查询词典 speaker

Surprisingly, now the speaker has quietly explode (mainly supply of inventory and personal collection), worth surge in, 2.5-inch uvula spring actually sold more than 200 yuan a speaker (with value-free city, and that it is another matter a), that not it has a new function, but the way people see it as an era is characterized by the desire to hold.

谁知现在这种喇叭又悄悄地火爆起来（货源主要是库存及个人收藏），身价激增，2.5寸的小舌簧喇叭居然卖到二百多元一只（有价无市那又是另外一回事了），到并不是它又有了新的功用，而是人们把它看成是一个时代的特征而渴望持有。

This paper proposed a new hierarchical speaker identification system based on Multi-Reduced Support Vector Machine and Principal Component Analysis classifier to reduce the recognition time of speaker identification.

提出一种基于主成分分析和多约简支持向量机的多级说话人辨识方法。

Voiceprint recognition recognizes speakers, and it does not recognize contents of the pronunciation signal of speaker, but the identity of the speaker of the pronunciation signal.

声纹认证不是认证语音信号的文字内容，而是认证发出语音信号的说话人的身份。

In order to decrease the error rate of speech recognition, speaker adaptation techniques are often used to adjust speaker-dependent acoustic models. MLLR (Maximum Likelihood Linear Regression) and MAP are two of the most popular techniques in recent years. MLLR uses the technique of regression trees. It calculates the transform matrix for each leaf node of the tree. This makes it possible to use fewer sentences to decrease the error rate of HMM-based speech recognition. However, while we examined the recognition result, we found that although the overall error rate decreased, but the error rate of certain confusable phones was higher. In order to solve this problem, we propose the use MPE (Minimum Phone Error Discriminative Training) to solve this problem.

在语音辨识技术的实际应用上，语者调适技术常被用做调整语者无关之声学模型，使其对於特定语者之辨识率有所提升，常见的语者调适技术有最大化相似度线性回归（Maximum Likelihood Linear Regression），其精神在於透过对语音辨识模型相近的mixture做群聚，再对各个群聚做调整，以期能达到利用少量语料，提升辨识率的目的，但其缺点为，在发音上相近的模型，其mixture原本就极为近似，若再分类为同一群聚做调整，容易因为使用者的发音习惯，而使模型偏向ㄓ或ㄗ，因此虽然整体的辨识率获得提升，但却造成混淆音的错误率上升。

The mobile phone speaker cover can not only protect the speaker, but also have an influence on the electroacoustic characteristics.

手机扬声器的面盖不仅起保护扬声器的作用，而且会对电声性能产生影响。

A speaker of another language might not hear in the sound // any such icon at all; for a French speaker the words hache, tache, crache, sache, cache, vache have no semantic relationship despite similar final sounds.

别的语言使用者往往不会听到这里的语言图标，对于一个法语实用者，斧点，吐痰，知道，皮革，牛，这些词除了尾音相似之外，没有什么语义上的联系。

Need SUPPLIER to source Hisense Marine Audio System, and demand that with the inbuilt speaker, speaker, radio, video stero, water-proof remote control that could avoid being damaged when it dropping into the water, light control sensor

客人要供应商公司寻找水下多功能音响系统，如：内置喇叭、立体音响、防水遥控器、光感器（防止人的手等其他部位置于升降器空隙中被夹伤）、DVD/电视功能、控制面板等

In the speaker recognition system, the personality feature of the speaker is one of the key problems of the system.

在说话人识别系统中，能够反映说话人个性的语音特征参数是系统的关键问题之一。

Come on Alibaba, here you need all kinds of Swans speaker unit, also welcome you to fairs Swans speaker unit, this is your opportunity to demonstrate strength!

快来阿里巴巴，这里有您所需要的各类惠威喇叭单元，也欢迎您来展销惠威喇叭单元，这是您彰显实力的好机会！

A speaker from each unit of the design, development, production to the aging test ;Speaker of the design, development, production to the aging test,We strictly operate the plant and each procedure, so that the perfect technology exquisite embodiment.

从每一个喇叭单元的设计，开发，生产到老化测试；音箱的设计，开发，生产到老化测试，我们严格操作生产每道工序，使精湛的技术得到完美体现。

The circulation, consumption and reproduction of the trilogy have not only testified to its historical significance and literariness, but also invested it with new meanings.

该三部曲的流通、消费与再生产不仅验证了其历史意义及文学性，而切还赋予它以新的意义。

If he thought that he could buy me off, he would be wrong.

如果他认为他可以收买我，那他就大错特错了。