BBYR Achieve
返回信息流
这是一条镜像帖。来源:北邮人论坛 / go-abroad / #40097同步于 2007/5/6
该镜像源已超过 30 天没有更新,可能在源站已被删除。
GoAbroad机器人发帖

[合集] 我翻译的一段文字,急切盼望大家拍转!!!

zhj5825
2007/5/6镜像同步0 回复
☆─────────────────────────────────────☆ panda (北邮人) 于 (Wed Mar 1 15:49:40 2006) 提到: 英文是 The use of segment-based features and segmentation networks in a segment-based speech recognizer complicates the probabilistic modeling because it alters the sample space of all possible segmentation paths and the feature observation space. This paper describes a novel Baum-Welch training algorithm for segment-based speech recognition which addresses these issues by an innovative use of finite-state transducers. This procedure has the desirable property of not requiring initial seed models that were needed by the Viterbi training procedure we have used previously. On the PhoneBook telephone-based corpus of read, isolated words, the Baum-Welch training algorithm obtained a relative error reduction of 37% on the training set and a relative error reduction of 5% on the test set, compared to Viterbi trained models. When combined with a duration model, and more flexible segmentation network, the Baum-Welch trained models obtain an overall word error rate of 7.6%, which is the best result we have seen published for the 8,000 word task. 我翻译为: 基于段的语音识别中对基于段的特征和分段的网络的使用,会因为它改变了所有可能分段路径的样本空间和特征观察空间,而使得其盖然论建模变得复杂。这篇论文描述了一种新颖的Baum-Welch训练算法,它以对有限状态变换器的创造性地运用来处理基于段的语音识别中的这些问题。其过程相比于Viterbi训练过程有令人欣喜的优势,那就是它不需要最初的原始模型。以从电话号码簿上的文本得到的孤立词为数据,Baum-Welch训练算法相比于从Viterbi训练得到的模型,在训练模块减少了37%的相关误差,在识别模块减少了5%的相关误差。当由Baum-Welch训练算法得到的模型与一个持续时间的模型和更多复杂的分段网络相结合之后,它的总体的单词差错率为7.6%,这是我们目前看到的已发表的8000单词任务中结果最好的。 ☆─────────────────────────────────────☆ moffatts (火星猫) 于 (Wed Mar 1 16:44:51 2006) 提到: 太专业,能力有限阿,纯支持一下~~~~~~~ ☆─────────────────────────────────────☆ Maccimus (德意志魂之无敌世界波) 于 (Wed Mar 1 17:22:50 2006) 提到: @__@ ☆─────────────────────────────────────☆ binghe (老徐) 于 (Wed Mar 1 17:32:28 2006) 提到: pai!中文基本能看懂 ☆─────────────────────────────────────☆ xuduoduo (小多多) 于 (Wed Mar 1 18:56:14 2006) 提到: 太长了,精神上支持一下你 ☆─────────────────────────────────────☆ Hajje (顺其自然) 于 (Wed Mar 1 20:17:06 2006) 提到: 我这还有篇5K多的文章,要不然你也帮着翻了?? ☆─────────────────────────────────────☆ panda (北邮人) 于 (Wed Mar 1 22:22:27 2006) 提到: 这就是我毕业设计要翻译的阿 想请大家帮我看看,翻译得对不对 ☆─────────────────────────────────────☆ superwendy (offers, ads and happiness) 于 (Wed Mar 1 22:57:35 2006) 提到: ......
订阅后,新回复会通过你的通知中心匿名送达。
0 条回复
暂无回复 · 你可以订阅本帖等待新回复。