公开(公告)号：US20170060353A1

公开(公告)日：2017-03-02

申请号：US14839297

申请日：2015-08-28

Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.

Inventor： Harry E. BLANCHARD ,  Lan ZHANG ,  Gregory PULZ

IPC: G06F3/0482 ,  H04L12/24

CPC classification number: G06F3/0482 ,  G06F9/451 ,  H04L41/5061

Abstract: Devices, systems, and methods for generating a unified menu for multiple communication channels are provided. User interaction information received via the multiple communication channels are transmitted to a central server over a network. The central server also receives notification information or directive information from a source external to the central server. The central server weighs the received information and transforms the weighted information into unified menu options in a unified menu. The unified menu is transmitted to the multiple communication channels, such that same unified menu options are provided at each of the multiple communication channels.

Abstract translation: 提供了用于生成用于多个通信信道的统一菜单的设备，系统和方法。 通过多个通信信道接收的用户交互信息通过网络发送到中央服务器。 中央服务器还从中央服务器外部的源接收通知信息或指令信息。 中央服务器对收到的信息进行权衡，并将加权信息转换为统一菜单中的统一菜单选项。 将统一菜单发送到多个通信信道，使得在多个通信信道中的每一个处提供相同的统一菜单选项。

公开(公告)号：US20170142255A1

公开(公告)日：2017-05-18

申请号：US15420487

申请日：2017-01-31

Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.

Inventor： Harry E. BLANCHARD ,  Gregory PULZ ,  Lan ZHANG

IPC: H04M3/493 ,  G10L25/78 ,  G10L15/22

CPC classification number: H04M3/4936 ,  G10L15/22 ,  G10L25/78 ,  H04M2201/40 ,  H04M2203/355 ,  H04M2203/556

Abstract: A dynamically updated script for an interactive communication is generated during an interactive communication. The interactive communication is monitored over a communication network using a computer with a processor and memory for input during the interactive communication. When an input incompatible with an original script for the interactive communication is detected for the interactive communication, a dynamically updated script different from the script is generated in accordance with a type of the incompatible input.

公开(公告)号：US20150081305A1

公开(公告)日：2015-03-19

申请号：US14554164

申请日：2014-11-26

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

Inventor： Gregory PULZ ,  Harry E. BLANCHARD ,  Steven H. LEWIS ,  Lan ZHANG

IPC: G10L15/19

CPC classification number: G10L15/19 ,  G10L15/005 ,  G10L15/1822 ,  G10L15/183

Abstract: Disclosed herein are systems, computer-implemented methods, and computer-readable media for recognizing speech. The method includes receiving speech from a user, perceiving at least one speech dialect in the received speech, selecting at least one grammar from a plurality of optimized dialect grammars based on at least one score associated with the perceived speech dialect and the perceived at least one speech dialect, and recognizing the received speech with the selected at least one grammar. Selecting at least one grammar can be further based on a user profile. Multiple grammars can be blended. Predefined parameters can include pronunciation differences, vocabulary, and sentence structure. Optimized dialect grammars can be domain specific. The method can further include recognizing initial received speech with a generic grammar until an optimized dialect grammar is selected. Selecting at least one grammar from a plurality of optimized dialect grammars can be based on a certainty threshold.

公开(公告)号：US20140114662A1

公开(公告)日：2014-04-24

申请号：US14139235

申请日：2013-12-23

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

Inventor： Gregory PULZ ,  Harry E. BLANCHARD ,  Steven H. LEWIS ,  Lan ZHANG

IPC: G10L15/18

CPC classification number: G10L15/19 ,  G10L15/005 ,  G10L15/1822 ,  G10L15/183

Abstract: Disclosed herein are systems, computer-implemented methods, and computer-readable media for recognizing speech. The method includes receiving speech from a user, perceiving at least one speech dialect in the received speech, selecting at least one grammar from a plurality of optimized dialect grammars based on at least one score associated with the perceived speech dialect and the perceived at least one speech dialect, and recognizing the received speech with the selected at least one grammar. Selecting at least one grammar can be further based on a user profile. Multiple grammars can be blended. Predefined parameters can include pronunciation differences, vocabulary, and sentence structure. Optimized dialect grammars can be domain specific. The method can further include recognizing initial received speech with a generic grammar until an optimized dialect grammar is selected. Selecting at least one grammar from a plurality of optimized dialect grammars can be based on a certainty threshold.

Abstract translation: 这里公开了用于识别语音的系统，计算机实现的方法和计算机可读介质。 该方法包括从用户接收语音，感知所接收到的语音中的至少一个语音方言，基于与所感知的语音方言相关联的至少一个分数，从多个优化的方言语法中选择至少一个语法，以及感知的至少一个 语音方言，并用所选择的至少一种语法识别所接收的语音。 选择至少一个语法可以进一步基于用户简档。 可以混合多种语法。 预定义参数可以包括发音差异，词汇和句子结构。 优化的方言语法可以是域特定的。 该方法还可以包括用通用语法识别初始接收到的语音，直到选择优化的方言语法。 从多个优化方言语法中选择至少一个语法可以基于确定性阈值。