-
公开(公告)号：US11798538B1
公开(公告)日：2023-10-24
申请号：US17027162
申请日：2020-09-21
发明人： Christopher Geiger Parker , Piyush Bhargava , Aparna Nandyal , Rajagopalan Ranganathan , Mugunthan Govindaraju , Vidya Narasimhan
IPC分类号： G10L15/18 , G06F16/9032 , G10L15/26 , G10L15/183 , G10L15/22
CPC分类号： G10L15/1822 , G06F16/90332 , G10L15/183 , G10L15/26 , G10L2015/228
摘要： This disclosure relates to answer prediction in a speech processing system. The system may disambiguate entities spoken or implied in a request to initiate an action with respect to a target user. To initiate the action, the system may determine one or more parameters; for example, the target (e.g., a contact/recipient), a source (e.g., a caller/requesting user), and a network (voice over internet protocol (VOIP), cellular, video chat, etc.). Due to the privacy implications of initiating actions involving data transfers between parties, the system may apply a high threshold for a confidence associated with each parameter. Rather than ask multiple follow-up questions, which may frustrate the requesting user, the system may attempt to disambiguate or determine a parameter, and skip a question regarding the parameter if it can predict an answer with high confidence. The system can improve the customer experience while maintaining security for actions involving, for example, communications.
-
公开(公告)号：US11790932B2
公开(公告)日：2023-10-17
申请号：US17547644
申请日：2021-12-10
发明人： Qingming Tang , Chieh-Chi Kao , Qin Zhang , Ming Sun , Chao Wang , Sumit Garg , Rong Chen , James Garnet Droppo , Chia-Jung Chang
CPC分类号： G10L25/51 , G06N3/045 , G06N3/08 , G10L25/21 , G10L25/30 , G10L15/08 , G10L15/22 , G10L2015/088 , G10L2015/223
摘要： A system may include a first acoustic event detection (AED) component configured to detect a predetermined set of acoustic events, and include a second AED component configured to detect custom acoustic events that a user configures a device to detect. The first and second AED components are configured to perform task-specific processing, and may receive as input the same acoustic feature data corresponding to audio data that potentially represents occurrence of one or more events. Based on processing by the first and second AED components, a device may output data indicating that one or more acoustic events occurred, where the acoustic events may be a predetermined acoustic event and/or a custom acoustic event.
-
公开(公告)号：US11785409B1
公开(公告)日：2023-10-10
申请号：US17529560
申请日：2021-11-18
发明人： Mohamed Mansour
IPC分类号： H04S7/00 , G10L19/008 , H04R3/00
CPC分类号： H04S7/302 , G10L19/008 , H04R3/005
摘要： Disclosed are techniques for an improved method for performing Acoustic Wave Decomposition (AWD) processing that reduces a complexity and processing consumption. The improved method enables a device to perform AWD processing to decompose an observed sound field into directional components, enabling the device to perform additional processing such as sound source separation, dereverberation, sound source localization, sound field reconstruction, and/or the like. The improved method splits the solution to two phases: a search phase that selects a subset of a device dictionary to reduce a complexity, and a decomposition phase that solves an optimization problem using the subset of the device dictionary.
-
公开(公告)号：US11763809B1
公开(公告)日：2023-09-19
申请号：US17114093
申请日：2020-12-07
CPC分类号： G10L15/22 , G06F3/017 , G10L15/1815 , G10L15/24 , G10L15/32 , G10L2015/088 , G10L2015/223
摘要： A speech-processing system may provide access to multiple virtual assistants via one or more voice-controlled devices. Each assistant may leverage language processing and language generation features of the speech-processing system, while handling different commands and/or providing access to different back applications. Each assistant may be associated with its own voice and/or speech style, and thus be perceived as having a particular “personality.” In some situations, a user may invoke a first assistant, e.g., with a wakeword or button press, and provide a command that the speech-processing system may determine will be better handled by a second assistant. The speech-processing system may thus call on a component to generate plan data describing one or more operations for the speech-processing system to execute to handoff the command to the second assistant and provide the user with indications of which assistant will handle the command.
-
公开(公告)号：US11763797B2
公开(公告)日：2023-09-19
申请号：US16908882
申请日：2020-06-23
发明人： Roberto Barra Chicote , Adam Franciszek Nadolski , Thomas Edward Merritt , Bartosz Putrycz , Andrew Paul Breen
IPC分类号： G10L13/10 , G10L13/033 , G10L13/00
CPC分类号： G10L13/033 , G10L13/00 , G10L13/10
摘要： A speech model includes a sub-model corresponding to a vocal attribute. The speech model generates an output waveform using a sample model, which receives text data, and a conditioning model, which receives text metadata and produces a prosody output for use by the sample model. If, during training or runtime, a different vocal attribute is desired or needed, the sub-model is re-trained or switched to a different sub-model corresponding to the different vocal attribute.
-
公开(公告)号：US11750514B1
公开(公告)日：2023-09-05
申请号：US18113888
申请日：2023-02-24
申请人： SimpliSafe, Inc.
发明人： Bojan Rajkovic , Chin Siong Ong
摘要： In accordance with one disclosed method, a first application may receive a first connectivity candidate from a second application, the first connectivity candidate identifying at least a first internet protocol (IP) address that a remote application can potentially use to send data over a network to the second application for use by the first application. The first application may determine that the first connectivity candidate satisfies at least one criterion and, based at least in part on the first connectivity candidate satisfying the at least one criterion, may cause the first connectivity candidate to be sent to the remote application via a signaling channel to cause the remote application to attempt to use the first connectivity candidate to send data to the second application via the network.
-
公开(公告)号：US11739234B2
公开(公告)日：2023-08-29
申请号：US17248664
申请日：2021-02-02
申请人： Questech Corporation
发明人： Barry Culkin , Roger Questel , Robert Harrington , Douglas Croteau , Paul Thottathil , Purushoth Kesavan , John Ryan , Satyabrata Mukherjee
IPC分类号： C09D127/16 , C09D5/02 , C09D7/20 , C09D175/14 , C09D133/04 , C04B41/63 , C04B41/45 , C04B41/48 , C04B41/00
CPC分类号： C09D127/16 , C04B41/009 , C04B41/4539 , C04B41/483 , C04B41/4842 , C04B41/4884 , C04B41/63 , C09D5/022 , C09D7/20 , C09D133/04 , C09D175/14
摘要： Disclosed is a two-part composition for sealing natural stone or masonry, and methods of use. The two-part composition is comprised of (1) a first part comprising a polyvinylidene fluoride (PVDF) particulate; a low evaporation rate organic solvent; and water; and (2) a second part comprising a blend of a plurality of liquid resin formulations.
-
公开(公告)号：US11722571B1
公开(公告)日：2023-08-08
申请号：US15385315
申请日：2016-12-20
发明人： Mario Chenier , Tony Roy Hardie , Nawdesh Uppal , Brian Oliver , Ran Mokady
IPC分类号： H04L67/143 , H04L65/1069 , H04L67/306 , G10L25/84 , G10L15/18 , G10L17/06 , G10L15/22 , H04L67/54
CPC分类号： H04L67/143 , G10L15/18 , G10L15/22 , G10L17/06 , G10L25/84 , H04L65/1069 , H04L67/306 , H04L67/54 , G10L2015/223
摘要： Methods and devices for causing a communications session between a first device and a second device to end based on lack of speech activity are described herein. In some embodiments, a communications between a first device and a second device may be initiated by the first device, where a first user account associated with the first device is authorized to initiate communications session with the second device by a second user account. After the communications session is started, audio data is received by a speech activity detection system, which determines whether the audio data represents speech or non-speech. If, after the communications session begins, non-speech is detected by the first device for more than a predefined amount of time, then the communications session is caused to end so that the first device is not capable of receiving video and/or audio associated with the second device.
-
公开(公告)号：US11704776B2
公开(公告)日：2023-07-18
申请号：US17547816
申请日：2021-12-10
发明人： Dong Zhou
IPC分类号： H04N13/128 , H04N13/239 , G06T5/00 , G06T5/50 , G06V20/40 , G06V20/64 , G06F18/00 , H04N23/68 , H04N13/25 , H04N5/265 , G06V30/142 , H04N13/00
CPC分类号： G06T5/002 , G06F18/00 , G06T5/50 , G06V20/46 , G06V20/64 , H04N5/265 , H04N13/128 , H04N13/239 , H04N13/25 , H04N23/68 , H04N23/682 , H04N23/683 , H04N23/6812 , G06T2207/10021 , G06T2207/30201 , G06V30/142 , H04N2013/0081
摘要： Depth information can be used to assist with image processing functionality, such as image stabilization and blur reduction. In at least some embodiments, depth information obtained from stereo imaging or distance sensing, for example, can be used to determine a foreground object and background object(s) for an image or frame of video. The foreground object then can be located in later frames of video or subsequent images. Small offsets of the foreground object can be determined, and the offset accounted for by adjusting the subsequent frames or images. Such an approach provides image stabilization for at least a foreground object, while providing simplified processing and reduce power consumption. Similarly processes can be used to reduce blur for an identified foreground object in a series of images, where the blur of the identified object is analyzed.
-
公开(公告)号：US11694684B1
公开(公告)日：2023-07-04
申请号：US17094076
申请日：2020-11-10
CPC分类号： G10L15/22 , G10L15/02 , G10L15/063 , G10L15/08
摘要： Techniques for generating a skill using skill portion deviceskill portion devices are described. A user generates a skill by connecting skill portion deviceskill portion devices in a particular manner. As devices are connected, a speech controllable device or a distributed system may maintain a data structure representing a skill configuration corresponding to the presently connected devices.
-
-
-
-
-
-
-
-
-
搜索结果
1572 条记录 (耗时 0.029 秒)
