Speech Enhancement via Residual Dense Generative Adversarial Network

Generative adversarial networks(GANs)are paid more attention to dealing with the end-to-end speech enhancement in recent years.Various GANbased enhancement methods are presented to improve the quality of reconstructed speech.However,the performance of these GAN-based methods is worse than those of masking-based methods.To tackle this problem,we propose speech enhancement method with a residual dense generative adversarial network(RDGAN)contributing to map the log-power spectrum(LPS)of degraded speech to the clean one.In detail,a residual dense block(RDB)architecture is designed to better estimate the LPS of clean speech,which can extract rich local features of LPS through densely connected convolution layers.Meanwhile,sequential RDB connections are incorporated on various scales of LPS.It significantly increases the feature learning flexibility and robustness in the time-frequency domain.Simulations show that the proposed method achieves attractive speech enhancement performance in various acoustic environments.Specifically,in the untrained acoustic test with limited priors,e.g.,unmatched signal-to-noise ratio(SNR)and unmatched noise category,RDGAN can still outperform the existing GAN-based methods and masking-based method in the measures of PESQ and other evaluation indexes.It indicates that our method is more generalized in untrained conditions.

Chemically induced hypoxia by dimethyloxalylglycine(DMOG)-loaded nanoporous silica nanoparticles supports endothelial tube formation by sustained VEGF release from adipose tissue-derived stem cells

Inadequate vascularization leading to insufficient oxygen and nutrient supply in deeper layers of bioartificial tissues remains a limitation in current tissue engineering approaches to which prevascularization offers a promising solution.Hypoxia triggering pre-vascularization by enhanced vascular endothelial growth factor(VEGF)expression can be induced chemically by dimethyloxalylglycine(DMOG).Nanoporous silica nanoparticles(NPSNPs,or mesoporous silica nanoparticles,MSNs)enable sustained delivery of molecules and potentially release DMOG allowing a durable capillarization of a construct.Here we evaluated the effects of soluble DMOG and DMOG-loaded NPSNPs on VEGF secretion of adipose tissue-derived stem cells(ASC)and on tube formation by human umbilical vein endothelial cells(HUVEC)-ASC co-cultures.Repeated doses of 100 mM and 500 mM soluble DMOG on ASC resulted in 3-to 7-fold increased VEGF levels on day 9(P<0.0001).Same doses of DMOG-NPSNPs enhanced VEGF secretion 7.7-fold(P<0.0001)which could be maintained until day 12 with 500 mM DMOG-NPSNPs.In fibrin-based tube formation assays,100 mM DMOG-NPSNPs had inhibitory effects whereas 50 mM significantly increased tube length,area and number of junctions transiently for 4 days.Thus,DMOG-NPSNPs supported endothelial tube formation by upregulated VEGF secretion from ASC and thus display a promising tool for prevascularization of tissue-engineered constructs.Further studies will evaluate their effect in hydrogels under perfusion.