专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

121. 发明授权

US08655651B2 Method, computer, computer program and computer program product for speech quality estimation 有权
标题翻译：方法，计算机，计算机程序和用于语音质量估计的计算机程序产品
公开(公告)号：US08655651B2
公开(公告)日：2014-02-18
申请号：US13384882
申请日：2010-07-26
申请人： Volodya Grancharov , Mats Folkesson
发明人： Volodya Grancharov , Mats Folkesson
IPC分类号： G10L25/00 , G10L19/00 , G10L19/12 , G10L21/00 , G10L19/02 , H04R29/00 , H03G3/20 , H04B17/02
CPC分类号： G10L25/69
摘要： The invention relates to a method, computer, computer program and computer program product for speech quality estimation. The method comprises the steps of: determining a coding distortion parameter (QCOD), a bandwidth related distortion parameter (BW) and a presentation level distortion parameter (PL) of a speech signal; extracting a first coefficient (ωl) and a second coefficient (ω2), the first coefficient and the second coefficient being dependent on the coding distortion parameter; and calculating a signal quality measure (Q), where the signal quality measure is QCOD+ω1BW+ω2PL using the signal quality measure in a quality estimation of the speech signal.
摘要翻译：本发明涉及用于语音质量估计的方法，计算机，计算机程序和计算机程序产品。该方法包括以下步骤：确定语音信号的编码失真参数（QCOD），带宽相关失真参数（BW）和呈现级别失真参数（PL）; 提取第一系数（omega）和第二系数（omega2），第一系数和第二系数取决于编码失真参数; 以及使用所述语音信号的质量估计中的所述信号质量测量来计算信号质量测量（Q），其中所述信号质量度量是QCOD +ω1BW+ω2PL。

122. 发明授权

US08645143B2 Systems and methods of performing speech recognition using global positioning (GPS) information 有权
标题翻译：使用全球定位（GPS）信息执行语音识别的系统和方法
公开(公告)号：US08645143B2
公开(公告)日：2014-02-04
申请号：US11799172
申请日：2007-05-01
申请人： Todd F. Mozer
发明人： Todd F. Mozer
IPC分类号： G10L21/00 , G10L25/00
CPC分类号： G10L2015/227 , G10L2015/228
摘要： Embodiments of the present invention improve content selection systems and methods using speech recognition. In one embodiment, the present invention includes a speech recognition method comprising receiving location parameters from a global positioning system, retrieving location data using the location parameters, and configuring one or more recognition sets of a speech recognizer using the location data.
摘要翻译：本发明的实施例改进了使用语音识别的内容选择系统和方法。在一个实施例中，本发明包括语音识别方法，其包括从全球定位系统接收位置参数，使用位置参数检索位置数据，以及使用位置数据配置语音识别器的一个或多个识别集。

123. 发明授权

US08639515B2 Extending voice-based markup using a plug-in framework 有权
标题翻译：使用插件框架扩展基于语音的标记
公开(公告)号：US08639515B2
公开(公告)日：2014-01-28
申请号：US11271594
申请日：2005-11-10
申请人： Brien H. Muschett , Wendi L. Nusbickel
发明人： Brien H. Muschett , Wendi L. Nusbickel
IPC分类号： G10L21/00 , G10L25/00
CPC分类号： H04M3/4936
摘要： A method for extending supported voice markup. The method can include a step of identifying a reference implementation (RI) for a software component that interprets voice-based markup. The RI can define a manner that the software component interprets voice-based markup. At least one plug-in can be identified that contains an extension to the RI. At runtime, the RI can be dynamically modified in accordance with the at least one plug-in. The software component can interpret voice-based markup documents based upon the modified reference implementation.
摘要翻译：扩展支持的语音标记的方法。该方法可以包括识别用于解释基于语音的标记的软件组件的参考实现（RI）的步骤。 RI可以定义软件组件解释基于语音的标记的方式。可以识别至少一个包含RI扩展的插件。在运行时，RI可以根据至少一个插件动态修改。软件组件可以基于修改的参考实现来解释基于语音的标记文档。

124. 发明授权

US08630855B2 Call system and method 有权
标题翻译：呼叫系统和方法
公开(公告)号：US08630855B2
公开(公告)日：2014-01-14
申请号：US12005025
申请日：2007-12-21
申请人： Anthony Oddo
发明人： Anthony Oddo
IPC分类号： G10L15/00 , G10L15/04 , G10L21/00 , G10L25/00
CPC分类号： H04L65/1096 , H04L29/12594 , H04L61/303 , H04L67/14 , H04M3/4935 , H04M2203/154
摘要： A system and method for operating a voice domain name network for use over a telephone network including the steps of a computer taking a call in which a user speaks a name. The system recognizes the spoken name. Then the system checks that the name is on a voice domain list stored in a database where the voice domain name corresponds to an Internet URL. The system creating a record registering the name as a voice domain name if the name corresponds to an Internet URL and if it is not previously registered as a voice domain name and wherein said record includes a registrant and a telephone number for the registrant. Such that future callers who call and speak the name are connected via telephone to the registrant.
摘要翻译：一种用于操作通过电话网络使用的语音域名称网络的系统和方法，包括计算机进行用户说话的呼叫的步骤。系统识别口语名称。然后，系统检查名称是否存在于语音域名对应于Internet URL的数据库中的语音域列表上。如果该名称对应于因特网URL，并且其以前未被注册为语音域名，则该系统创建将该名称注册为语音域名的记录，并且其中所述记录包括注册者的注册人和电话号码。这样呼叫和通话的未来呼叫者通过电话连接到注册人。

125. 发明授权

US08626493B2 Insertion of sounds into audio content according to pattern 失效
标题翻译：根据模式将声音插入音频内容
公开(公告)号：US08626493B2
公开(公告)日：2014-01-07
申请号：US13871025
申请日：2013-04-26
申请人： AT&T Intellectual Property I, L.P.
发明人： Steven N. Tischer
IPC分类号： G06F15/00 , G10L25/00 , G10L21/00 , G10L21/06
CPC分类号： G10L21/00 , G06F21/10 , G06F2221/0704 , G06F2221/0753 , G10L19/018 , G11B27/11 , G11B27/28
摘要： Sounds are inserted into audio content according to a pattern. A library stores humanly perceptible voice sounds. Pattern control information is received that is associated with a device recording the audio content. A pattern is retrieved and washing machine sounds are inserted into the audio content according to the pattern. The humanly perceptible voice sounds are inserted into the audio content according to the pattern to generate a signed audio recording.
摘要翻译：根据图案将声音插入音频内容。图书馆存储人类可感知的声音。接收与记录音频内容的设备相关联的模式控制信息。检索图案，并根据图案将洗衣机声音插入到音频内容中。根据图案将人为可感知的声音插入到音频内容中，以产生签名的音频记录。

126. 发明授权

US08620669B2 Automated sentence planning in a task classification system 有权
标题翻译：任务分类系统中的自动句子计划
公开(公告)号：US08620669B2
公开(公告)日：2013-12-31
申请号：US13470913
申请日：2012-05-14
申请人： Marilyn A. Walker , Owen Christopher Rambow , Monica Rogati
发明人： Marilyn A. Walker , Owen Christopher Rambow , Monica Rogati
IPC分类号： G06F17/27 , G10L15/00 , G10L25/00
CPC分类号： G10L13/027 , G10L15/1822 , G10L15/22 , H04M3/4936 , H04M2201/40 , H04M2203/355
摘要： Disclosed is a task classification system that interacts with a user. The task classification system may include a recognizer that may recognize symbols in the user's input communication, and a natural language understanding unit that may determine whether the user's input communication can be understood. If the user's input communication can be understood, the natural language understanding unit may generate understanding data. The system may also include a communicative goal generator that may generate communicative goals based on the symbols recognized by the recognizer and understanding data from the natural language understanding unit. The generated communicative goals may be related to information needed to be obtained from the user. The system may further include a sentence planning unit that may automatically plan one or more sentences based on the communicative goals generated by the communicative goal generator with at least one of the sentences plans being output to the user.
摘要翻译：公开了与用户交互的任务分类系统。任务分类系统可以包括可以识别用户输入通信中的符号的识别器，以及可以确定用户的输入通信是否可以被理解的自然语言理解单元。如果可以理解用户的输入通信，则自然语言理解单元可以产生理解数据。该系统还可以包括通信目标生成器，其可以基于由识别器识别的符号并且理解来自自然语言理解单元的数据来生成通信目标。所产生的交际目标可能与从用户获得的信息有关。该系统可以进一步包括句子计划单元，其可以基于由通信目标生成器生成的通信目标自动地计划一个或多个句子，其中至少一个句子计划被输出给用户。

127. 发明授权

US08589160B2 Systems and methods for providing an electronic dictation interface 有权
公开(公告)号：US08589160B2
公开(公告)日：2013-11-19
申请号：US13213763
申请日：2011-08-19
申请人： Curtis A. Weeks , Aaron G. Weeks , Stephen E. Barton
发明人： Curtis A. Weeks , Aaron G. Weeks , Stephen E. Barton
IPC分类号： G10L21/00 , G10L25/00 , G10L15/00 , G10L17/00 , G10L19/00 , G06F15/16 , G06F3/048
CPC分类号： G10L15/26 , G06F3/167 , G10L15/28 , G10L15/30
摘要： Some embodiments disclosed herein store a target application and a dictation application. The target application may be configured to receive input from a user. The dictation application interface may include a full overlay mode option, where in response to selection of the full overlay mode option, the dictation application interface is automatically sized and positioned over the target application interface to fully cover a text area of the target application interface to appear as if the dictation application interface is part of the target application interface. The dictation application may be further configured to receive an audio dictation from the user, convert the audio dictation into text, provide the text in the dictation application interface and in response to receiving a first user command to complete the dictation, automatically copy the text from the dictation application interface and inserting the text into the target application interface.

128. 发明授权

US08577682B2 System and method to use text-to-speech to prompt whether text-to-speech output should be added during installation of a program on a computer system normally controlled through a user interactive display 有权
标题翻译：使用文本到语音来提示在通常通过用户交互显示控制的计算机系统上的程序安装期间是否应该添加文本到语音输出的系统和方法
公开(公告)号：US08577682B2
公开(公告)日：2013-11-05
申请号：US11260575
申请日：2005-10-27
申请人： Peter T. Brunet , Anh Quy Lu , Mark Edward Nosewicz , Lawrence Frank Weiss
发明人： Peter T. Brunet , Anh Quy Lu , Mark Edward Nosewicz , Lawrence Frank Weiss
IPC分类号： G10L21/06 , G10L25/00 , G10L13/00 , G10L13/08
CPC分类号： G06F8/61 , G06F8/60 , G06F9/453
摘要： An auditory user interactive interface to an application program being installed in the computer controlled system. A routine in an object, in an application program being installed in the computer controlled system for providing an auditory user interface to the program in combination with auditory means for offering the user of the computer controlled system the auditory user interface during installation of said application program, and responsive to the selection of the auditory interface provides the auditory user interface during said installation of the application program. The functional object in the application program being installed includes the routine for providing the auditory interface preferably implemented in Text to Speech (TTS) functions together with an implementation for determining whether the computer controlled system receiving the application program includes a TTS engine compatible with the TTS functions in the application program and a routine for installing a TTS engine compatible with the routine when the computer controlled system does not include the TTS engine.
摘要翻译：用于安装在计算机控制系统中的应用程序的听觉用户交互界面。一种应用程序中的例程，安装在计算机控制系统中，用于提供与该程序的听觉用户界面结合用于在安装所述应用程序期间向计算机控制系统的用户提供听觉用户界面的听觉装置并且响应于所述听觉界面的选择在所述安装应用程序期间提供听觉用户界面。正在安装的应用程序中的功能对象包括用于提供听觉界面的例程，优选地以文本到语音（TTS）功能实现，以及用于确定接收到应用程序的计算机控制系统是否包括与TTS兼容的TTS引擎的实现应用程序中的功能以及当计算机控制系统不包括TTS引擎时安装与该程序兼容的TTS引擎的例程。

129. 发明申请

US20050060145A1 Closed caption signal processing apparatus and method 有权
标题翻译：闭路字幕信号处理装置及方法
公开(公告)号：US20050060145A1
公开(公告)日：2005-03-17
申请号：US10899007
申请日：2004-07-27
申请人： Kazuhiko Abe , Yasuyuki Masai , Makoto Yajima , Kohei Momosaki , Koichi Yamamoto , Munehiko Sasajima
发明人： Kazuhiko Abe , Yasuyuki Masai , Makoto Yajima , Kohei Momosaki , Koichi Yamamoto , Munehiko Sasajima
IPC分类号： H04N5/278 , G10L15/00 , G10L15/04 , G10L15/08 , G10L15/10 , G10L15/26 , G10L25/00 , H04N5/04 , H04N5/445 , H04N5/60 , H04N7/08 , H04N7/081 , G10L19/14
CPC分类号： H04N21/4884 , G10L15/26 , H04N5/04 , H04N5/44513 , H04N5/60 , H04N7/0885 , H04N17/04 , H04N21/42661 , H04N21/4307 , H04N21/435 , H04N21/4394 , H04N2017/008
摘要： A closed caption signal processing apparatus comprises a speech recognition unit to recognize speech contents from the speech signal, a speech timing detecting unit to detect a speech timing of the speech contents, a closed caption contents acquisition unit to acquire closed caption contents from the closed caption signal associated with the speech signal, a presentation timing detecting unit to detect a presentation timing of the closed caption contents, an agreement detecting unit to detect an agreement between the speech contents and the closed caption contents, and a time difference calculating unit to calculate a time difference between the speech timing and the presentation timing that are detected on the speech contents and the closed caption contents that agree with each other, respectively.
摘要翻译：闭路字幕信号处理装置包括：语音识别单元，用于从语音信号识别语音内容;语音定时检测单元，用于检测语音内容的语音定时;闭路字幕内容获取单元，从闭路字幕获取隐藏字幕内容与语音信号相关联的信号;呈现定时检测单元，用于检测隐藏字幕内容的呈现定时;协商检测单元，用于检测语音内容和隐藏字幕内容之间的一致性;以及时间差计算单元，分别在语音内容上检测到的语音定时和呈现定时之间的时间差以及彼此一致的隐藏字幕内容。

130. 发明授权

US6094628A Method and apparatus for transmitting user-customized high-quality, low-bit-rate speech 失效
标题翻译：发送用户定制的高质量，低比特率语音的方法和装置
公开(公告)号：US6094628A
公开(公告)日：2000-07-25
申请号：US28111
申请日：1998-02-23
申请人： William Joe Haber , George Thomas Kroncke , William George Schmidt
发明人： William Joe Haber , George Thomas Kroncke , William George Schmidt
IPC分类号： G10L19/00 , G10L25/00 , G10L3/02
CPC分类号： G10L19/00 , G10L25/00
摘要： A method and apparatus for improving the quality and transmission rates of speech is presented. Upon connection of a call with a receiving terminal, a communication unit (12, 26, 28, 42, 57, 54, 60) reads a dynamic user-specific speech characteristics model (SCM) table and user-specific input stimulus table and sends them to an appropriate point in the connection path with the receiving terminal. As normal voice conversation begins, the user's speech is collected into speech frames. The speech frames are compared to input stimuli entries in the user-specific input stimulus table, and are used to calculate SCMs which are compared to dynamic user-specific SCM table entries in the dynamic user-specific SCM table to generate an encoded bit stream. Simultaneously, speech characteristics statistics are collected and analyzed in view of multiple available generic SCMs to update and improve the dynamic user-specific SCM table during the progress of the call to closely track changes in the user's voice.
摘要翻译：提出了一种用于提高语音质量和传输速率的方法和装置。在通话与接收终端连接时，通信单元（12,26,28,42,57,54,60）读取动态用户特定语音特征模型（SCM）表和用户专用输入激励表，并发送它们到与接收终端的连接路径中的适当点。当正常语音对话开始时，用户的语音被收集到语音帧中。将语音帧与用户专用输入激励表中的输入刺激条目进行比较，并且用于计算与动态用户专用SCM表中的动态用户特定SCM表条目进行比较以生成编码比特流的SCM。同时，根据多个可用的通用SCM收集和分析语音特征统计信息，以在通话过程中更新和改进动态用户特定的SCM表，以密切跟踪用户语音的变化。

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