专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US6085162A Translation system and method in which words are translated by a specialized dictionary and then a general dictionary 失效
标题翻译：翻译系统和方法，其中单词由专门词典翻译，然后通用词典翻译
公开(公告)号：US6085162A
公开(公告)日：2000-07-04
申请号：US733808
申请日：1996-10-18
申请人： Julius Cherny
发明人： Julius Cherny
IPC分类号： G10L15/18 , G06F17/27 , G06F17/28 , G10L13/00 , G10L15/00 , G10L9/06
CPC分类号： G06F17/2872 , G06F17/2735 , G06F17/2765 , G06F17/2818 , G06F17/289
摘要： Methods and apparatus for performing translation between different language are provided. The present invention includes a translation system that performs translation having increased accuracy by providing a three-dimensional topical dual-language database. The topical database includes a set of source-to-target language translations for each topic that the database is being used for. In one embodiment, a user first selects the topic of conversation, then words spoken into a telephone are translated and produced as synthesized voice signals from another telephone so that a near real-time conversation may be had between two people speaking different languages. An additional feature of the present invention is the addition of a computer terminal that displays the input and output phrases so that either user may edit the input phrases, or indicate that the translation was ambiguous and request a rephrasing of the material.
摘要翻译：提供用于执行不同语言之间的翻译的方法和装置。本发明包括通过提供三维局部双语言数据库来提高精度的翻译的翻译系统。主题数据库包括数据库正在使用的每个主题的一组源到目标语言翻译。在一个实施例中，用户首先选择对话主题，然后将来自电话的话转换成来自另一个电话的合成语音信号，从而可以在两个不同语言的人之间进行接近实时的对话。本发明的附加特征是添加了显示输入和输出短语的计算机终端，使得任一用户可以编辑输入短语，或指示翻译是不明确的，并请求重新表述材料。

2. 发明授权

US5946658A Cartridge-based, interactive speech recognition method with a response creation capability 有权
标题翻译：基于墨盒的交互式语音识别方法，具有响应创造能力
公开(公告)号：US5946658A
公开(公告)日：1999-08-31
申请号：US165512
申请日：1998-10-02
申请人： Yasunaga Miyazawa , Mitsuhiro Inazumi , Hiroshi Hasegawa , Isao Edatsune , Osamu Urano
发明人： Yasunaga Miyazawa , Mitsuhiro Inazumi , Hiroshi Hasegawa , Isao Edatsune , Osamu Urano
IPC分类号： G10L15/00 , G10L15/06 , G10L15/26 , G10L9/06 , G10L5/02
CPC分类号： G10L15/26 , G10L2015/0638 , G10L2015/088
摘要： A technique for improving speech recognition in low-cost, speech interactive devices. This technique calls for selectively implementing a speaker-specific word enrollment and detection unit in parallel with a word detection unit to permit comprehension of spoken commands or messages when no recognizable words are found. Preferably, specific speaker detection will be based on the speaker's own personal list of words or expression. Other facets include complementing non-specific pre-registered word characteristic information with individual, speaker-specific verbal characteristics to improve recognition in cases where the speaker has unusual speech mannerisms or accent and response alteration in which speaker-specification registration functions are leveraged to provide access and permit changes to a predefined responses table according to user needs and tastes. Also disclosed is the externalization and modularization of non-specific speaker recognition, action and response information to enhance adaptability of the speech recognizer without sacrificing product cost competitiveness or overall device responsiveness.
摘要翻译：一种用于在低成本语音交互设备中改善语音识别的技术。该技术要求与字检测单元并行地选择性地实现与扬声器特定的单词注册和检测单元，以便在找不到可识别的单词时允许理解口语命令或消息。优选地，具体的说话者检测将基于说话者自己的单词或表达的个人列表。其他方面包括补充非特定的预先登记的单词特征信息，具有单独的具有说话者的语言特征，以在讲话者具有不寻常的语音方式或重音和响应改变的情况下改善识别，其中利用说话者说明书注册功能来提供访问并允许根据用户需求和口味对预定义的响应表进行更改。还公开了非特定说话人识别，动作和响应信息的外部化和模块化，以增强语音识别器的适应性，而不牺牲产品成本竞争力或整体设备响应性。

3. 发明授权

US5937380A Keypad-assisted speech recognition for text or command input to concurrently-running computer application 失效
标题翻译：键盘辅助语音识别，用于文本或命令输入到并发运行的计算机应用程序
公开(公告)号：US5937380A
公开(公告)日：1999-08-10
申请号：US105662
申请日：1998-06-26
申请人： Marc H. Segan
发明人： Marc H. Segan
IPC分类号： G10L15/22 , G10L15/24 , G10L15/26 , G10L9/06
CPC分类号： G10L15/24 , G10L15/22
摘要： A method for recognizing a spoken audio signal as input data to a computer includes receiving the spoken audio signal at an input device of the computer, receiving a typed first letter of the spoken audio signal at the input device of the computer and searching through entries that begin with the typed first letter in a dictionary in the computer for a best match with the spoken audio signal.
摘要翻译：用于将口语音频信号识别为作为计算机的输入数据的方法包括在计算机的输入设备处接收口语音频信号，在计算机的输入设备处接收所述口语音频信号的类型化的第一个字母，并通过条目搜索从电脑中的字典中键入的第一个字母开始，以便与口头音频信号最佳匹配。

4. 发明授权

US5924069A Voice-control integrated field support data communications system for maintenance, repair and emergency services 失效
标题翻译：语音控制集成现场支持数据通信系统进行维护，维修和应急服务
公开(公告)号：US5924069A
公开(公告)日：1999-07-13
申请号：US790424
申请日：1997-01-30
申请人： Mark Anthony Kowalkowski , Ronald Charles Koziel , Robert Joseph Kuch , Varudiyam P. Shanmugham
发明人： Mark Anthony Kowalkowski , Ronald Charles Koziel , Robert Joseph Kuch , Varudiyam P. Shanmugham
IPC分类号： G10L15/26 , G10L9/06
CPC分类号： G10L15/26
摘要： A method and apparatus for assisting in the performance of maintenance, repair and emergency services. An integrated field support system is connectable to a customer support center. The integrated field support system comprises a portable platform (a computer), a group of peripheral devices, and a communications interface for accessing the customer support center. The field system allows field personnel to receive displays of documentation, graphics and other pictorial displays, and to issue commands orally for interpretation by a speech recognition unit. The connection to the customer support center provides personnel in that center with all data available to the field personnel and vice versa. Advantageously, this method and apparatus allow field personnel to receive the information they need to perform their tasks in an optimal fashion.
摘要翻译：一种用于协助进行维护，修理和紧急服务的方法和装置。集成的现场支持系统可连接到客户支持中心。集成的现场支持系统包括便携式平台（计算机），一组外围设备和用于访问客户支持中心的通信接口。现场系统允许现场人员接收文件，图形和其他图形显示器的显示器，并且通过语音识别单元口头解释命令。与客户支持中心的连接为该中心的人员提供现场人员可用的所有数据，反之亦然。有利地，该方法和装置允许现场工作人员以最佳方式接收他们执行其任务所需的信息。

5. 发明授权

US5920841A Speech supported navigation of a pointer in a graphical user interface 失效
标题翻译：语音支持图形用户界面中指针的导航
公开(公告)号：US5920841A
公开(公告)日：1999-07-06
申请号：US882667
申请日：1997-06-25
申请人： Claus Schottmuller , Viktor Schwab
发明人： Claus Schottmuller , Viktor Schwab
IPC分类号： G06F3/02 , G06F3/033 , G06F3/041 , G06F3/048 , G06F3/16 , G10L9/06
CPC分类号： G06F3/16 , G06F3/04812
摘要： A method and an apparatus for speech controlled navigation of a pointer in a graphical user interface. Previous methods use speech commands like arrow keys of a keyboard and lack user friendly interfaces. The method and apparatus therefore provides a space of discrete position states (quantization) for the pointer which can be navigated only via those discrete positions by means of speech command input. The granularity of the discrete position states can be adapted to the respective application window and the position states can be represented by a system of coordinates where the speech command input is based on absolute or relative coordinates. Advantageously a copy image of the graphical user interface of operation can be provided in front of or beside the actual user interface and a proxy pointer device is displayed on the copy image. In one embodiment, only the copy image comprises the discrete position states, and the speech input commands are only transferred to the copy image. Navigation of the proxy pointer device within the copy is transferred and converted into commands within the actual user interface. By this method, an operation event effected by a manipulation of the proxy pointer effects a corresponding event at the user interface.
摘要翻译：一种用于图形用户界面中指针的语音控制导航的方法和装置。以前的方法使用诸如键盘的箭头键的语音命令，并且缺少用户友好的接口。因此，该方法和装置为指针提供离散位置状态（量化）的空间，该空间只能通过语音命令输入通过这些离散位置导航。离散位置状态的粒度可以适应于相应的应用窗口，位置状态可以由坐标系统来表示，其中语音命令输入基于绝对坐标或相对坐标。有利地，可以在实际用户界面的前面或旁边提供操作的图形用户界面的复制图像，并且在复制图像上显示代理指针装置。在一个实施例中，仅复印图像包括离散位置状态，并且语音输入命令仅被传送到复制图像。复制内的代理指针设备的导航被传送并转换成实际用户界面内的命令。通过该方法，通过代理指示器的操纵而实现的操作事件在用户界面处产生相应的事件。

6. 发明授权

US5806034A Speaker independent speech recognition method utilizing multiple training iterations 失效
标题翻译：使用多次训练迭代的扬声器独立语音识别方法
公开(公告)号：US5806034A
公开(公告)日：1998-09-08
申请号：US510321
申请日：1995-08-02
申请人： Joe A. Naylor , William Y. Huang , Lawrence G. Bahler
发明人： Joe A. Naylor , William Y. Huang , Lawrence G. Bahler
IPC分类号： G10L15/14 , G10L9/06
CPC分类号： G10L15/144
摘要： A method for recognizing spoken utterances of a speaker is disclosed, the method comprising the steps of providing a database of labeled speech data; providing a prototype of a Hidden Markov Model (HMM) definition to define the characteristics of the HMM; and parameterizing speech utterances according to one of linear prediction parameters or Mel-scale filter bank parameters. The method further includes selecting a frame period for accommodating the parameters and generating HMMs and decoding to specified speech utterances by causing the user to utter predefined training speech utterances for each HMM. The method then statistically computes the generated HMMs with the prototype HMM to provide a set of fully trained HMMs for each utterance indicative of the speaker. The trained HMMs are used for recognizing a speaker by computing Laplacian distances via distance table lookup for utterances of the speaker during the selected frame period; and iteratively decoding node transitions corresponding to the spoken utterances during the selected frame period to determine which predefined utterance is present.
摘要翻译：公开了一种用于识别扬声器的讲话语音的方法，所述方法包括以下步骤：提供标记语音数据的数据库; 提供隐马尔可夫模型（HMM）定义的原型来定义HMM的特征; 并根据线性预测参数或Mel-scale滤波器组参数之一参数化语音话语。该方法还包括通过使用户对每个HMM发出预定义的训练语音话语来选择用于容纳参数的帧周期和生成HMM并解码为指定的语音话语。该方法然后用原型HMM统计计算所生成的HMM，以便为指示说话者的每个话语提供一组经过充分训练的HMM。所训练的HMM用于通过在所选择的帧周期期间通过对说话者的话语的距离表查找来计算拉普拉斯算子来识别扬声器; 并且在所选择的帧周期期间迭代地解码对应于所说话语音的节点转换，以确定哪个预定义的话语存在。

7. 发明授权

US5675705A Spectrogram-feature-based speech syllable and word recognition using syllabic language dictionary 失效
标题翻译：基于谱图特征的语音音节和使用音节语言字典的单词识别
公开(公告)号：US5675705A
公开(公告)日：1997-10-07
申请号：US475767
申请日：1995-06-07
申请人： Tara Chand Singhal
发明人： Tara Chand Singhal
IPC分类号： G10L15/02 , G10L7/08 , G10L9/06
CPC分类号： G10L15/02 , G10L25/18
摘要： A speech recognizing device performing speech syllable recognition and language word identification. The speech syllable recognition is performed on an ensemble composed of nearly one thousand syllables formed by the human vocal system, which allows for variations caused by language dialects and speech accents. For syllable recognition, the nearly one thousand speech syllables, using a spectrogram-feature-based approach, are parsed in a hierarchical structure based on the region of the vocal system from where the syllable emanated from, root syllable from that vocal region, vowel-caused variation of the root syllable, and syllable duration. The syllable's coded representation includes sub-codes for each of the levels of this hierarchical structure. For identification, speech words composed of sequences of coded syllables are mapped to known language words and their grammatical attribute, using a syllabic dictionary where the same words spoken differently map to a known language word.
摘要翻译：执行语音音节识别和语言词识别的语音识别装置。语音音节识别是由由人类声乐系统形成的近千个音节组成的整体进行的，这种语音允许由语言方言和语音口音引起的变化。为了音节识别，使用基于谱图特征的方法将近一千个语音音节以基于声音系统的区域的分层结构进行解析，其中音节从该声部发出，根音从该声部区域，元音 - 导致根音节的变化和音节的持续时间。音节的编码表示包括该层次结构的每个级别的子代码。为了识别，由编码音节序列组成的语音词被映射到已知语言单词及其语法属性，使用音节相同的单词不同地映射到已知语言单词的音节词典。

8. 发明授权

US4592085A Speech-recognition method and apparatus for recognizing phonemes in a voice signal 失效
标题翻译：用于识别语音信号中的音素的语音识别方法和装置
公开(公告)号：US4592085A
公开(公告)日：1986-05-27
申请号：US469114
申请日：1983-02-23
申请人： Masao Watari , Makoto Akabane , Hisao Nishioka , Toshihiko Waku
发明人： Masao Watari , Makoto Akabane , Hisao Nishioka , Toshihiko Waku
IPC分类号： G10L11/00 , G10L15/00 , G10L15/02 , G10L15/20 , G10L21/02 , G10L9/06
CPC分类号： G10L15/00
摘要： Phoneme recognition uses the silence-phoneme and phoneme-phoneme transition spectral information rather than the phoneme information itself. The transition detector features first and second differences in level for each frequency band.
摘要翻译：音素识别使用沉默音素和音素 - 音素转换频谱信息而不是音素信息本身。转换检测器具有每个频带的第一和第二电平差异。

9. 发明授权

US6064958A Pattern recognition scheme using probabilistic models based on mixtures distribution of discrete distribution 失效
标题翻译：基于离散分布的混合分布的概率模型的模式识别方案
公开(公告)号：US6064958A
公开(公告)日：2000-05-16
申请号：US934376
申请日：1997-09-19
申请人： Satoshi Takahashi , Shigeki Sagayama
发明人： Satoshi Takahashi , Shigeki Sagayama
IPC分类号： G06K9/62 , G10L15/14 , G10L9/06
CPC分类号： G10L15/144 , G06K9/6297
摘要： A pattern recognition scheme using probabilistic models that are capable of reducing a calculation cost for the output probability while improving a recognition performance even when a number of mixture component distributions of respective states is small, by arranging distributions with low calculation cost and high expressive power as the mixture component distribution. In this pattern recognition scheme, a probability of each probabilistic model expressing features of each recognition category with respect to each input feature vector derived from each input signal is calculated, where the probabilistic model represents a feature parameter subspace in which feature vectors of each recognition category exist and the feature parameter subspace is expressed by using mixture distributions of one-dimensional discrete distributions with arbitrary distribution shapes which are arranged in respective dimensions. Then, a recognition category expressed by a probabilistic model with a highest probability among a plurality of probabilistic models is outputted as a recognition result.
摘要翻译：使用概率模型的模式识别方案，即使当各种状态的混合分量分布的数量少时，也能够通过以低的计算成本和高的表现力排列分布来提高识别性能，从而降低输出概率的计算成本，混合物成分分布。在该模式识别方案中，计算表示从每个输入信号导出的每个输入特征矢量的每个识别类别的特征的每个概率模型的概率，其中概率模型表示其中每个识别类别的特征向量的特征参数子空间存在，并且通过使用以相应尺寸排列的具有任意分布形状的一维离散分布的混合分布来表示特征参数子空间。然后，输出由多个概率模型中具有最高概率的概率模型表示的识别类别作为识别结果。

10. 发明授权

US5995935A Language information processing apparatus with speech output of a sentence example in accordance with the sex of persons who use it 失效
标题翻译：语言信息处理装置，具有根据使用它的人的性别的句子示例的语音输出
公开(公告)号：US5995935A
公开(公告)日：1999-11-30
申请号：US804119
申请日：1997-02-20
申请人： Nobuki Hagiwara , Kunihiro Seno , Hiromi Furusawa , Kentaro Tsuchiya
发明人： Nobuki Hagiwara , Kunihiro Seno , Hiromi Furusawa , Kentaro Tsuchiya
IPC分类号： G06F3/16 , G06F17/28 , G10L13/00 , G10L13/04 , G10L17/00 , G10L21/06 , H04M11/00 , G10L9/06
CPC分类号： G10L17/00
摘要： When a voice button is pressed after selection of a desired sentence example, a CPU causes a musical note mark to be displayed on a display. If the selected sentence example is one for the opposite sex, the CPU reads out speech data (in a voice of a person of the opposite sex) corresponding to the selected sentence example from a ROM, and causes the readout speech data to be outputted in voice form from a speaker. The selected sentence example is displayed in parenthesis, to show the user that the displayed sentence is for the opposite sex. If the selected sentence example is not one for the opposite sex, the CPU reads out speech data (in a voice of a person of the same sex) corresponding to the selected sentence example from the ROM, and causes the readout speech data to be outputted in voice form from the speaker. Alternatively, speech data corresponding to sentence examples for the opposite sex are not stored in the ROM, and therefore are not outputted in voice form.
摘要翻译：当选择所需的语句示例之后按下语音按钮时，CPU使音符标记显示在显示器上。如果所选择的句子例子是针对异性的，则CPU从ROM中读出对应于所选择的语句示例的语音数据（在异性的人的声音中），并且将读出的语音数据输出到来自演讲者的声音形式。所选句子示例显示在括号中，以向用户显示所显示的句子为异性。如果所选择的句子例子不是针对异性的，则CPU从ROM中读出与所选择的句子对应的语音数据（在同一人的声音中），并且输出读出的语音数据来自演讲者的声音形式。或者，对应于异性的句子示例的语音数据不存储在ROM中，因此不以语音形式输出。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式