The redundant convolutional encoder-decoder network has been proven useful in speech enhancement tasks. This network can capture the localized time-frequency details of speech signals through the fully convolutional network structure and the feature selection capability that results from the encoderdecoder mechanism. However, extracting informative features, which we regard as important for the representational capability of speech enhancement models, is not considered explicitly. To solve this problem, we introduce the attention mechanism into the convolutional encoder-decoder model to explicitly emphasize useful information from three aspects, namely, channel, space, and concurrent space-and-channel. Furthermore, the attention operation is specifically achieved through the squeeze-and-excitation mechanism and its variants. The model can adaptively emphasize valuable information and suppress useless ones by assigning weights from different perspectives according to global information, thereby improving its representational capability. Experimental results show that the proposed attention mechanisms can employ a small fraction of parameters to effectively improve the performance of CNN-based models compared with their normal versions, and generalize well to unseen noises, signal-to-noise ratios (SNR) and speakers. Among these mechanisms, the concurrent space-channel-wise attention exhibits the most significant improvement. And when comparing with the state-of-the-art, they can produce comparable or better results. We also integrate the proposed attention mechanisms with other convolutional neural network (CNN)-based models and gain performance. Moreover, we visualize the enhancement results to show the effect of the attention mechanisms more clearly.
The auditory selection framework with attention and memory (ASAM), which has an attention mechanism, embedding generator, generated embedding array, and lifelong memory, is used to deal with mixed speech. When ASAM is applied to speech enhancement, the discrepancy between the voice and noise feature memories is huge and the separability of noise and voice is increased. However, ASAM cannot achieve desirable performance in terms of speech enhancement because it fails to utilize the time-frequency dependence of the embedding vectors to generate a corresponding mask unit. This work proposes a novel embedding encoder-decoder (EED), and a convolutional neural network (CNN) is used as decoder. The CNN structure is good at detecting local patterns, which can be exploited to extract correlation embedding data from the embedding array to generate the target spectrogram. This work evaluates a similar ASAM, EED with an LSTM encoder and a CNN decoder (RC-EED), RC-EED with an attention mechanism (RC-AEED), other similar EED structures and baseline models. Experiment results show that RC-EED and RC-AEED networks have good performance on speech enhancement task at low signal-to-noise ratio conditions. In addition, RC-AEED exhibits superior speech enhancement performance over ASAM and achieves better speech quality than do deep recurrent network and convolutional recurrent network. INDEX TERMS Speech enhancement, embedding encoder-decoder, convolutional neural network, attention mechanism, neural network.
Rationale: Eczematous eruption is an increasingly recognized form of drug-related eruption, typically reported in association with interleukin 17 (IL-17)A inhibitors. However, severe paradoxical eczematous eruption due to IL-17A inhibitors has been rarely reported. Herein, we reported a case of a man with severe psoriasis with erythematous scaly plaques on the scalp, trunk, and arms and legs after the administration of secukinumab was initiated. Patient concerns: We reported a case of a 20-year-old man with severe psoriasis with erythematous scaly plaques on the scalp, trunk, and arms and legs after the administration of secukinumab was initiated. A skin biopsy was performed. It revealed spongiotic dermatitis consistent with eczematous reaction. Direct and indirect immunofluorescence assays were negative. Diagnoses: He was diagnosed with eczematous eruption. Interventions: Discontinuation of secukinumab and administration of cyclosporine and prednisone were considered. Outcomes: Significant improvement was observed, with no adverse events. Conclusion: Our case shows that eczematous eruption can paradoxically occur in patients on IL-17A inhibitors and this report is expected to increase awareness of the rising number of cutaneous eruptions related to biological agents.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.