-
公开(公告)号：US20210304766A1
公开(公告)日：2021-09-30
申请号：US17347398
申请日：2021-06-14
Applicant: AT&T Intellectual Property I, L.P.
Inventor： Varun Gupta , John Murray , Kaustubh Joshi , Mazin Gilbert , Oliver Spatscheck , Rittwik Jana
Abstract: Devices, computer-readable media, and methods for submitting a modified voice input to a service based upon a user intent determined from a voice input in accordance with a voice interface of the service are disclosed. A processing system including at least one processor may obtain a voice input of a user, determine an intent from the voice input, identify a first service, from among a plurality of services, in accordance with the intent, and formulate a first modified voice input from the voice input in accordance with a voice interface of the first service, where each of the services is associated with one of a plurality of different voice interfaces. The processing system may further submit the first modified voice input to the first service, obtain a first voice response from the first service, and present a voice output to the user in accordance with the first voice response.
-
公开(公告)号：US20210006463A1
公开(公告)日：2021-01-07
申请号：US17027889
申请日：2020-09-22
Applicant: AT&T Intellectual Property I, L.P.
Inventor： David Gibbon , Thomas Kirk , Behzad Shahraray , John Murray , Mazin Gilbert
Abstract: An intelligent agent monitors operation of at least one software virtualized network (VN). Context information associated with the VN is used to analyze a state of the VN. At least one configuration change is caused to the VN in response to analysis of the state of the VN. A change is identified to the state of the VN caused by the configuration change. A determination is made as to whether or not the change to the state of the VN is an improvement to operation of the VN. A response to the determination is made by causing at least one other configuration change to the VN.
-
公开(公告)号：US10762452B2
公开(公告)日：2020-09-01
申请号：US15454050
申请日：2017-03-09
Applicant: AT&T Intellectual Property I, L.P.
Inventor： Rittwik Jana , Mazin Gilbert , Eric Noel , Vijay Gopalakrishnan
Abstract: A system for designing and executing control loops in a cloud environment includes a control platform implemented in the cloud environment having a data collection, analytics and events module, a policy module and an application controller module. The system includes a business process management application coupled to the control platform having a control loop designer module for designing a control loop template and a workflow engine for distributing the control loop template. The business process management application is coupled to the data collection analytics and events module of the control platform as well as the policy module in the application controller module to control platform. The control loop is activated by the control platform.
-
公开(公告)号：US20200211541A1
公开(公告)日：2020-07-02
申请号：US16234343
申请日：2018-12-27
Applicant: AT&T Intellectual Property I, L.P.
Inventor： Varun Gupta , John Murray , Kaustubh Joshi , Mazin Gilbert , Oliver Spatscheck , Rittwik Jana
Abstract: Devices, computer-readable media, and methods for submitting a modified voice input to a service based upon a user intent determined from a voice input in accordance with a voice interface of the service are disclosed. A processing system including at least one processor may obtain a voice input of a user, determine an intent from the voice input, identify a first service, from among a plurality of services, in accordance with the intent, and formulate a first modified voice input from the voice input in accordance with a voice interface of the first service, where each of the services is associated with one of a plurality of different voice interfaces. The processing system may further submit the first modified voice input to the first service, obtain a first voice response from the first service, and present a voice output to the user in accordance with the first voice response.
-
Patent Agency Ranking
公开(公告)号：US20190044802A1
公开(公告)日：2019-02-07
申请号：US15666143
申请日：2017-08-01
Applicant: AT&T Intellectual Property I, L.P.
Inventor： David Gibbon , Thomas Kirk , Behzad Shahraray , John Murray , Mazin Gilbert
CPC classification number: H04L41/0816 , G06F9/45558 , G06F2009/45591 , G06F2009/45595 , H04L41/0823 , H04L41/20 , H04L43/08 , H04L43/0817
Abstract: An intelligent agent monitors operation of at least one software virtualized network (VN). Context information associated with the VN is used to analyze a state of the VN. At least one configuration change is caused to the VN in response to analysis of the state of the VN. A change is identified to the state of the VN caused by the configuration change. A determination is made as to whether or not the change to the state of the VN is an improvement to operation of the VN. A response to the determination is made by causing at least one other configuration change to the VN.
-
公开(公告)号：US20180260745A1
公开(公告)日：2018-09-13
申请号：US15454050
申请日：2017-03-09
Applicant: AT&T Intellectual Property I, L.P.
Inventor： Rittwik Jana , Mazin Gilbert , Eric Noel , Vijay Gopalakrishnan
Abstract: A system for designing and executing control loops in a cloud environment includes a control platform implemented in the cloud environment having a data collection, analytics and events module, a policy module and an application controller module. The system includes a business process management application coupled to the control platform having a control loop designer module for designing a control loop template and a workflow engine for distributing the control loop template. The business process management application is coupled to the data collection analytics and events module of the control platform as well as the policy module in the application controller module to control platform. The control loop is activated by the control platform.
-
公开(公告)号：US09431005B2
公开(公告)日：2016-08-30
申请号：US13690671
申请日：2012-11-30
Applicant: AT&T Intellectual Property I, L.P.
Inventor： Andrej Ljolje , Mazin Gilbert
CPC classification number: G10L15/00 , G10L15/285 , G10L15/32
Abstract: Disclosed herein are systems, methods, and computer-readable storage media for improving automatic speech recognition performance. A system practicing the method identifies idle speech recognition resources and establishes a supplemental speech recognizer on the idle resources based on overall speech recognition demand. The supplemental speech recognizer can differ from a main speech recognizer, and, along with the main speech recognizer, can be associated with a particular speaker. The system performs speech recognition on speech received from the particular speaker in parallel with the main speech recognizer and the supplemental speech recognizer and combines results from the main and supplemental speech recognizer. The system recognizes the received speech based on the combined results. The system can use beam adjustment in place of or in combination with a supplemental speech recognizer. A scheduling algorithm can tailor a particular combination of speech recognition resources and release the supplemental speech recognizer based on increased demand.
-
公开(公告)号：US08913720B2
公开(公告)日：2014-12-16
申请号：US13767460
申请日：2013-02-14
Applicant: AT&T Intellectual Property I, L.P.
Inventor： Mazin Gilbert
CPC classification number: H04M3/4936 , G10L17/04 , G10L17/14 , H04M3/385 , H04M3/42221 , H04M3/51 , H04M2201/36 , H04M2201/41 , H04M2203/6045
Abstract: A method includes receiving a communication from a party at a voice response system and capturing verbal communication spoken by the party. Then a processor creates a voice model associated with the party, the voice model being created by processing the captured verbal communication spoken by the party. The creation of the voice model is imperceptible to the party. The voice model is then stored to provide voice verification of the party during a subsequent communication.
Abstract translation: 一种方法包括从语音响应系统的一方接收通信并捕获由该方所说的口头通信。 然后，处理器创建与该方相关联的语音模型，该语音模型是通过处理由该方所说出的所捕获的语言通信来创建的。 声音模式的创建是党无法察觉的。 然后存储语音模型以在随后的通信期间提供对方的语音验证。
-
39.发明申请System and Method for Discriminative Pronunciation Modeling for Voice Search 有权用于语音搜索的歧视性发音建模的系统和方法公开(公告)号：US20130035939A1
公开(公告)日：2013-02-07
申请号：US13649680
申请日：2012-10-11
Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.
Inventor： Mazin Gilbert , Alistair D. Conkie , Andrej Ljolje
IPC: G10L15/04
CPC classification number: G10L15/063 , G10L15/187 , G10L2015/025
Abstract: Disclosed herein is a method for speech recognition. The method includes receiving speech utterances, assigning a pronunciation weight to each unit of speech in the speech utterances, each respective pronunciation weight being normalized at a unit of speech level to sum to 1, for each received speech utterance, optimizing the pronunciation weight by identifying word and phone alignments and corresponding likelihood scores, and discriminatively adapting the pronunciation weight to minimize classification errors, and recognizing additional received speech utterances using the optimized pronunciation weights. A unit of speech can be a sentence, a word, a context-dependent phone, a context-independent phone, or a syllable. The method can further include discriminatively adapting pronunciation weights based on an objective function. The objective function can be maximum mutual information, maximum likelihood training, minimum classification error training, or other functions known to those of skill in the art.
Abstract translation: 这里公开了一种用于语音识别的方法。 该方法包括接收语音话语，在语音话语中为每个语音单位分配发音权重，将每个相应的发音权重以语音级别为单位进行归一化，以对于每个接收的语音话语归一化，通过识别来优化发音权重 字和电话对齐和相应的可能性得分，并且歧视性地适应发音权重以最小化分类错误，以及使用优化的发音权重来识别附加的接收到的语音话语。 语音单位可以是句子，单词，上下文相关的电话，与上下文无关的电话或音节。 该方法还可以包括基于目标函数的歧视地适应发音权重。 目标函数可以是最大相互信息，最大似然训练，最小分类误差训练或本领域技术人员已知的其它功能。
-
-
-
-
-
-
-
-
Search Results
39
records
(took 0.021 seconds)
