公开(公告)号：US20050144015A1

公开(公告)日：2005-06-30

申请号：US10730540

申请日：2003-12-08

Applicant: Ciprian Agapi ,  Felipe Gomez ,  James Lewis ,  Vanessa Michelini ,  Sibyl Sullivan

Inventor： Ciprian Agapi ,  Felipe Gomez ,  James Lewis ,  Vanessa Michelini ,  Sibyl Sullivan

IPC: G10L15/24 ,  G10L11/00

CPC classification number: G10L15/24

Abstract: A method and system of identifying and optimizing audio segments in a speech application program. Audio segments are identified and extracted from a speech application program. The audio segments containing audio text to be recorded are then optimized in order to facilitate the recording of the audio text. The optimization of the extracted audio segments may include accounting for programmed pauses and variables in the speech application code, identifying multi-sentence segments and the presense of duplicate audio segments, and accounting for the effects of coarticulation.

Abstract translation: 一种在语音应用程序中识别和优化音频段的方法和系统。 从语音应用程序中识别和提取音频段。 然后对包含要记录的音频文本的音频片段进行优化，以便于录制音频文本。 所提取的音频片段的优化可以包括对语音应用代码中的编程暂停和变量进行计算，识别多句段和重复音频段的预言，并且考虑到coarticulation的影响。

公开(公告)号：US09583096B2

公开(公告)日：2017-02-28

申请号：US11464512

申请日：2006-08-15

Applicant: Ciprian Agapi ,  Musaed A. Almutawa ,  Oscar J. Blass ,  Patrick M. Commarford ,  Roberto Vila

Inventor： Ciprian Agapi ,  Musaed A. Almutawa ,  Oscar J. Blass ,  Patrick M. Commarford ,  Roberto Vila

IPC: G10L21/00 ,  G10L15/07 ,  G10L15/26

CPC classification number: G10L15/07 ,  G10L15/265

Abstract: A method for state transition in voice systems including: generating one or more stackable state macros, each of the one or more stackable state macros including a plurality of commands; saving the current state before executing another macro; enabling restoring the previous state after a plurality of commands is completed, allowing a user to utter voice commands to restore the individual state of components or the voice systems as a whole to the previous state or to a known home state. The method further utilizes voice commands not specific to the current state and is used specifically for automatically controlling a plurality of components of a vehicle.

Abstract translation: 一种用于语音系统中的状态转换的方法，包括：产生一个或多个可堆叠状态宏，所述一个或多个可堆叠状态宏中的每一个包括多个命令; 在执行另一个宏之前保存当前状态; 在多个命令完成之后能够恢复先前的状态，允许用户发出语音命令以将组件或语音系统的单个状态整体恢复到先前状态或已知的家庭状态。 该方法还利用不特定于当前状态的语音命令，并且专门用于自动控制车辆的多个部件。

公开(公告)号：US09349367B2

公开(公告)日：2016-05-24

申请号：US12109167

申请日：2008-04-24

Applicant: Ciprian Agapi ,  William K. Bodin ,  Charles W. Cross, Jr. ,  Pradeep P. Mansey

Inventor： Ciprian Agapi ,  William K. Bodin ,  Charles W. Cross, Jr. ,  Pradeep P. Mansey

IPC: G10L15/00 ,  G10L15/08 ,  G10L15/183 ,  G10L15/22

CPC classification number: G10L15/22 ,  G10L15/00 ,  G10L15/08 ,  G10L15/183

Abstract: Methods, apparatus, and products are disclosed for record disambiguation in a multimodal application operating on a multimodal device, the multimodal device supporting multiple modes of interaction including at least a voice mode and a visual mode, that include: prompting, by the multimodal application, a user to identify a particular record among a plurality of records; receiving, by the multimodal application in response to the prompt, a voice utterance from the user; determining, by the multimodal application, that the voice utterance ambiguously identifies more than one of the plurality of records; generating, by the multimodal application, a user interaction to disambiguate the records ambiguously identified by the voice utterance in dependence upon record attributes of the records ambiguously identified by the voice utterance; and selecting, by the multimodal application for further processing, one of the records ambiguously identified by the voice utterance in dependence upon the user interaction.

Abstract translation: 公开了用于在多模式设备上操作的多模式应用中的记录消歧的方法，装置和产品，所述多模式设备支持包括至少语音模式和视觉模式的多种交互模式，其包括：由多模式应用提示， 用户识别多个记录中的特定记录; 由多模式应用程序响应于该提示，接收来自用户的语音发声; 由所述多模式应用程序确定所述语音发音含糊地识别所述多​​个记录中的多于一个的记录; 由多模式应用程序产生用户交互，以消除由声音话语模糊识别的记录，依赖于由语音话语模糊识别的记录的记录属性; 以及通过多模式应用程序进行进一步处理，根据用户交互，通过语音话语模糊识别的记录之一。

公开(公告)号：US08799001B2

公开(公告)日：2014-08-05

申请号：US10715316

申请日：2003-11-17

Applicant: Ciprian Agapi ,  Felipe Gomez ,  James R. Lewis ,  Vanessa V. Michelini ,  Sibyl C. Sullivan

Inventor： Ciprian Agapi ,  Felipe Gomez ,  James R. Lewis ,  Vanessa V. Michelini ,  Sibyl C. Sullivan

IPC: G10L15/22

CPC classification number: G10L13/027

Abstract: A method and system for defining standard catch styles used in generating speech application code for managing catch events, in which a style-selection menu that allows for selection of one or more catch styles is presented. Each catch style represents a system response to a catch event. A catch style can be selected from the style-selection menu. For each selected catch style, the system can prepare a response for each catch event. If the selected catch style requires playing a new audio message in response to a particular catch event, a contextual message can be entered in one or more text fields. The contextual message entered in each text field corresponds to the new audio message that will be played in response to the particular catch event. In certain catch styles, the entered contextual message is different for each catch event, while in other catch styles, the entered contextual message is the same for each catch event. Finally, if the selected catch style does not require playing of a new audio message in response to a particular catch event, the system can replay the system prompt.

Abstract translation: 一种用于定义用于生成用于管理捕捉事件的语音应用程序代码的标准捕获样式的方法和系统，其中呈现允许选择一个或多个捕捉样式的样式选择菜单。 每个catch样式表示对catch事件的系统响应。 可以从样式选择菜单中选择捕捉样式。 对于每个选定的捕捉样式，系统可以为每个捕获事件准备响应。 如果选择的捕捉样式需要响应于特定的捕获事件播放新的音频消息，则可以在一个或多个文本字段中输入上下文消息。 在每个文本字段中输入的上下文消息对应于将响应于特定捕获事件而播放的新的音频消息。 在某些catch样式中，输入的上下文消息对于每个catch事件是不同的，而在其他catch样式中，输入的上下文消息对于每个catch事件是相同的。 最后，如果所选抓取样式不需要播放响应于特定捕获事件的新音频消息，则系统可以重播系统提示。

公开(公告)号：US20120053934A1

公开(公告)日：2012-03-01

申请号：US13289233

申请日：2011-11-04

Applicant: Ciprian Agapi ,  William K. Bodin ,  Charles W. Cross, JR. ,  Michael H. Mirt

Inventor： Ciprian Agapi ,  William K. Bodin ,  Charles W. Cross, JR. ,  Michael H. Mirt

IPC: G10L15/20

CPC classification number: G10L15/01

Abstract: Methods, systems, and products for testing a grammar used in speech recognition for reliability in a plurality of operating environments having different background noise that include: receiving recorded background noise for each of the plurality of operating environments; generating a test speech utterance for recognition by a speech recognition engine using a grammar; mixing the test speech utterance with each recorded background noise, resulting in a plurality of mixed test speech utterances, each mixed test speech utterance having different background noise; performing, for each of the mixed test speech utterances, speech recognition using the grammar and the mixed test speech utterance, resulting in speech recognition results for each of the mixed test speech utterances; and evaluating, for each recorded background noise, speech recognition reliability of the grammar in dependence upon the speech recognition results for the mixed test speech utterance having that recorded background noise.

Abstract translation: 用于在具有不同背景噪声的多个操作环境中测试用于语音识别中的语法的可靠性的方法，系统和产品，包括：为所述多个操作环境中的每一个接收记录的背景噪声; 产生语音识别引擎使用语法进行识别的测试语音语音; 将测试语音发音与每个记录的背景噪声混合，导致多个混合测试语音话语，每个混合测试语音话语具有不同的背景噪声; 对于每个混合测试语音话语，使用语法和混合测试语音话语进行语音识别，导致每个混合测试语音话语的语音识别结果; 并且对于每个记录的背景噪声，根据具有记录的背景噪声的混合测试语音话语的语音识别结果，评估语法的语音识别可靠性。

公开(公告)号：US08082148B2

公开(公告)日：2011-12-20

申请号：US12109204

申请日：2008-04-24

Applicant: Ciprian Agapi ,  William K. Bodin ,  Charles W. Cross, Jr. ,  Michael H. Mirt

Inventor： Ciprian Agapi ,  William K. Bodin ,  Charles W. Cross, Jr. ,  Michael H. Mirt

IPC: G10L15/20

CPC classification number: G10L15/01

Abstract: Methods, systems, and products for testing a grammar used in speech recognition for reliability in a plurality of operating environments having different background noise that include: receiving recorded background noise for each of the plurality of operating environments; generating a test speech utterance for recognition by a speech recognition engine using a grammar; mixing the test speech utterance with each recorded background noise, resulting in a plurality of mixed test speech utterances, each mixed test speech utterance having different background noise; performing, for each of the mixed test speech utterances, speech recognition using the grammar and the mixed test speech utterance, resulting in speech recognition results for each of the mixed test speech utterances; and evaluating, for each recorded background noise, speech recognition reliability of the grammar in dependence upon the speech recognition results for the mixed test speech utterance having that recorded background noise.

Abstract translation: 用于在具有不同背景噪声的多个操作环境中测试用于语音识别中的语法的可靠性的方法，系统和产品，包括：为所述多个操作环境中的每一个接收记录的背景噪声; 产生语音识别引擎使用语法进行识别的测试语音语音; 将测试语音发音与每个记录的背景噪声混合，导致多个混合测试语音话语，每个混合测试语音话语具有不同的背景噪声; 对于每个混合测试语音话语，使用语法和混合测试语音话语进行语音识别，导致每个混合测试语音话语的语音识别结果; 并且对于每个记录的背景噪声，根据具有记录的背景噪声的混合测试语音话语的语音识别结果来评估语法的语音识别可靠性。

公开(公告)号：US07797676B2

公开(公告)日：2010-09-14

申请号：US10827852

申请日：2004-04-20

Applicant: Ciprian Agapi ,  Felipe Gomez ,  James R. Lewis ,  Vanessa V. Michelini ,  Sibyl C. Sullivan

Inventor： Ciprian Agapi ,  Felipe Gomez ,  James R. Lewis ,  Vanessa V. Michelini ,  Sibyl C. Sullivan

IPC: G06F9/44 ,  G06F17/00 ,  G06F7/00 ,  G06F3/00 ,  G06F3/048

CPC classification number: G06F8/34 ,  G06Q10/06

Abstract: A method and system for automated code generation in a call flow builder (10) can include a display coupled to a processor. The processor can be programmed to select a real code (database connection) or a prototype code using a graphical interface (20) to provide a selected code and develop a call flow using the selected code. The processor can be programmed to select the prototype code as the selected code, test the call flow in a local development environment and further enable the switching of the selected code from the prototype to the real code to complete a database connection. The processor can be further programmed to enable specification of a default or range of values. Additionally, the processor can be programmed to use a database connection code that replaces a prototype assignment of values to variables when the real code is the selected code.

Abstract translation: 在呼叫流程构建器（10）中用于自动代码生成的方法和系统可以包括耦合到处理器的显示器。 处理器可以被编程为使用图形界面（20）选择真实代码（数据库连接）或原型代码，以提供所选择的代码并使用所选择的代码开发呼叫流程。 处理器可以编程为选择原型代码作为所选代码，测试本地开发环境中的调用流程，并进一步使所选代码从原型切换到实际代码以完成数据库连接。 处理器可以被进一步编程以使得能够指定默认值或范围值。 此外，当实际代码是所选择的代码时，处理器可以被编程为使用数据库连接代码来代替值的原型分配给变量。

公开(公告)号：US07787598B2

公开(公告)日：2010-08-31

申请号：US11170120

申请日：2005-06-29

Applicant: Ciprian Agapi ,  Michael H. Mirt ,  Charles Sumner

Inventor： Ciprian Agapi ,  Michael H. Mirt ,  Charles Sumner

IPC: H04M1/24 ,  H04M3/08 ,  H04M3/22

CPC classification number: H04M3/323 ,  H04M3/493 ,  H04Q1/45

Abstract: A method (100) and system (30) to enable automatic generation and testing of voice applications includes generating (102) a test driver application (TDA) (32) and generating (104) a modified original voice application (34) to be tested by the TDA within a call flow builder (10). The modified application can include or generate (106) “test hooks” or more particularly DTMF tones and DTMF grammars that can be used to synchronize the modified original voice application with the TDA. The TDA can test (110) all possible paths of the modified original voice application. Note the TDA and the modified original voice application can be generated and/or tested (112) in a test environment within the call flow builder or a telephony environment. The TDA can be automatically generated (108) to exercise all possible flows where the DTMF tones define the current state and location of the modified application.

Abstract translation: 实现语音应用的自动生成和测试的方法（100）和系统（30）包括生成（102）测试驱动器应用（TDA）（32）并生成（104）待测试的修改的原始语音应用（34） 由TDA在呼叫流程构建器（10）内。 经修改的应用程序可以包括或生成（106）“测试挂钩”，或更具体地可以用于将修改的原始语音应用与TDA同步的DTMF音和DTMF语法。 TDA可以测试（110）修改的原始语音应用程序的所有可能路径。 请注意，TDA和修改的原始语音应用程序可以在呼叫流程构建器或电话环境中的测试环境中生成和/或测试（112）。 TDA可以被自动生成（108）来运行所有可能的流，其中DTMF音定义了修改后的应用的当前状态和位置。

公开(公告)号：US20090271189A1

公开(公告)日：2009-10-29

申请号：US12109204

申请日：2008-04-24

Applicant: Ciprian Agapi ,  William K. Bodin ,  Charles W. Cross, JR. ,  Michael H. Mirt

Inventor： Ciprian Agapi ,  William K. Bodin ,  Charles W. Cross, JR. ,  Michael H. Mirt

IPC: G10L15/00

CPC classification number: G10L15/01

Abstract: Methods, systems, and products for testing a grammar used in speech recognition for reliability in a plurality of operating environments having different background noise that include: receiving recorded background noise for each of the plurality of operating environments; generating a test speech utterance for recognition by a speech recognition engine using a grammar; mixing the test speech utterance with each recorded background noise, resulting in a plurality of mixed test speech utterances, each mixed test speech utterance having different background noise; performing, for each of the mixed test speech utterances, speech recognition using the grammar and the mixed test speech utterance, resulting in speech recognition results for each of the mixed test speech utterances; and evaluating, for each recorded background noise, speech recognition reliability of the grammar in dependence upon the speech recognition results for the mixed test speech utterance having that recorded background noise.

Abstract translation: 用于在具有不同背景噪声的多个操作环境中测试用于语音识别中的语法的可靠性的方法，系统和产品，包括：为所述多个操作环境中的每一个接收记录的背景噪声; 产生语音识别引擎使用语法进行识别的测试语音语音; 将测试语音发音与每个记录的背景噪声混合，导致多个混合测试语音话语，每个混合测试语音话语具有不同的背景噪声; 对于每个混合测试语音话语，使用语法和混合测试语音话语进行语音识别，导致每个混合测试语音话语的语音识别结果; 并且对于每个记录的背景噪声，根据具有记录的背景噪声的混合测试语音话语的语音识别结果，评估语法的语音识别可靠性。

公开(公告)号：US20090271188A1

公开(公告)日：2009-10-29

申请号：US12109151

申请日：2008-04-24

Applicant: Ciprian Agapi ,  William K. Bodin ,  Charles W. Cross, JR. ,  Paritosh D. Patel

Inventor： Ciprian Agapi ,  William K. Bodin ,  Charles W. Cross, JR. ,  Paritosh D. Patel

IPC: G10L15/00

CPC classification number: G10L21/0208 ,  G10L15/20

Abstract: Methods, apparatus, and products are disclosed for adjusting a speech engine for a mobile computing device based on background noise, the mobile computing device operatively coupled to a microphone, that include: sampling, through the microphone, background noise for a plurality of operating environments in which the mobile computing device operates; generating, for each operating environment, a noise model in dependence upon the sampled background noise for that operating environment; and configuring the speech engine for the mobile computing device with the noise model for the operating environment in which the mobile computing device currently operates.

Abstract translation: 公开了用于基于背景噪声调整用于移动计算设备的语音引擎的方法，装置和产品，该移动计算设备可操作地耦合到麦克风，其包括：通过麦克风对多个操作环境的背景噪声进行采样 其中移动计算设备运行; 根据所述操作环境的采样背景噪声，为每个操作环境产生噪声模型; 以及为移动计算设备当前操作的操作环境的噪声模型配置移动计算设备的语音引擎。