查询词典 in speech

Endpoint detection of speech is a curial problem in speech recognition. Endpoint detection has an important effect on speech recognition.

端点检测是语音识别中的一项关键技术，端点检测的准确性对语音识别的结果有很大影响。

I think that is in a large part due to the quality of the speech synthesizer, which is made by Speech Plus.

我想大部分原因是声音合成器的质量很好，是由Speech Plus生产的。

Reason is such, because we think to did not come in speech calculative, the browser is the platform of a special core, because later of the user get online, the osculatory speech computation of the user, no matter be in PC, mobile phone or over the hardware of other, it needs a very powerful browser.

理由是这样的，因为我们认为在语音计算的未来，浏览器是一个非常核心的平台，因为以后用户的上网、用户的接触语音计算，无论是在PC、手机或者是其它的硬件之上，它需要一个非常强而有力的浏览器。

The word-to-sound rule and the structure of a speech database are modified during the implementation of TTS system, and then a filter algorithm based on part-of-speech is proposed to solve the polyphone problem. Prosodic research on Chinese characters plays a great role in speech recognition and speech synthesis system. In order to improve the naturalness of a speech synthesis system, the relationship among the sentence structure, the length of a sentence and the breath boundaries is analyzed and a breath boundary assigning algorithm based on such relationship is put forward. In addition, the author analyzes the process of a speech synthesis system and builds a prosodic markup language suitable for Chinese speech synthesis.

呼吸群边界划分作为汉语韵律的一种表现方式，它在语音感知和文语转换系统的性能方面起着十分重要的作用，作者在对汉语句法结构、句子长度和和呼吸群划分之间关系的研究基础上，设计并实现了基于句子长度和句法结构的呼吸群边界划分算法；为更好地描述文语转换过程，作者提出了适合汉语语音合成的SSML韵律标注语言，该标注语言不仅从声学层上对语音的韵律进行描述，而且从语言学层上标注句法结构信息，最后本文对基于语言理解的韵律规则用SSML进行了描述并用实验验证了语言学层面的标注对系统自然度的影响。

Speech recognition is one of the important contents of the speech signal processing, and how to increase the preciseness in speech recognition is the mainly intention of the speech recognition research.

语音识别是语音信号处理的重要内容之一，如何提高语音识别的正确率则是语音识别研究的主要目的。

Keyword spotting is an important area in speech recognition. Its objective is to identify and verify a few specified key-words in continuous speech.

关键词识别是语音识别研究中的一个重要领域，其目的是从连续语音中检测并确认给定的若干个特定关键词。

It has settled hidden markov model a dominant position in the area of speech acoustic and linguistic modeling that more 30 years application and development in speech recognition.

本文提出了矢量量化中初始码本设计应该遵循的准则，即训练矢量空间中初始码字的分布应该使码字聚类形成的胞腔在总畸变上而不是在空间体积上尽可能均衡。

The history and current situation of research in speech recognition are proposed all-sidedly and systematically. We probe into such topics about acoustic features, phonetic features, phonologic features and auditory perception in terms of related theory and disciplines. Furthermore, we summarize and analyze focus in current theoretical and technical aspects of speech recognition and immediately put an insight into challenge to speech recognition presently, even in a long time.

论文全面、系统地介绍了国内外语音识别的发展历史和发展现状，结合相关学科的知识，分析了语音声学特征、语音学特征、音系学特征及其语音感知等有关问题，分析并总结了目前语音识别理论和技术实现方面的研究重点以及目前、甚至在相当长的时期内语音识别面临的挑战。

In speech communication, almost half of the time is the silence state, which contains much redundant information need to be taken away to improve code efficiency, so the silence frame should be compressed; On the other hand, to satisfy people's listening feelings, speech code implemented on UWB would be a new future's research direction on speech code. Nowadays the compression on narrow band or wideband have been studied a lot, but the silence compression on UWB need to be studied more, which is the main job of this paper.

在语音通信中，平均一半的时间处于无语音的空闲状态，这里蕴含着大量的冗余信息，所以去掉这些冗余信息将会大幅度的提高语音编码的传输效率，这就需要对静音信号进行压缩；此外，为了满足人们听觉享受，在高带上实现语音编码也将成为未来的研究方向，现如今窄带和宽带的静音压缩技术已经较为成熟，但高带的静音压缩技术尚待发展，这也正是本文研究的必要性。

Methods 22 parients(35 ears)had been tested in three noises, including white noise,speech noiseand babble noise.BN was recorded when 8～12 persons were talking at same time.The monosyllabic phonetic balance word list was made by Shen Ye in 1983 and every list includs twenty-five words,Meantime ,the effect to speech discrimination score curve was tested in different signal to noise ratio.

目的 为了观察传导性聋患者在噪声竞争下言语清晰度曲线及不同噪声对清晰度曲线的不同影响；方法测试22名(35耳)传导性聋患者三种不同噪声竞争下测得的言语识别率结果，这三种噪声为①白噪声(white noise，WN)，②言语噪声(speech noise，SN)，③多人谈话声(babble noise，BN)，即由8～12人同时讲话录制而成，其频谱与言语长时平均频谱接近。

I didn't watch TV last night, because it .

昨晚我没有看电视，因为电视机坏了。

Since this year, in a lot of villages of Beijing, TV of elevator liquid crystal was removed.

今年以来，在北京的很多小区里，电梯液晶电视被撤了下来。