchmark datasets and achieved 2nd place for the real-time fullband track in terms of Mean Opinion Score (MOS) and Word Accuracy (WAcc) in the ICASSP 2022 Deep Noise Suppression (DNS) challenge.
翻译:将调频器-代coder(CRED)结构与调频器结构相结合的CRED(CRED)网络中,将调频器结构与调频器结构结合起来的CRED(CRED)结构与常态结构相融合,在调频器增强调频器的特征代表制(CRED)结构中,由于CED演化过程中的接收场有限,不同频率的特征代表受到高度限制。在本文中,我们建议采用CRED(CRED)结构,将调频器结构与调频轴相融合。CRED(CRED)结构在3D调频轴中应用了频率重现频率,因此,它能够捕捉到远程频率相关关系,并增强语音投入的特征表现。提议的频率重现之所以有效,是因为使用了一个向向后继后传的连续存储网络(FSMMN)。除了CRED(CM)网络,我们还在电路段20-CRM(CRRM)基准中拟议将FM-CR-CRD(CRD-CRisal-CRisal-Bal-Bal-Bal-Bal-Bal-Bal-BY)方法用于实现的全时段的全时空和BS-CLon-CW-S-CW-CWA-S-CRM)标准。