公开(公告)号：US10182152B2

公开(公告)日：2019-01-15

申请号：US15964259

申请日：2018-04-27

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

Inventor： Mazin E. Gilbert

IPC: H04M3/00 ,  H04M3/51

Abstract: A customer contact system receives a customer inquiry from a customer. Availability of different types of resources for handling the customer inquiry is used to calculate a ranking for the different types of resources for handling the customer inquiry. A type of resource with the highest rank is offered to the customer in order to resolve the customer inquiry.

公开(公告)号：US20180300731A1

公开(公告)日：2018-10-18

申请号：US16014423

申请日：2018-06-21

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

Inventor： Rittwik Jana ,  Thomas Kirk ,  Syed Anwar Aftab ,  John F. Murray ,  Mazin E. Gilbert ,  Shu Shi ,  Serban Jora ,  Avi Zahavi

IPC: G06Q30/00 ,  G06Q10/10 ,  G06F9/50 ,  G06F3/0481 ,  G06F3/0484 ,  G06N99/00

Abstract: A cloud services composition system allows customers to interactively create service constructs from network function virtualization resources. The network function virtualization primitives are modeled using a standard modeling language. An expert system suggests network function virtualization resources for use in the service construct, based on an expert system learning algorithm. The customer uses a graphical user interface to interconnect the resources and create the service construct. The process may involve collaboration with the network provider. The resulting construct is validated for use in a communications network.

公开(公告)号：US20180137348A1

公开(公告)日：2018-05-17

申请号：US15868546

申请日：2018-01-11

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

Inventor： Dimitrios Dimitriadis ,  Donald J. Bowen ,  Mazin E. Gilbert ,  Horst J. Schroeter

IPC: G06K9/00

CPC classification number: G06K9/00335 ,  G06K9/00664 ,  G10L15/065 ,  G10L2015/227 ,  G10L2015/228

Abstract: A system for sensor enhanced speech recognition is disclosed. The system may obtain visual content or other content associated with a user and an environment of the user. Additionally, the system may obtain, from the visual content, metadata associated with the user and the environment of the user. The system may also include determining, based on the visual content and metadata, if the user is speaking. If the user is determined to be speaking, the system may obtain audio content associated with the user and the environment. The system may then adapt, based on the visual content, audio content, and metadata, one or more acoustic models that match the user and the environment. Once the one or more acoustic models are adapted and loaded, the system may enhance a speech recognition process or other process associated with the user.

公开(公告)号：US09870500B2

公开(公告)日：2018-01-16

申请号：US14302137

申请日：2014-06-11

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

Inventor： Dimitrios Dimitriadis ,  Donald J. Bowen ,  Mazin E. Gilbert ,  Horst J. Schroeter

IPC: G10L15/25 ,  G06K9/00 ,  G10L15/065 ,  G10L15/22

CPC classification number: G06K9/00335 ,  G06K9/00664 ,  G10L15/065 ,  G10L2015/227 ,  G10L2015/228

Abstract: A system for sensor enhanced speech recognition is disclosed. The system may obtain visual content or other content associated with a user and an environment of the user. Additionally, the system may obtain, from the visual content, metadata associated with the user and the environment of the user. The system may also include determining, based on the visual content and metadata, if the user is speaking. If the user is determined to be speaking, the system may obtain audio content associated with the user and the environment. The system may then adapt, based on the visual content, audio content, and metadata, one or more acoustic models that match the user and the environment. Once the one or more acoustic models are adapted and loaded, the system may enhance a speech recognition process or other process associated with the user.

公开(公告)号：US20170168690A1

公开(公告)日：2017-06-15

申请号：US14970270

申请日：2015-12-15

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

Inventor： Thomas Kirk ,  Rittwik Jana ,  Mazin E. Gilbert ,  John F. Murray ,  Tan Xu

IPC: G06F3/0484 ,  G06F17/30 ,  G06F3/0482 ,  H04L29/08

CPC classification number: G06F16/90324 ,  G06F3/04842 ,  G06F16/24578 ,  H04L67/02

Abstract: Concepts and technologies disclosed herein are directed to a sequential recommender system for virtualized network services. According to one aspect disclosed herein, a recommender system can receive user input regarding a service project interest expressed by a user. In response to the user input, the recommender system can consult a knowledge base to determine a recommended service based upon the user input regarding the service project interest expressed by the user. The recommender system can then present the recommended service to the user.

公开(公告)号：US20150364139A1

公开(公告)日：2015-12-17

申请号：US14302137

申请日：2014-06-11

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

Inventor： Dimitrios Dimitriadis ,  Donald J. Bowen ,  Mazin E. Gilbert ,  Horst J. Schroeter

IPC: G10L15/25 ,  G06K9/00

CPC classification number: G06K9/00335 ,  G06K9/00664 ,  G10L15/065 ,  G10L2015/227 ,  G10L2015/228

Abstract: A system for sensor enhanced speech recognition is disclosed. The system may obtain visual content or other content associated with a user and an environment of the user. Additionally, the system may obtain, from the visual content, metadata associated with the user and the environment of the user. The system may also include determining, based on the visual content and metadata, if the user is speaking. If the user is determined to be speaking, the system may obtain audio content associated with the user and the environment. The system may then adapt, based on the visual content, audio content, and metadata, one or more acoustic models that match the user and the environment. Once the one or more acoustic models are adapted and loaded, the system may enhance a speech recognition process or other process associated with the user.

Abstract translation: 公开了一种用于传感器增强语音识别的系统。 系统可以获得与用户和用户的环境相关联的可视内容或其他内容。 此外，系统可以从视觉内容获得与用户相关联的元数据和用户的环境。 系统还可以包括基于视觉内容和元数据来确定用户是否正在说话。 如果确定用户正在说话，系统可以获得与用户和环境相关联的音频内容。 然后，系统可以基于视觉内容，音频内容和元数据，匹配与用户和环境匹配的一个或多个声学模型。 一旦一个或多个声学模型被适应和加载，则系统可以增强与用户相关联的语音识别过程或其他过程。