A frame loss compensation method and device includes: receiving a voice stream sequence; acquiring historical frame information and future frame information in the voice stream sequence, in which the voice stream sequence includes frame information of multiple voice frames, which include at least one historical frame, at least one current frame and at least one future frame, and the at least one historical frame is located in the time domain. Before at least one current frame, at least one future frame is located after at least one current frame in the time domain, and the historical frame information is the frame information of the at least one historical frame, and the future frame information is the frame information of the at least one future frame. Based on the historical frame information and the future frame information, the frame information of the at least one current frame is estimated to improve the accuracy of frame loss compensation.
【技术实现步骤摘要】
【国外来华专利技术】PCT国内申请,说明书已公开。
【技术保护点】
PCT国内申请,权利要求书已公开。
【技术特征摘要】
【国外来华专利技术】PCT国内申请,...
【专利技术属性】
技术研发人员:高振东,肖建良,刘泽新,
申请(专利权)人:华为技术有限公司,
类型:发明
国别省市:广东,44
还没有人留言评论。发表了对其他浏览者有用的留言会获得科技券。