DBNet: A Dual-Branch Network Architecture Processing on Spectrum and Waveform for Single-Channel Speech Enhancement

Zhang, Kanghao; He, Shulin; Li, Hao; Zhang, Xueliang

doi:10.21437/interspeech.2021-1042

Cited by 10 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zheng et al (2021), and Liu et al (2021) decomposed the speech enhancement process into two stages: in the first, the magnitude of the noise was estimated and used as a priori information for the second stage, which estimated the complex spectrum of the clean speech. Zhang et al (2021) proposed a dual-branch framework for spectrum and waveform modeling. All of the above-mentioned decoupling methods achieved better performance in terms of PESQ and STOI or Extended STOI (ESTOI) scores than methods mapping learning targets directly.…”

Section: Deep Learning Methodsmentioning

confidence: 99%

Sixty Years of Frequency-Domain Monaural Speech Enhancement: From Traditional to Deep Learning Methods

Zheng,

Zhang,

Liu

et al. 2023

Trends in Hearing

View full text Add to dashboard Cite

Frequency-domain monaural speech enhancement has been extensively studied for over 60 years, and a great number of methods have been proposed and applied to many devices. In the last decade, monaural speech enhancement has made tremendous progress with the advent and development of deep learning, and performance using such methods has been greatly improved relative to traditional methods. This survey paper first provides a comprehensive overview of traditional and deep-learning methods for monaural speech enhancement in the frequency domain. The fundamental assumptions of each approach are then summarized and analyzed to clarify their limitations and advantages. A comprehensive evaluation of some typical methods was conducted using the WSJ + Deep Noise Suppression (DNS) challenge and Voice Bank + DEMAND datasets to give an intuitive and unified comparison. The benefits of monaural speech enhancement methods using objective metrics relevant for normal-hearing and hearing-impaired listeners were evaluated. The objective test results showed that compression of the input features was important for simulated normal-hearing listeners but not for simulated hearing-impaired listeners. Potential future research and development topics in monaural speech enhancement are suggested.

show abstract

Section: Deep Learning Methodsmentioning

confidence: 99%

Sixty Years of Frequency-Domain Monaural Speech Enhancement: From Traditional to Deep Learning Methods

Zheng,

Zhang,

Liu

et al. 2023

Trends in Hearing

View full text Add to dashboard Cite

show abstract

“…Figure 1 presents some representative examples of different crop disease images, which can clearly observe that these crop disease images face problems such as variable disease types, irregular distribution of disease spots, and varying sizes of disease areas (Cohen et al, 2022). Recently, the advantages of two-branch networks using different learning strategies to integrate different feature information have been widely used in computer vision (Zhang et al, 2021;Xie et al, 2022;Zheng et al, 2022). In contrast, cooperative learning is applied to tracking learning of remote sensing scenes by taking advantage of the synergy and complementarity between different modules (Li et al, 2022b).…”

Section: Introductionmentioning

confidence: 99%

Dual-branch collaborative learning network for crop disease identification

et al. 2023

View full text Add to dashboard Cite

Crop diseases seriously affect the quality, yield, and food security of crops. redBesides, traditional manual monitoring methods can no longer meet intelligent agriculture’s efficiency and accuracy requirements. Recently, deep learning methods have been rapidly developed in computer vision. To cope with these issues, we propose a dual-branch collaborative learning network for crop disease identification, called DBCLNet. Concretely, we propose a dual-branch collaborative module using convolutional kernels of different scales to extract global and local features of images, which can effectively utilize both global and local features. Meanwhile, we embed a channel attention mechanism in each branch module to refine the global and local features. Whereafter, we cascade multiple dual-branch collaborative modules to design a feature cascade module, which further learns features at more abstract levels via the multi-layer cascade design strategy. Extensive experiments on the Plant Village dataset demonstrated the best classification performance of our DBCLNet method compared to the state-of-the-art methods for the identification of 38 categories of crop diseases. Besides, the Accuracy, Precision, Recall, and F-score of our DBCLNet for the identification of 38 categories of crop diseases are 99.89%, 99.97%, 99.67%, and 99.79%, respectively. 811

show abstract

Joint waveform and magnitude processing for monaural speech enhancement

Xiang

Zhang

2022

Applied Acoustics

View full text Add to dashboard Cite

DBNet: A Dual-Branch Network Architecture Processing on Spectrum and Waveform for Single-Channel Speech Enhancement

Cited by 10 publications

References 0 publications

Sixty Years of Frequency-Domain Monaural Speech Enhancement: From Traditional to Deep Learning Methods

Sixty Years of Frequency-Domain Monaural Speech Enhancement: From Traditional to Deep Learning Methods

Dual-branch collaborative learning network for crop disease identification

Joint waveform and magnitude processing for monaural speech enhancement

Contact Info

Product

Resources

About