Rethinking Complex-valued Deep Neural Networks For Monaural Speech Enhancement
2023 · Haibin Wu, Ke Tan, Buye Xu, et al.
Abstract
Despite multiple efforts made towards adopting complex-valued deep neural networks (DNNs), it remains an open question whether complex-valued DNNs are generally more effective than real-valued DNNs for monaural speech enhancement. This work is devoted to presenting a critical assessment by systematically examining complex-valued DNNs against their real-valued counterparts. Specifically, we investigate complex-valued DNN atomic units, including linear layers, convolutional layers, long short-term memory (LSTM), and gated linear units. By comparing complex- and real-valued versions of fundamental building blocks in the recently developed gated convolutional recurrent network (GCRN), we show how different mechanisms for basic blocks affect the performance. We also find that the use of complex-valued operations hinders the model capacity when the model size is small. In addition, we examine two recent complex-valued DNNs, i.e. deep complex convolutional recurrent network (DCCRN) and deep c
Authors
(none)
Tags
Stats
Related papers
- DCCRN: Deep Complex Convolution Recurrent Network For Phase-aware Speech Enhancement (2020)20.78
- Deep Neural Network Techniques For Monaural Speech Enhancement: State Of The Art Analysis (2022)0.00
- A Deep Representation Learning-based Speech Enhancement Method Using Complex Convolution Recurrent Variational Autoencoder (2023)7.16
- Real-time Monaural Speech Enhancement With Short-time Discrete Cosine Transform (2021)0.00
- DCCRN+: Channel-wise Subband DCCRN With SNR Estimation For Speech Enhancement (2021)0.00
- Monaural Speech Enhancement Using A Multi-branch Temporal Convolutional Network (2019)3.58
- Convolutional Recurrent Neural Network Based Progressive Learning For Monaural Speech Enhancement (2019)0.00
- DCCRGAN: Deep Complex Convolution Recurrent Generator Adversarial Network For Speech Enhancement (2020)0.00