语音

Lastly, combine the vision track module and voice recognize module, and debug the whole system, note the experiment result.

将视觉跟踪模块与语音识别模块结合起来，根据基于视觉与语音鼠标的体系结构进行设计，编写全部程序进行系统的整体调试，调试成功后进行预定的实验，记录实验结果。

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。

So, extract the voicing features of speech signal play an important role in speech signal processing.

因此，语音信号特征提取在语音信号处理应用中具有举足轻重的地位。

The following functions are used with waveform audio.

通常无论是语音识别还是语音合成，都不会去使用音频文件，而是直接通过控制声卡来

Primary phonological iconicity is sub-divided into auditory iconicity, articulary iconicity and associative iconicity.

而次要语音象似主要是指人在交流中的语音语调符合语境和说话者的心情态度等。

New measures of confusability for multiple-pronunciation dictionaries were developed and shown to have a very strong correlation with the recognition performance. With the proposed framework, it was shown that the confusability as measured can be reduced and recognition performance improved stage by stage.

另外，我们也在第七章中提出了新方法来衡量词典中各种发音的混淆度，实验结果显示衡量出来的混淆度跟语音辨识率有很大的相关性，而且这个架构所建立的发音变异词典可以有效地降低混淆度和语音辨识的错误率。

In mandarin digit speech recognition,"2" and "8" are the most confusable pair of words.

在汉语数码语音识别中，&2&和&8&是最易混淆的一对语音。

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。

Aimed at non-stationary and time-correlation property of the natural speech signals,a new online time-domain blind separation algorithm is proposed for convolutive mixtures of natural speech.

针对语音信号所具有的非平稳性和时域相关性，提出了一种新的卷积混合语音信号盲分离的在线时域算法。

Features Include:-Intelligent Voice Dictation with rapid correction ability -Document Player that can convert any document into audible files for later playback -Default and Creatable Voice Shortcuts that run programs, open documents or lead to Websites at your Command -Audible Announcement of OS messages -Multiple Voices to choose from -Continuous Evolution: Constant free updates to registered users.

功能包括：智能语音听写与迅速纠正的能力，文件播放器，可以转换成任何文件声音文件供以后播放，违约和Creatable语音快捷的运行程序，打开文件或导致网站在您的命令声短片的OS邮件，多选择的声音从连续进化：免费的恒定更新的注册用户。

Breath, muscle contraction of the buttocks; arch body, as far as possible to hold his head, right leg straight towards the ceiling (peg-leg knee in order to avoid muscle tension).

呼气，收缩臀部肌肉；拱起身体，尽量抬起头来，右腿伸直朝向天花板（膝微屈，以避免肌肉紧张）。

The cost of moving grain food products was unchanged from May, but year over year are up 8%.

粮食产品的运输费用与5月份相比没有变化，但却比去年同期高8％。