The employment of non-uniform processes assists greatly in the corpus-based text-to-speech (TTS) system to synthesize natural speech. However, tailoring a TTS voice font, or pruning redundant syn-thesis instances, usually results in loss of non-uniform synthesis instances. In order to solve this problem, we propose the concept of virtual non-uniform instances. According to this concept and the synthesis fre-quency of each instance, the algorithm named StaRp-VPA is constructed to make up for the loss of non-uniform instances. In experimental testing, the naturalness scored by the mean opinion score (MOS) re-mains almost unchanged when less than 50% instances are pruned, and the MOS is only slightly degraded for reduction rates above 50%. The test results show that the algorithm StaRp-VPA is effective.
为了有效接受邮件客户端反馈并自动根据邮件客户端反馈对邮件过滤系统做出调整,提出了用户反馈自适应的POP3邮件过滤代理模型SAMFUF(self-adaptive mail filtering POP3 proxy based on users’feedback).SAMFUF采用异步连接模拟同步连接方式建立邮件客户端和邮件服务器间POP3连接,实现了邮件客户端与邮件服务器间的透明性连接;将最大熵、贝叶斯和支持向量机等基于内容过滤的方法从邮件过滤系统中独立出来,实现了通用邮件过滤系统的设计;通过在邮件中插入包含邮件唯一标识、分类结果等信息的HTML表单的标签以及调整邮件过滤模型,实现了基于邮件客户端的用户反馈以及邮件过滤系统的自适应功能;采用线程池管理线程和overlapped I/O事件通信方式实现邮件客户端与邮件服务器间通信,实现了邮件过滤服务的高效率和稳定性.实验表明,SAMFUF在垃圾邮件过滤上具有较高的效率和准确率.
