Search Results - "Wei, Guangcun"

Lambda-vector modeling temporal and channel interactions for text-independent speaker verification by Wei, Guangcun, Min, Hang, Xu, Yunfei, Zhang, Yanna

“…Most of the current excellent models in speaker verification are ResNet-based deep models and attention-based models. These models have a general weakness,…”
Get full text

Toward Arbitrary-Shaped Text Spotting Based On End-To-End by Wei, Guangcun, Rong, Wansheng, Liang, Yongquan, Xiao, Xinguang, Liu, Xiang

“…At present, text spotting in natural scenes has become one of the research hotspots. Among them, curvilinear text and long text are the main difficulties of…”
Get full text

BIUnet: Unet Network for Mask Estimation in Single-Channel Speech Enhancement by Fang, Qingge, Wei, Guangcun, Pan, Zhifei, Fu, Jihua

“…Deep learning-based single-channel speech enhancement techniques have demonstrated their effectiveness in enhancing speech quality. However, their performance,…”
Get full text

An Optimization Method for Short Utterances Speaker Verification Based on Seq2Seq by Xu, Yunfei, Wei, Guangcun, Min, Hang, Zhang, Yanna

“…The progress of deep learning technology has led to remarkable advancements in the field of text-independent speaker verification. However, when dealing with…”
Get full text

End-to-end speaker identification research based on multi-scale SincNet and CGAN by Wei, Guangcun, Zhang, Yanna, Min, Hang, Xu, Yunfei

“…Deep learning has improved the performance of speaker identification systems in recent years, but it has also presented significant challenges. Typically,…”
Get full text

The Application Research on Graphic Traverse Algorithm in Graphic Topology Analysis by Wei Guangcun, Wang Qiang

“…Graph depth-first traverse algorithm is based on the premise of establishing an adjacency table. According to the demand of graphic component auto-creating in…”
Get full text

Research on Traffic Light Adjustment Based on Compatibility Graph of Traffic Flow by Qiang Wang, Lei Wang, Guangcun Wei

“…As the baton of urban traffic, traffic light plays the most important role on the traffic impact. Now traffic light has been able to better schedule and extend…”
Get full text

Notice of Retraction: Analysis and forecasting model of tourism economy based on improved support vector regression by Liu Taian, Xue Xin, Wei Guangcun, Shen Chuanhe, Liu Xinying

Get full text

Dual-Stage Training Frame-level Overlapping Speech Detection Model Based on Convolutional Neural Network Architecture by Pan, Zhifei, Wei, Guangcun, Fang, Qingge, Fu, Jihua, Liu, Jianan

“…A dual-stage training frame-level overlapping speech detection model is proposed in this paper, with its core being based on RepVGG blocks structure, and…”
Get full text

Wavelet Packet Sub-band Cepstral Coefficient for Speaker Verification by Min, Hang, Wei, Guangcun, Xu, Yunfei, Zhang, Yanna

“…Existing speaker verification systems perform well under clean condition, however their performance degrades significantly when subjected to noise…”
Get full text

The Higher-quality High-level Semantics based on Improved Visual Model for VQA by Xiao, Xinguang, Wei, Guangcun, Rong, Wansheng, Liu, Xiang

“…Visual question answering is a new research direction that combines computer vision and natural language processing. Some recent research uses image…”
Get full text