维普期刊资源整合服务平台（V6.5）

维普中文期刊产品整合服务

6篇 您的检索式：作者名="Haikang"

选中清除导出查看参考文献查看引证文献引用追踪共1页首页上一页第1页下一页末页 /1 跳转

		题名	作者	年代	出处	被引量
	1	Remifentanil protects liver against ischemia/reperfusion injury through activation of anti-apoptotic pathways显示文摘	Ge Zhao Xin Shen Haiyan Nan Linfeng Yan Haikang Zhao Jun Yu Yi Lv	2013	Journal of Surgical Research2013，，2：	1
	2	Prognostic evaluation of microRNA-210 expression in pediatric osteosarcoma显示文摘	Haiqing Cai Lijun Lin Haikang Cai Mingjie Tang Zhigang Wang	2013	Medical Oncology2013，，2：	1
	3	MicroRNA-145 downregulation associates with advanced tumor progression and poor prognosis in patients suffering osteosarcoma显示文摘	Zubin Zhou Jie Tang Haikang Cai Lijun Lin Mingjie Tang	2013	OncoTargets and Therapy . 2013 (defa)2013，，：	1
	4	Levels of Emotional Distress Among Parents Living with AIDS and their Adolescent Children显示文摘	Mary Jane Rotheram-Borus Marguerita Lightfoot Haikang Shen	1999	AIDS and Behavior1999，，4：	1
	5	Lower extremity injuries from motorcycle crashes: A common cause of preventable injury显示文摘	Elisa RB Haikang S	1994	J Trauma1994，37，3：	1
	6	A Novel Re-weighted CTC Loss for Data Imbalance in Speech Keyword Spotting显示文摘Speech keyword spotting system is a critical component of human-computer interfaces.And connectionist temporal classifier(CTC)has been proven to be an effective tool for that task.However,the standard training process of speech keyword spotting faces a data imbalance issue where positive samples are usually far less than negative samples.Numerous easy-training negative examples overwhelm the training,resulting in a degenerated model.To deal with it,this paper tries to reshape the standard CTC loss and proposes a novel reweighted CTC loss.It evaluates the sample importance by its number of detection errors during training and automatically down-weights the contribution of easy examples,the majorities of which are negatives,making the training focus on samples deserving more training.The proposed method can alleviate the imbalance naturally and make use of all available data efficiently.Evaluation on several sets of keywords selected from AISHELL-1 and AISHELL-2 achieves 16%–38%relative reductions in false rejection rates over standard CTC loss at 0.5 false alarms per keyword per hour in experiments.	LAN Xiaotian HE Qianhua YAN Haikang LI Yanxiong	2023	Chinese Journal of Electronics2023，32，3：	0

返回顶部每页显示：

共1页首页上一页第1页下一页末页 /1 跳转

goolge学术搜索-维普

网站首页 | 关于我们 | 联系我们 | 产品服务 | 客服中心 | 广告服务 | 版权声明 | 网站联盟 | 友情链接 | 售卡网点

版权所有© 渝B2-20050021-1　渝公网安备 50019002500403号　违法和不良信息举报中心

互联网出版许可证新出网证(渝)字10号全国400电话 - 免长途话费