-
公开(公告)号：US20190251110A1
公开(公告)日：2019-08-15
申请号：US16263272
申请日：2019-01-31
Applicant: ALPINE ELECTRONICS, INC.
Inventor： Masaaki OHIRA , Yuki NAKAHARA
IPC: G06F16/38 , G06F16/33 , G06F16/332 , G06F17/27 , G06F3/16
CPC classification number: G06F16/38 , G06F3/167 , G06F16/3329 , G06F16/3344 , G06F17/2705 , G06F17/2775 , G10L15/265 , G10L25/54
Abstract: A retrieval result providing device includes a retrieval unit which acquires an individual retrieval result having item values of a plurality of items by a retrieval based on a keyword, an unprocessed sentence generation unit which generates an unprocessed sentence where retrieval result corresponding sentences with the item values arranged are arranged, an output sentence generation unit which performs at least one of a first process of erasing some of the sentences on the basis of a commonality between a word and the keyword contained in the retrieval result corresponding sentences, a second process of erasing some of the sentences on the basis of a commonality of the item values of specific items in the different sentences, and a third process of erasing some of the sentences on the basis of a commonality of the item values of a plurality of different items in one sentence so as to generate an output sentence, and an output sentence output unit which outputs a voice based on the output sentence.
-
公开(公告)号：US20190244630A1
公开(公告)日：2019-08-08
申请号：US16383861
申请日：2019-04-15
Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.
Inventor： David C. GIBBON , Andrea BASSO , Lee BEGEJA , Sumit KUMAR , Zhu LIU , Bernard S. RENGER , Behzad SHAHRARAY , Eric ZAVESKY
IPC: G10L21/10 , H04L29/06 , H04L29/08 , G06F16/61 , G11B27/28 , G10L15/26 , G06F16/683 , G06F3/16 , G06F16/68 , G11B27/34
CPC classification number: G10L21/10 , G06F3/167 , G06F16/61 , G06F16/683 , G06F16/686 , G06F16/9535 , G10L15/07 , G10L15/26 , G10L15/265 , G10L17/00 , G10L17/005 , G10L2015/0631 , G11B27/28 , G11B27/34 , H04L65/403 , H04L67/306 , H04M2201/40 , H04N5/76
Abstract: Speaker content generated in an audio conference is selectively and visually represented. A profile for each audience member who participates in the audio conference is obtained. Speaker content spoken during the audio conference is monitored. Different weights are applied to words included in the speaker content according to a parameter of the profile for each of the audience members. A relation between the speaker content to the profile for each of the audience members is determined. Visual representations of the speaker content are presented to selective members among the audience members based on the determined relation.
-
公开(公告)号：US20190243831A1
公开(公告)日：2019-08-08
申请号：US16249725
申请日：2019-01-16
Applicant: ServiceNow, Inc.
Inventor： Mikhail Rumiantsau , Alyaksandr Zaytsav , Alexey Zenovich , Aliaksei Vertsel
IPC: G06F16/2452 , G06F16/22 , G06F17/27 , G10L15/26
CPC classification number: G06F16/24522 , G06F16/2246 , G06F17/274 , G06F17/2785 , G10L15/265
Abstract: Translating a natural language search query into a query language includes receiving a natural language query for a database, processing the natural language query to generate a modified text input, generating an entity tree based on the modified text input, including assigning one or more semantic markers to one or more words or one or more groups of words within the modified text input, wherein each semantic tag denotes a semantic class for each respective word or group or words, and converting the entity tree into the query language associated with the first database.
-
公开(公告)号：US20190236083A1
公开(公告)日：2019-08-01
申请号：US16327168
申请日：2017-06-07
Applicant: NEC CORPORATION
Inventor： Yuji TAHARA
CPC classification number: G06F16/287 , G06F3/0482 , G06F3/16 , G06F16/00 , G06F16/26 , G06F17/2765 , G06Q30/02 , G10L15/265
Abstract: A category determining unit (202) determines a category of a first layer and a category of a second layer related to an input keyword by using category information and the keyword. The category information is information indicating hierarchical categories. The second layer is a hierarchy lower than the first layer. A first display control unit (204) causes a display device (10) to display information on each product belonging to the determined category of the first layer. Here, the first display control unit (204) displays information on a product belonging to the determined category of the second layer at a higher priority than information on the other product.
-
公开(公告)号：US20190235831A1
公开(公告)日：2019-08-01
申请号：US15884907
申请日：2018-01-31
Applicant: Amazon Technologies, Inc.
Inventor： Yu Bao
CPC classification number: G06F3/167 , G06F17/2785 , G06F21/30 , G10L15/18 , G10L15/19 , G10L15/22 , G10L15/265 , G10L17/005 , H04L12/2829
Abstract: Techniques for restricting content, available to a speech processing system, from certain users of the system are described. The system may include child devices. When a user (e.g., an adult user or a child user) provides input to a child device, the system may process the input to determine child appropriate content based on the invoked device being a child device. In addition to including child devices, the system may also include child profiles. When a user provides input to a device, the system may identify the user, determine an age of the user, and process the input to determine content appropriate for the user's age. The system may be configured such that child user may be restricted to invoking certain intents, speechlets, skills, and the like. The system may include restrictions that apply uniformly to each child user and/or child device. In addition, the system may include restrictions that are unique to a specific child user and/or device.
-
Patent Agency Ranking
公开(公告)号：US20190232169A1
公开(公告)日：2019-08-01
申请号：US15885162
申请日：2018-01-31
Applicant: Sony Interactive Entertainment LLC
Inventor： Warren M. Benedetto , Landon Noss
IPC: A63F13/5375 , A63F13/67 , G10L15/26 , G06K9/00
CPC classification number: A63F13/5375 , A63F13/67 , G06K9/00302 , G06K9/00536 , G10L15/265
Abstract: The present disclosure describes methods and systems directed towards assignment of contextual gameplay assistance to player reaction. By analyzing user gameplay and reactions of a user, appropriate gameplay assistance (such as hints, advice, or walk-through information) can be assigned for different thresholds associated with levels of frustration that users can obtain regarding different obstacles found within the video games. The system and methods allow for customization of what type of gameplay assistance can be provided to each user as each user may have different thresholds of frustration or preferences regarding the types of assistance they would like to receive within the video game.
-
公开(公告)号：US20190222928A1
公开(公告)日：2019-07-18
申请号：US16365011
申请日：2019-03-26
Applicant: Bose Corporation
Inventor： William Henry Arthur Voigt , Darren Abrams , William D. Rice , Pelham Norville , Noah Stupak , John Trotter
CPC classification number: H04R1/406 , G06F3/012 , G10L15/265 , H03G3/342 , H04R2201/40 , H04S7/304
Abstract: An apparatus is configured to rest on a wearer's neck or shoulders, and has a first microphone positioned at a first position located on the right side of the wearer, when the apparatus is worn, and a second microphone positioned at a second position located on the left side of the wearer. A processor receives audio signals output by the first and second microphones, and compares the audio signals from the first microphone to the audio signals from the second microphone. Based on the comparison, the processor determines whether the wearer's head is rotated to the right, left, or center, during an instance of the user speaking. Based on the determination, the processor selects a first one of at least two audio signal destinations, and provides the audio signal from at least one of the microphones to the first selected audio signal destination.
-
公开(公告)号：US20190220520A1
公开(公告)日：2019-07-18
申请号：US15871992
申请日：2018-01-16
Applicant: CHIH HUNG KAO
Inventor： CHIH HUNG KAO
CPC classification number: G06F17/289 , G10L15/22 , G10L15/265 , H04W4/12 , H04W88/02
Abstract: The present invention is to provide a simultaneous interpretation method, comprising the steps of: acquiring an audio stream data input by a user into a simultaneous interpretation device; converting the audio stream data into textual data according to a source language, after acquiring the audio stream data; translating the textual data according to text corpuses in an optimized database that correspond to a target language in order to acquire a first translation text; transmitting the textual data to a third-party database in order for the third-party database to translate the textual data according to the target language, and acquiring a second translation text from the third-party database; and determining whether the first translation text is acquired; and if yes, converting the first translation text into an audio stream data and transmitting the audio stream data to the simultaneous interpretation device in order for the simultaneous interpretation device to output the audio stream data in voice; or if no, converting the second translation text into an audio stream data and transmitting the audio stream data to the simultaneous interpretation device in order for the simultaneous interpretation device to output the audio stream data in voice.
-
公开(公告)号：US20190212976A1
公开(公告)日：2019-07-11
申请号：US16355709
申请日：2019-03-16
Applicant: The Reverie Group, LLC
Inventor： Dennis Fountaine
IPC: G06F3/16 , G06F16/683 , G10L21/06 , G10L15/26
CPC classification number: G06F3/167 , G06F3/165 , G06F16/683 , G10L15/22 , G10L15/265 , G10L21/06 , H04M1/6066
Abstract: Disclosed is a method, a device, a system and/or a manufacture of control and security of a voice controlled device. In one embodiment, an apparatus includes a signal input for receiving a command signal and a soundwave damper to dampen a sound receiving capability of a voice controlled device. The voice controlled device is capable of initiating a responsive action in response to a voice command. A processor determinations that the command signal is associated with the voice command and in response to the determination generate with a speaker a soundwave carrying the voice command bypassing the soundwave damper such that the soundwave carrying the voice command is communicable to the microphone of the voice controlled device. The apparatus also includes a cap housing the speaker and optionally the soundwave damper. As an example, the soundwave damper may be a barrier, a flexible membrane, or a sound interference generator.
-
公开(公告)号：US20190198040A1
公开(公告)日：2019-06-27
申请号：US16153148
申请日：2018-10-05
Inventor： Bo XIE
CPC classification number: G10L25/63 , G10L15/265
Abstract: The present disclosure discloses a mood recognition method, a device, an electronic device and a computer-readable storage medium. The method includes: obtaining a sample text; obtaining a plurality of recordings corresponding to the sample text, in which the plurality of recordings are speech obtained by reading the sample text using a plurality of mood types; extracting a mood feature from each of the plurality of recordings, and determining a mood type corresponding to the mood feature; establishing a mood recognition model based on the sample text, mood features extracted from the plurality of recordings, and mood types corresponding to the mood features; and performing mood recognition on a speech data of a user based on the mood recognition model to obtain a corresponding mood meaning.
-
-
-
-
-
-
-
-
-
Search Results
1630
records
(took 0.024 seconds)
