-
公开(公告)号：US12047529B2
公开(公告)日：2024-07-23
申请号：US17000542
申请日：2020-08-24
Applicant: MOTOROLA SOLUTIONS, INC.
Inventor： Chew Yee Kee , Guo Dong Gan , Mun Yew Tham
CPC classification number: H04M3/2281 , H04L63/0869 , H04N7/147 , G06Q50/26 , H04M2203/2027 , H04M2203/251 , H04M2203/6027 , H04M2242/04
Abstract: A method and apparatus for identifying a faked video is provided herein. During operation, when a video, or video call is received from a device, a simultaneous audio call is placed to the device (i.e., the video call and audio call take place simultaneously in time). The audio streams on both the video and audio call are compared, and a difference between the audio streams is identified. The video is deemed a potential fake if the difference between the audio streams is above a particular threshold.
-
公开(公告)号：US20230216955A1
公开(公告)日：2023-07-06
申请号：US17736645
申请日：2022-05-04
Applicant: CenturyLink Intellectual Property LLC
Inventor： Patrick Giagnocavo , Michael Stillman
CPC classification number: H04M3/436 , H04M3/42085 , H04M2203/2027
Abstract: Novel tools and techniques are provided for implementing automated robocall detection. In various embodiments, a computing system may compare first abstracted raw data, obtained from a portion of call data from a first call from a first originating party, with each of a plurality of abstracted raw data, obtained from portions of call data from a plurality of calls from a corresponding plurality of originating parties. In some instances, the plurality of abstracted raw data and the first abstracted raw data may each include at least one of word count data, phoneme count data, inter-word timing data, voice pitch estimation data, and/or background noise data. The computing system may determine whether the first abstracted raw data is indicative of the first call being a suspected unsolicited or unwanted communication, based at least in part on the comparison. If so, the computing system may perform one or more tasks.
-
公开(公告)号：US20190068657A1
公开(公告)日：2019-02-28
申请号：US15690023
申请日：2017-08-29
Applicant: T-Mobile USA, Inc.
Inventor： Homer Nicolas B. Filart
CPC classification number: H04L65/1079 , H04L65/1006 , H04L65/1073 , H04M2203/2027 , H04W8/02 , H04W8/26
Abstract: Systems and methods for preventing a robocall from leaving a voicemail are described. When an incoming call without a history information header (HIH) destined for a subscriber is detected, the incoming call is prevented from leaving a voicemail if the subscriber does not answer the incoming call. If the incoming call has the HIH, additional determination process based on a visited network address of the subscriber is performed to determine whether the incoming call is to be prevented from leaving a voicemail.
-
公开(公告)号：US10013972B2
公开(公告)日：2018-07-03
申请号：US15214064
申请日：2016-07-19
Inventor： John Nicholas Gross
IPC: G06F7/04 , G10L15/06 , G10L15/22 , G10L17/26 , G10L13/08 , G06F21/32 , G10L13/027 , G10L17/22 , G10L17/00 , G10L17/02 , G10L17/04 , G10L17/06 , H04L29/06 , G10L15/02
CPC classification number: G10L15/063 , G06F21/32 , G10L13/027 , G10L13/08 , G10L15/02 , G10L15/22 , G10L17/00 , G10L17/02 , G10L17/04 , G10L17/06 , G10L17/22 , G10L17/26 , H04L63/102 , H04L63/123 , H04M2203/2027
Abstract: An electronic challenge system is used to control access to resources by using a spoken test to identify an origin of a voice. The test is based on a series of questions posed during an interactive dialog session with the entity attempting access.
-
5.发明申请公开(公告)号：US20180115641A1
公开(公告)日：2018-04-26
申请号：US15789974
申请日：2017-10-21
Inventor： Chao LI , Xiangang LI , Jue SUN
CPC classification number: H04M3/42059 , G06N3/0445 , G06N3/0454 , G06N3/08 , G10L25/30 , G10L25/51 , G10L25/78 , H04M3/26 , H04M2203/2027
Abstract: A method and an apparatus for classifying a telephone dialing test audio based on AI is provided. Data of a telephone dialing test audio is acquired first, then the data of the telephone dialing test audio is processed via a preset classifier so as to obtain similarities among the data of the telephone dialing test audio and telephone types in the preset classifier, in which the preset classifier is a deep-learning model determined by historical data of telephone dialing test audios and their corresponding telephone types; finally, the telephone type corresponding to the telephone dialing test audio is determined according to the similarities. With the method and apparatus, the telephone dialing test audio is classified via machine learning to determine whether a user is a normal user, thus human costs is saved and an efficiency of dialing test is increased.
-
Patent Agency Ranking
公开(公告)号：US09679042B2
公开(公告)日：2017-06-13
申请号：US14169218
申请日：2014-01-31
Applicant: Interactive Intelligence, Inc.
Inventor： Kevin Vlack , Felix Immanuel Wyss
CPC classification number: G06F17/30595 , G06F17/30743 , G10L19/018 , G10L25/54 , H03M7/3059 , H03M7/3066 , H03M7/3082 , H04M3/5158 , H04M2203/2027
Abstract: Systems and methods for the matching of datasets, such as input audio segments, with known datasets in a database are disclosed. In an illustrative embodiment, the use of the presently disclosed systems and methods is described in conjunction with recognizing known network message recordings encountered during an outbound telephone call. The methodologies include creation of a ternary fingerprint bitmap to make the comparison process more efficient. Also disclosed are automated methodologies for creating the database of known datasets from a larger collection of datasets.
-
公开(公告)号：US09558337B2
公开(公告)日：2017-01-31
申请号：US14792370
申请日：2015-07-06
Applicant: The John Nicholas and Kristin Gross Trust
Inventor： John Nicholas Gross
CPC classification number: G10L15/063 , G06F21/32 , G10L13/027 , G10L13/08 , G10L15/02 , G10L15/22 , G10L17/00 , G10L17/02 , G10L17/04 , G10L17/06 , G10L17/22 , G10L17/26 , H04L63/102 , H04L63/123 , H04M2203/2027
Abstract: Methods of creating a corpus of spoken CAPTCHA challenges are disclosed. The methods involve training a computing system with samples of human voices and computer synthesized voices articulating a set of reference challenge items, scoring the reference challenge items based on differences in articulation between human and machine articulation of each challenge item, and selecting suitable challenge items from among the reference challenge items based on the score.
Abstract translation: 公开了创建口头CAPTCHA挑战语料库的方法。 这些方法涉及对计算系统进行训练，其中包含人类声音和计算机合成语音的样本，其中阐述了一组参考挑战项目，基于每个挑战项目的人机交互之间的关系差异来评估参考挑战项目，以及从 基于评分的参考挑战项目。
-
公开(公告)号：US20170026367A1
公开(公告)日：2017-01-26
申请号：US15289767
申请日：2016-10-10
Applicant: Gary Stephen Shuster
Inventor： Gary Stephen Shuster
CPC classification number: H04L63/0853 , G06F21/31 , G06F21/316 , G06F21/36 , G06F2221/2133 , H04L63/08 , H04L63/083 , H04L63/126 , H04M2203/2027 , H04W12/06
Abstract: Systems and methods for verifying human users through cognitive processes that computers cannot imitate are described herein. Human cognitive language processing techniques may be used to verify human users. Visual patterns and tests may be used to distinguish between humans and computers because computer-based visual recognition is fundamentally different from human visual processing. Persistent plugins and tests may be used to continuously verify human users.
Abstract translation: 本文描述了通过计算机不能模仿的认知过程来验证人类用户的系统和方法。 可以使用人类认知语言处理技术来验证人类用户。 视觉模式和测试可用于区分人和计算机，因为基于计算机的视觉识别与人类视觉处理有着根本的不同。 持久性插件和测试可用于持续验证人类用户。
-
公开(公告)号：US09542856B2
公开(公告)日：2017-01-10
申请号：US14014530
申请日：2013-08-30
Applicant: Interactive Intelligence, Inc.
Inventor： Felix Immanuel Wyss , Matthew Alan Taylor , Kevin Charles Vlack
CPC classification number: H04M3/5158 , G09B19/00 , G10L25/48 , G10L25/51 , H04M3/42102 , H04M3/5183 , H04M2203/2027 , H04M2203/558 , H04M2203/6054
Abstract: A system and method are presented for learning call analysis. Audio fingerprinting may be employed to identify audio recordings that answer communications. In one embodiment, the system may generate a fingerprint of a candidate audio stream and compare it against known fingerprints within a database. The system may also search for a speech-like signal to determine if the end point contains a known audio recording. If a known audio recording is not encountered, a fingerprint may be computed for the contact and the communication routed to a human for handling. An indication may be made as to if the call is indeed an audio recording. The associated information may be saved and used for future identification purposes.
Abstract translation: 提出了一种用于学习呼叫分析的系统和方法。 可以使用音频指纹来识别应答通信的音频记录。 在一个实施例中，系统可以生成候选音频流的指纹，并将其与数据库内的已知指纹进行比较。 系统还可以搜索类似语音的信号以确定终点是否包含已知的音频记录。 如果没有遇到已知的音频记录，则可以为联系人计算指纹，并将通信路由到人的处理。 可以指示呼叫确实是音频记录。 相关信息可以被保存并用于将来识别。
-
公开(公告)号：US20160328548A1
公开(公告)日：2016-11-10
申请号：US15214064
申请日：2016-07-19
Inventor： John Nicholas Gross
CPC classification number: G10L15/063 , G06F21/32 , G10L13/027 , G10L13/08 , G10L15/02 , G10L15/22 , G10L17/00 , G10L17/02 , G10L17/04 , G10L17/06 , G10L17/22 , G10L17/26 , H04L63/102 , H04L63/123 , H04M2203/2027
Abstract: An electronic challenge system is used to control access to resources by using a spoken test to identify an origin of a voice. The test is based on a series of questions posed during an interactive dialog session with the entity attempting access.
Abstract translation: 电子挑战系统用于通过使用口语测试来识别语音的来源来控制对资源的访问。 该测试基于在与实体尝试访问的实体的交互式对话会话期间提出的一系列问题。
-
-
-
-
-
-
-
-
-
Search Results
312
records
(took 0.024 seconds)
