结果表明，非语音是设计听觉用户界面的可行途径。
The results show that aural user interface design using non-speech sound is feasible.
在非语音间隔使用不连续传输和噪音填充的不同比率运行的选择也是可能的。
An option for variable rate operation using discontinuous transmission and noise fill during non-speech intervals is also possible.
描写音变又包括语流音变、位置音变与非语音原因的音变；历史音变则分为有规律的演变与特殊的变化两小类。
Descriptive sound change consists of changes in sound flow, sound position and some other non-phonetic aspects while historical phonetic change is divided into two subtypes.
语音信号的端点检测技术就是从包含语音的一段信号中准确地确定语音的起始点和终止点，区分语音和非语音信号。
The endpoint detection technology of speech signal is to accurately determine starting point and ending point from a section of speech signal. Thus it can distinguish speech and non-speech signal.
演员们会花成小时的时间反复练习他们的台词，语音语调的变化和每个时刻的非语言立场。
Actors spend hours practicing their lines, the different inflections of their voice and the non-verbal stance of the moment.
例如，一个处理关键语音事件的服务与用来收集非关键性能统计数据的服务，两者处于不同的进程中。
For example, a service providing essential telephony event processing would be in a different process than a service collecting nonessential performance statistics.
一直以来，心理学家在不断研究非语言类的交流方式，比如小声嘀咕或者使个眼色之类的，这些口头语音和面部表情也能体现人的情感。
Psychologists have long studied the grunts and winks of nonverbal communication, the vocal tones and facial expressions that carry emotion.
汉字并不是拼音文字，是一种非形态的、以形表意的文字体系，汉字的形体不表示汉语的语音。
Character is a non-formula character system with its form expressing its meaning not the phonetic sound , totally different from Pinyin.
非语言交际包括语音质量，眼睛运动，面部表情和身体的动作，如手势和身体姿势的变化。
Nonverbal communication includes voice quality, eyes movement, facial expression and body movements such as gestures and change in body position.
举例说，不需要再被语音邮件充斥，联系人可以得知某人正在某个非关键性的会议，因此可以选择向他发送一条措辞谨慎的即时消息。
Instead of filling up voice mail, for example, correspondents will see that someone is in a non-critical meeting and shoot him or her a discreet im.
实验表明，MAP算法可以有效地降低汉语数码语音识别对被适应人的误识率，而且对非自适应人性能影响很小。
The experiment shows that the MAP algorithm can considerably reduce the error rate of Mandarin digital speech recognition on the adapted speaker and cause little influence on the non-adapted speakers.
首先通过阈值判决区分静音和非静音，然后利用VQ-GMM分类器将非静音进而分为语音、音乐和环境背景音。
Firstly silence and non-silence are classified based on threshold judging and then VQ-GMM is used to further classify non-silence into speech, music and background.
介绍了面向中英文双语应用的英文语音合成系统中基于混合基元模型的非定长基元选取算法。
This paper presents hybrid unit model based non-uniform unit selection in Chinese and English bilingual application oriented English text-to-speech system.
非齐次hmm模型是提高语音识别性能的潜在的重要方法。
Using the inhomogeneous HMM is a potential way to improve the performance of speech recognition system.
本文提出了“形式词”概念，并在形式词的基础上，进一步研究了确定切词单位的非语法因素，包括语义因素、语音因素。
Based on the conception of formal word, the author inquires into the non grammatical factors for determination of segmentation element. They include the semantic factors, phonetic factors.
针对语音激活检测的鲁棒性问题，提出在非平稳噪声环境下使用基于复高斯混合模型的鲁棒语音激活检测算法。
In order to improve the robustness of voice activity detection (VAD), the use of an algorithm based on complex Gaussian mixture model under nonstationary noisy environments was presented.
携带着大量信息的语音信号本身是非常复杂的，并且具有非平稳性、时变性等特征。
Speech signal, carrying a large amount of information, is so complex with the character of non-stationary and time-varying.
实验表明，MAP算法可以有效地降低汉语数码语音识别对被适应人的误识率，而且对非自适应人性能影响很小。
The experiment shows that the MAP algorithm can considerably reduce the error rate of Mandarin digital speech recognition on the adapted speaker and cause litt...
口吃者与非口吃者在词长效应上的差异是口吃语音编码缺陷的一个重要的支持证据。
The difference of word length effect between PWS and people who do not stutter (PWNS) provided important support for the phonological encoding deficit hypothesis of stuttering.
双通路模型理论认为语音的通达存在两条通路，即词典通路和非词典通路。
There are two routes about phonological access in dual route model, lexical route and non-lexical route.
然而，语音信号是一个非平稳过程，因此适用于周期信号、瞬变信号或平稳随机信号的标准傅立叶变换不能用来直接表示语音信号。
But voice signal is an instable process, so standard FT that fit to the period signal and stable signal can not be express the voice signal directly.
该语音库支持使用有限词汇的非文本输入的说话人识别系统的开发、训练和测试。
The YOHO speaker verification Corpus supports development, training and testing of speaker verification systems that use limited vocabulary, free-text input.
本建议提出评估低速率数字语音(或更普遍地说数字源)编码器对于非话音信号的性能的方法。
In this Recommendation, an evaluation methodology is presented for the characterization of low-rate digital speech (or more generally source) coder performance with non-voice signals.
它不仅适用于亲属语言内部语音、语法规则的历史比较，也适用于非亲属语言之间某些语言要素的比较。
It not only applies to historical comparison between rules of phonology and those of grammar in relative languages, but also applies to some linguistic elements beyond relative languages.
将普通的文本转换为剧本，同时将文字语音化，把隐含在文字中的非语言信息，通过虚拟机器人以适当的肢体语言表达出来。
The text will be converted into ordinary script and text is changed into speeches, nonverbal information which embedded in contexts is expressed with body languages through virtual robot.
该方法利用掌声与非掌声事件之间的时长和基音频率差异，无需构建复杂的统计模型就能检测出会议语音中的掌声。
The proposed approach can detect applause in meeting speech by only using the differences of duration and pitch between applause and non-applause events, without using any complex statistical models.
该方法利用掌声与非掌声事件之间的时长和基音频率差异，无需构建复杂的统计模型就能检测出会议语音中的掌声。
The proposed approach can detect applause in meeting speech by only using the differences of duration and pitch between applause and non-applause events, without using any complex statistical models.
应用推荐