-
1.发明授权Systems and methods for improving the accuracy of a transcription using auxiliary data such as personal data 有权使用辅助数据（如个人数据）提高转录准确性的系统和方法公开(公告)号：US09009041B2
公开(公告)日：2015-04-14
申请号：US13190749
申请日：2011-07-26
申请人： George Zavaliagkos , William F. Ganong, III , Uwe H. Jost , Shreedhar Madhavapeddi , Gary B. Clayton
发明人： George Zavaliagkos , William F. Ganong, III , Uwe H. Jost , Shreedhar Madhavapeddi , Gary B. Clayton
CPC分类号： G10L15/26 , G10L15/065 , G10L15/08 , G10L15/24 , G10L15/30 , G10L2015/227
摘要： A method is described for improving the accuracy of a transcription generated by an automatic speech recognition (ASR) engine. A personal vocabulary is maintained that includes replacement words. The replacement words in the personal vocabulary are obtained from personal data associated with a user. A transcription is received of an audio recording. The transcription is generated by an ASR engine using an ASR vocabulary and includes a transcribed word that represents a spoken word in the audio recording. Data is received that is associated with the transcribed word. A replacement word from the personal vocabulary is identified, which is used to re-score the transcription and replace the transcribed word.
摘要翻译： 描述了一种用于提高由自动语音识别（ASR）引擎产生的转录的准确性的方法。 维护包含替换词的个人词汇。 个人词汇中的替换词是从与用户相关联的个人数据获得的。 接收到录音的录音。 转录由使用ASR词汇的ASR引擎生成，并且包括表示音频记录中的口语单词的转录词。 收到与转录词相关联的数据。 识别出个人词汇中的替代词，用于重新得分转录并替换转录词。
-
公开(公告)号：US20120281819A1
公开(公告)日：2012-11-08
申请号：US13101909
申请日：2011-05-05
申请人： Shreedhar Madhavapeddi , William F. Ganong, III , George Zavaliagkos , Uwe H. Jost , Gary B. Clayton
发明人： Shreedhar Madhavapeddi , William F. Ganong, III , George Zavaliagkos , Uwe H. Jost , Gary B. Clayton
IPC分类号： H04M11/00
CPC分类号： H04M3/53358 , G10L15/26 , H04M3/53366 , H04M2201/40 , H04M2203/4536 , H04M2203/4554
摘要： A voicemail computer system transcribes a voicemail message into text that is presented to a calling party for approval. A calling party is able to approve, disapprove or edit a voicemail message prior to delivery to one or more called parties. The voicemail computer system may analyze a voicemail message to detect errors, omissions, or potentially offensive words. The voicemail computer may analyze a voicemail message to make suggestions as to tone, content or information contained within the voicemail message. The calling party can edit the voicemail message or approve it prior to providing a notification to one or more called parties that they have received the voicemail message.
摘要翻译： 语音信箱计算机系统将语音邮件消息转换成呈现给主叫方批准的文本。 主叫方可以在发送给一个或多个被叫方之前批准，不批准或编辑语音邮件消息。 语音邮件计算机系统可以分析语音邮件消息以检测错误，遗漏或潜在令人反感的词语。 语音信箱计算机可以分析语音邮件消息，以提供关于语音邮件消息中包含的音调，内容或信息的建议。 主叫方可以在向一个或多个被叫方提供他们已经收到该语音邮件消息的通知之前编辑该语音邮件消息或者批准它。
-
公开(公告)号：US08913722B2
公开(公告)日：2014-12-16
申请号：US13101909
申请日：2011-05-05
申请人： Shreedhar Madhavapeddi , William F. Ganong, III , George Zavaliagkos , Uwe H. Jost , Gary B. Clayton
发明人： Shreedhar Madhavapeddi , William F. Ganong, III , George Zavaliagkos , Uwe H. Jost , Gary B. Clayton
CPC分类号： H04M3/53358 , G10L15/26 , H04M3/53366 , H04M2201/40 , H04M2203/4536 , H04M2203/4554
摘要： A voicemail computer system transcribes a voicemail message into text that is presented to a calling party for approval. A calling party is able to approve, disapprove or edit a voicemail message prior to delivery to one or more called parties. The voicemail computer system may analyze a voicemail message to detect errors, omissions, or potentially offensive words. The voicemail computer may analyze a voicemail message to make suggestions as to tone, content or information contained within the voicemail message. The calling party can edit the voicemail message or approve it prior to providing a notification to one or more called parties that they have received the voicemail message.
摘要翻译： 语音信箱计算机系统将语音邮件消息转换成呈现给主叫方批准的文本。 主叫方可以在发送给一个或多个被叫方之前批准，不批准或编辑语音邮件消息。 语音邮件计算机系统可以分析语音邮件消息以检测错误，遗漏或潜在令人反感的词语。 语音信箱计算机可以分析语音邮件消息，以提供关于语音邮件消息中包含的音调，内容或信息的建议。 主叫方可以在向一个或多个被叫方提供他们已经收到该语音邮件消息的通知之前编辑该语音邮件消息或者批准它。
-
公开(公告)号：US20130030804A1
公开(公告)日：2013-01-31
申请号：US13190749
申请日：2011-07-26
申请人： George Zavaliagkos , William F. Ganong, III , Uwe H. Jost , Shreedhar Madhavapeddi , Gary B. Clayton
发明人： George Zavaliagkos , William F. Ganong, III , Uwe H. Jost , Shreedhar Madhavapeddi , Gary B. Clayton
IPC分类号： G10L15/26
CPC分类号： G10L15/26 , G10L15/065 , G10L15/08 , G10L15/24 , G10L15/30 , G10L2015/227
摘要： A method is described for improving the accuracy of a transcription generated by an automatic speech recognition (ASR) engine. A personal vocabulary is maintained that includes replacement words. The replacement words in the personal vocabulary are obtained from personal data associated with a user. A transcription is received of an audio recording. The transcription is generated by an ASR engine using an ASR vocabulary and includes a transcribed word that represents a spoken word in the audio recording. Data is received that is associated with the transcribed word. A replacement word from the personal vocabulary is identified, which is used to re-score the transcription and replace the transcribed word.
-
公开(公告)号：US20110268260A1
公开(公告)日：2011-11-03
申请号：US13101085
申请日：2011-05-04
IPC分类号： H04M11/00
CPC分类号： H04M3/2281 , G06Q10/00 , G06Q30/0603 , H04M3/53383
摘要： Techniques are described for performing actions for users based at least in part on spoken information, such as spoken voice-based information received from the users during telephone calls. The described techniques include categorizing spoken information obtained from a user in one or more ways, and performing actions on behalf of the user related to the categorized information. For example, in some situations, spoken information obtained from a user is analyzed to identify one or more spoken information items (e.g., words, phrases, sentences, etc.) supplied by the user, and to generate corresponding textual representations (e.g., via automated speech-to-text techniques). One or more actions may then be taken regarding the identified information items, including to categorize the items by adding textual representations of the spoken information items to one or more of multiple predefined lists or other collections of information that are specific to or otherwise available to the user.
摘要翻译： 描述了用于至少部分地基于话音信息（例如在电话呼叫期间从用户接收的基于语音的信息）来为用户执行动作的技术。 所描述的技术包括以一种或多种方式对从用户获得的口语信息进行分类，以及代表与分类信息相关的用户执行动作。 例如，在一些情况下，分析从用户获得的口语信息以识别由用户提供的一个或多个口语信息项（例如，单词，短语，句子等），并生成相应的文本表示（例如，经由 自动语音到文本技术）。 然后可以对所识别的信息项采取一个或多个动作，包括通过将口语信息项的文本表示添加到多个预定义列表中的一个或多个或其他特定或可用于其中的信息集合来分类项目 用户。
-
公开(公告)号：US09020107B2
公开(公告)日：2015-04-28
申请号：US13101085
申请日：2011-05-04
CPC分类号： H04M3/2281 , G06Q10/00 , G06Q30/0603 , H04M3/53383
摘要： Techniques are described for performing actions for users based at least in part on spoken information, such as spoken voice-based information received from the users during telephone calls. The described techniques include categorizing spoken information obtained from a user in one or more ways, and performing actions on behalf of the user related to the categorized information. For example, in some situations, spoken information obtained from a user is analyzed to identify one or more spoken information items (e.g., words, phrases, sentences, etc.) supplied by the user, and to generate corresponding textual representations (e.g., via automated speech-to-text techniques). One or more actions may then be taken regarding the identified information items, including to categorize the items by adding textual representations of the spoken information items to one or more of multiple predefined lists or other collections of information that are specific to or otherwise available to the user.
摘要翻译： 描述了用于至少部分地基于话音信息（例如在电话呼叫期间从用户接收的基于语音的信息）来为用户执行动作的技术。 所描述的技术包括以一种或多种方式对从用户获得的口语信息进行分类，以及代表与分类信息相关的用户执行动作。 例如，在一些情况下，分析从用户获得的口语信息以识别由用户提供的一个或多个口语信息项（例如，单词，短语，句子等），并生成相应的文本表示（例如，经由 自动语音到文本技术）。 然后可以对所识别的信息项采取一个或多个动作，包括通过将口语信息项的文本表示添加到多个预定义列表中的一个或多个或其他特定或可用于其中的信息集合来分类项目 用户。
-
公开(公告)号：US20140213223A1
公开(公告)日：2014-07-31
申请号：US14141375
申请日：2013-12-26
CPC分类号： H04M3/533 , H04M3/42357 , H04M3/53333 , H04M7/0039 , H04M7/0051 , H04M2201/60 , H04M2207/18 , H04M2207/20 , H04W4/025 , H04W4/12
摘要： A data communication system routes calls from a mobile communication device associated with a calling party to a mobile communication device associated with a called party. If calls are not answered by the called party, a call is routed to a voicemail server. A data channel is opened between the mobile communication device associated with the calling party and the voicemail server over which higher fidelity audio signals are transmitted. The transmitted audio is supplied to the voicemail server for conversion from an audio to a text format. In accordance with another aspect, a data channel is opened with a call placed by the calling party. The data channel is used to append information that is sent with a call to give the called party information regarding the call or the caller without having to answer the call.
摘要翻译： 数据通信系统将与主叫方相关联的移动通信设备的呼叫路由到与被叫方相关联的移动通信设备。 如果被叫方没有应答呼叫，则呼叫路由到语音信箱服务器。 在与呼叫方相关联的移动通信设备和发送更高保真音频信号的语音邮件服务器之间打开数据信道。 发送的音频被提供给语音邮件服务器以从音频转换为文本格式。 根据另一方面，通过主叫方的呼叫来打开数据信道。 数据信道用于附加通过呼叫发送的信息，以给出关于呼叫或呼叫者的被叫方信息，而不必接听呼叫。
-
公开(公告)号：US20110255671A1
公开(公告)日：2011-10-20
申请号：US13170463
申请日：2011-06-28
IPC分类号： H04M1/64
CPC分类号： G06Q30/0267 , G06Q30/0241 , G06Q30/0251 , H04M3/4878 , H04M3/53366 , H04M2201/40 , H04M2203/353 , H04M2203/4518 , H04M2207/18
摘要： Techniques are described for providing relevant information to users (e.g., information that is at least potentially of interest to the users). Relevant information for a user may be automatically determined based on a determined context of the user and/or on a request for that information from the user. For example, voice-based information may be obtained from a user in one or more ways, and then analyzed to identify requests or other indications of information of interest and/or to otherwise determine a context of the user that corresponds to potential information of interest. Relevant information for a user may be provided to the user in various ways, such as via a voice-based response during a telephone call and/or via one or more electronic messages sent to the user (e.g., via emails, instant messages, paging messages, SMS or other text messages, etc.).
摘要翻译： 描述了用于向用户提供相关信息（例如，至少可能对用户感兴趣的信息）的技术。 可以基于用户的确定的上下文和/或从用户对该信息的请求来自动确定用户的相关信息。 例如，可以以一种或多种方式从用户获得基于语音的信息，然后分析以识别感兴趣的信息的请求或其他指示和/或以其他方式确定与感兴趣的潜在信息相对应的用户的上下文 。 可以以各种方式向用户提供用户的相关信息，例如经由电话呼叫期间的基于语音的响应和/或经由发送给用户的一个或多个电子消息（例如，经由电子邮件，即时消息，寻呼 消息，短信或其他短信等）。
-
9.发明授权Methods and computer program products for providing network quality of service for world wide web applications 有权用于为万维网应用程序提供网络服务质量的方法和计算机程序产品公开(公告)号：US07359986B2
公开(公告)日：2008-04-15
申请号：US11627887
申请日：2007-01-26
IPC分类号： G06F15/16
CPC分类号： H04L67/322
摘要： Methods and computer program products are disclosed for providing QoS for Web applications via an internet service application programming interface “ISAPI”) filter running on an internet information server, wherein the ISAPI filter uses a traffic control application programming interface to manage bandwidth for individual HTTP requests. Responses to HTTP requests can be prioritized based on policies defined by the Web application developer, wherein policy decisions may be made based on many different parameters, such as, for example, the IP address of the Web browser making the request, the type of browser being used, HTTP “cookies,” the uniform resource locator being requested, an authenticated user ID, or any other information that is exposed from the internet information server through server variables. The present invention accomplishes this with no modifications to the internet information server, and •with very minimal changes to the Web application.
摘要翻译： 公开了用于通过互联网信息服务器上运行的因特网服务应用程序编程接口“ISAPI”）过滤器为Web应用程序提供QoS的方法和计算机程序产品，其中ISAPI过滤器使用流量控制应用编程接口来管理各个HTTP请求的带宽 。 基于Web应用程序开发人员定义的策略可以对HTTP请求的响应进行优先级排序，其中策略决定可以基于许多不同的参数进行，例如，提供请求的Web浏览器的IP地址，浏览器的类型 正在使用的HTTP“cookies”，正在请求的统一资源定位符，经过身份验证的用户ID或通过服务器变量从互联网信息服务器公开的任何其他信息。 本发明不对互联网信息服务器进行任何修改，并且对Web应用的改变非常小。
-
10.发明申请METHODS AND COMPUTER PROGRAM PRODUCTS FOR PROVIDING NETWORK QUALITY OF SERVICE FOR WORLD WIDE WEB APPLICATIONS 有权提供世界各地网络应用网络质量服务的方法和计算机程序产品公开(公告)号：US20070124463A1
公开(公告)日：2007-05-31
申请号：US11627887
申请日：2007-01-26
IPC分类号： G06F15/173
CPC分类号： H04L67/322
摘要： Methods and computer program products are disclosed for providing QoS for Web applications via an internet service application programming interface “ISAPI”) filter running on an internet information server, wherein the ISAPI filter uses a traffic control application programming interface to manage bandwidth for individual HTTP requests. Responses to HTTP requests can be prioritized based on policies defined by the Web application developer, wherein policy decisions may be made based on many different parameters, such as, for example, the IP address of the Web browser making the request, the type of browser being used, HTTP “cookies,” the uniform resource locator being requested, an authenticated user ID, or any other information that is exposed from the Internet information server through server variables. The present invention accomplishes this with no modifications to the internet information server, and with very minimal changes to the Web application.
摘要翻译： 公开了用于通过互联网信息服务器上运行的因特网服务应用程序编程接口“ISAPI”）过滤器为Web应用程序提供QoS的方法和计算机程序产品，其中ISAPI过滤器使用流量控制应用编程接口来管理各个HTTP请求的带宽 。 基于Web应用程序开发人员定义的策略可以对HTTP请求的响应进行优先级排序，其中策略决定可以基于许多不同的参数进行，例如，提供请求的Web浏览器的IP地址，浏览器的类型 正在使用的HTTP“cookies”，正在请求的统一资源定位符，经过身份验证的用户ID或通过服务器变量从Internet信息服务器公开的任何其他信息。 本发明不对互联网信息服务器进行修改，并且对Web应用程序进行极小的改变。
-
-
-
-
-
-
-
-
-
搜索结果
24 条记录 (耗时 0.032 秒)