公开(公告)号：US20170118632A1

公开(公告)日：2017-04-27

申请号：US14919275

申请日：2015-10-21

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Jean-Francois Paiement ,  Sastry Isukapalli ,  Ann E. Skudlark ,  Christopher T. Volinsky ,  Dan Melamed

IPC: H04W8/28 ,  H04W8/26

CPC classification number: H04M3/4872 ,  H04L12/14 ,  H04M3/42348 ,  H04M7/128 ,  H04M15/00 ,  H04M15/43 ,  H04M15/47 ,  H04M15/48 ,  H04M15/58 ,  H04M15/70 ,  H04M15/705 ,  H04M2203/2005 ,  H04M2203/555 ,  H04W4/24

Abstract: A method and apparatus for assigning a mobile device that is unassigned to a user are disclosed. Mobile phone numbers are used as a surrogate for device. For example, the method implemented via a processor obtains the phone number that is unassigned from a list of phone numbers associated with a billing account number, assigns the phone number that is unassigned to the user, wherein the user is selected from among a plurality of users associated with the billing account number, determines a confidence level for the assigning of the phone number that is unassigned to the user, and performs an analysis to provide a service for the user to whom the phone number is assigned.

公开(公告)号：US09355638B2

公开(公告)日：2016-05-31

申请号：US14737708

申请日：2015-06-12

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Dan Melamed ,  Srinivas Bangalore ,  Michael Johnston

IPC: G10L15/06 ,  G10L15/18 ,  G10L15/19 ,  G10L17/04 ,  G10L15/183

CPC classification number: G10L25/51 ,  G06F3/162 ,  G10L15/05 ,  G10L15/07 ,  G10L15/18 ,  G10L15/183 ,  G10L15/19 ,  G10L15/30 ,  G10L17/04 ,  G10L2015/228

Abstract: Disclosed herein are systems, methods, and computer-readable storage media for improving speech recognition accuracy using textual context. The method includes retrieving a recorded utterance, capturing text from a device display associated with the spoken dialog and viewed by one party to the recorded utterance, and identifying words in the captured text that are relevant to the recorded utterance. The method further includes adding the identified words to a dynamic language model, and recognizing the recorded utterance using the dynamic language model. The recorded utterance can be a spoken dialog. A time stamp can be assigned to each identified word. The method can include adding identified words to and/or removing identified words from the dynamic language model based on their respective time stamps. A screen scraper can capture text from the device display associated with the recorded utterance. The device display can contain customer service data.

公开(公告)号：US09058808B2

公开(公告)日：2015-06-16

申请号：US14061855

申请日：2013-10-24

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Dan Melamed ,  Srinivas Bangalore ,  Michael Johnston

IPC: G10L15/04 ,  G10L17/04 ,  G10L15/19 ,  G10L15/183

CPC classification number: G10L25/51 ,  G06F3/162 ,  G10L15/05 ,  G10L15/07 ,  G10L15/18 ,  G10L15/183 ,  G10L15/19 ,  G10L15/30 ,  G10L17/04 ,  G10L2015/228

Abstract: Disclosed herein are systems, methods, and computer-readable storage media for improving speech recognition accuracy using textual context. The method includes retrieving a recorded utterance, capturing text from a device display associated with the spoken dialog and viewed by one party to the recorded utterance, and identifying words in the captured text that are relevant to the recorded utterance. The method further includes adding the identified words to a dynamic language model, and recognizing the recorded utterance using the dynamic language model. The recorded utterance can be a spoken dialog. A time stamp can be assigned to each identified word. The method can include adding identified words to and/or removing identified words from the dynamic language model based on their respective time stamps. A screen scraper can capture text from the device display associated with the recorded utterance. The device display can contain customer service data.

Abstract translation: 本文公开了用于使用文本上下文改善语音识别精度的系统，方法和计算机可读存储介质。 所述方法包括检索记录的话语，从与所述口语对话相关联的设备显示中捕获文本并由一方观看所述记录的话语，以及识别与记录的话语相关的所捕获的文本中的单词。 该方法还包括将所识别的词添加到动态语言模型中，并使用动态语言模型来识别记录的话语。 记录的话语可以是一个口语对话。 时间戳可以分配给每个识别的单词。 该方法可以包括基于它们各自的时间戳将识别的词添加到动态语言模型中和/或从动态语言模型中移除所识别的单词。 屏幕刮刀可以从与记录的话语相关联的设备显示中捕获文本。 设备显示可以包含客户服务数据。

公开(公告)号：US20140046663A1

公开(公告)日：2014-02-13

申请号：US14061855

申请日：2013-10-24

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Dan Melamed

IPC: G10L17/04

CPC classification number: G10L25/51 ,  G06F3/162 ,  G10L15/05 ,  G10L15/07 ,  G10L15/18 ,  G10L15/183 ,  G10L15/19 ,  G10L15/30 ,  G10L17/04 ,  G10L2015/228

Abstract: Disclosed herein are systems, methods, and computer-readable storage media for improving speech recognition accuracy using textual context. The method includes retrieving a recorded utterance, capturing text from a device display associated with the spoken dialog and viewed by one party to the recorded utterance, and identifying words in the captured text that are relevant to the recorded utterance. The method further includes adding the identified words to a dynamic language model, and recognizing the recorded utterance using the dynamic language model. The recorded utterance can be a spoken dialog. A time stamp can be assigned to each identified word. The method can include adding identified words to and/or removing identified words from the dynamic language model based on their respective time stamps. A screen scraper can capture text from the device display associated with the recorded utterance. The device display can contain customer service data.

Abstract translation: 本文公开了用于使用文本上下文改善语音识别精度的系统，方法和计算机可读存储介质。 所述方法包括检索记录的话语，从与所述口语对话相关联的设备显示中捕获文本并由一方观看所述记录的话语，以及识别与记录的话语相关的所捕获的文本中的单词。 该方法还包括将所识别的词添加到动态语言模型中，并使用动态语言模型来识别记录的话语。 记录的话语可以是一个口语对话。 时间戳可以分配给每个识别的单词。 该方法可以包括基于它们各自的时间戳将识别的词添加到动态语言模型中和/或从动态语言模型中移除所识别的单词。 屏幕刮刀可以从与记录的话语相关联的设备显示中捕获文本。 设备显示可以包含客户服务数据。

公开(公告)号：US10057420B2

公开(公告)日：2018-08-21

申请号：US14919275

申请日：2015-10-21

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Jean-Francois Paiement ,  Sastry Isukapalli ,  Ann E. Skudlark ,  Christopher T. Volinsky ,  Dan Melamed

IPC: H04M11/00 ,  H04M3/42 ,  G06Q30/00 ,  H04M3/487 ,  H04M7/12

CPC classification number: H04M3/4872 ,  H04L12/14 ,  H04M3/42348 ,  H04M7/128 ,  H04M15/00 ,  H04M15/43 ,  H04M15/47 ,  H04M15/48 ,  H04M15/58 ,  H04M15/70 ,  H04M15/705 ,  H04M2203/2005 ,  H04M2203/555 ,  H04W4/24

Abstract: A method and apparatus for assigning a mobile device that is unassigned to a user are disclosed. Mobile phone numbers are used as a surrogate for device. For example, the method implemented via a processor obtains the phone number that is unassigned from a list of phone numbers associated with a billing account number, assigns the phone number that is unassigned to the user, wherein the user is selected from among a plurality of users associated with the billing account number, determines a confidence level for the assigning of the phone number that is unassigned to the user, and performs an analysis to provide a service for the user to whom the phone number is assigned.

公开(公告)号：US20170092261A1

公开(公告)日：2017-03-30

申请号：US15374542

申请日：2016-12-09

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Jason Williams ,  Tirso Alonso ,  Barbara Hollister ,  Dan Melamed

IPC: G10L15/01 ,  G06F17/30 ,  G06N99/00 ,  G10L15/26

CPC classification number: G10L15/01 ,  G06F16/683 ,  G06N20/00 ,  G10L15/063 ,  G10L15/26 ,  G10L15/265 ,  G10L2015/0638

Abstract: Systems, methods, and computer-readable storage devices for crowd-sourced data labeling. The system requests a respective response from each of a set of entities. The set of entities includes crowd workers. Next, the system incrementally receives a number of responses from the set of entities until one of an accuracy threshold is reached and m responses are received, wherein the accuracy threshold is based on characteristics of the number of responses. Finally, the system generates an output response based on the number of responses.

公开(公告)号：US20150279361A1

公开(公告)日：2015-10-01

申请号：US14737708

申请日：2015-06-12

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Dan Melamed ,  Srinivas Bangalore ,  Michael Johnston

IPC: G10L15/18

CPC classification number: G10L25/51 ,  G06F3/162 ,  G10L15/05 ,  G10L15/07 ,  G10L15/18 ,  G10L15/183 ,  G10L15/19 ,  G10L15/30 ,  G10L17/04 ,  G10L2015/228

Abstract: Disclosed herein are systems, methods, and computer-readable storage media for improving speech recognition accuracy using textual context. The method includes retrieving a recorded utterance, capturing text from a device display associated with the spoken dialog and viewed by one party to the recorded utterance, and identifying words in the captured text that are relevant to the recorded utterance. The method further includes adding the identified words to a dynamic language model, and recognizing the recorded utterance using the dynamic language model. The recorded utterance can be a spoken dialog. A time stamp can be assigned to each identified word. The method can include adding identified words to and/or removing identified words from the dynamic language model based on their respective time stamps. A screen scraper can capture text from the device display associated with the recorded utterance. The device display can contain customer service data.

Abstract translation: 本文公开了用于使用文本上下文改善语音识别精度的系统，方法和计算机可读存储介质。 所述方法包括检索记录的话语，从与所述口语对话相关联的设备显示中捕获文本并由一方观看所述记录的话语，以及识别与记录的话语相关的所捕获的文本中的单词。 该方法还包括将所识别的词添加到动态语言模型中，并使用动态语言模型来识别记录的话语。 记录的话语可以是一个口语对话。 时间戳可以分配给每个识别的单词。 该方法可以包括基于它们各自的时间戳将识别的词添加到动态语言模型中和/或从动态语言模型中移除所识别的单词。 屏幕刮刀可以从与记录的话语相关联的设备显示中捕获文本。 设备显示可以包含客户服务数据。