公开(公告)号：US20230042051A1

公开(公告)日：2023-02-09

申请号：US17382341

申请日：2021-07-22

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.

Inventor： COLIN BRUCE CLEMENT ,  DAWN DRAIN ,  NEELAKANTAN SUNDARESAN ,  CHEN WU

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62 ,  G06F40/42 ,  G06F8/40

Abstract: A distillation system extracts knowledge from a large pre-trained sequence-to-sequence neural transformer model into a smaller bi-encoder. The pre-trained sequence-to-sequence neural transformer model is trained to translate data from a first domain into a second domain on a large corpus. A teacher model is generated from the pre-trained model by fine-tuning the pre-trained neural transformer model on a smaller translation task with true translation pairs. The fine-tuned model is then used to generate augmented data values which are used with the true translation pairs to train the bi-encoder. The bi-encoder is used for perform cross-domain searches.

公开(公告)号：US11538455B2

公开(公告)日：2022-12-27

申请号：US16969950

申请日：2019-02-14

Applicant: DOLBY LABORATORIES LICENSING CORPORATION

Inventor： Cong Zhou ,  Michael Getty Horgan ,  Vivek Kumar ,  Jaime H. Morales ,  Cristina Michel Vasco

IPC: G10L25/00 ,  G06F15/00 ,  G10L13/02 ,  G06F40/42 ,  G06N3/04 ,  G06N3/08 ,  G10L25/30

Abstract: Computer-implemented methods for speech synthesis are provided. A speech synthesizer may be trained to generate synthesized audio data that corresponds to words uttered by a source speaker according to speech characteristics of a target speaker. The speech synthesizer may be trained by time-stamped phoneme sequences, pitch contour data and speaker identification data. The speech synthesizer may include a voice modeling neural network and a conditioning neural network.

公开(公告)号：US11450232B2

公开(公告)日：2022-09-20

申请号：US16244634

申请日：2019-01-10

Applicant: Transcendent International, LLC.

Inventor： William Z. Tan

IPC: G06F40/42 ,  G09B19/06 ,  G09B5/06 ,  G06F40/58 ,  G06F40/205 ,  G06F40/289

Abstract: An electronic platform to generate and display blended multilingual content. The methods and systems can be employed in an educational environment to assist a user fluent in a native language in learning a target language. One or more blended combinations of content in the native language and the target language are generated and displayed to the user. A machine learning component can be used to evaluate performance data to execute adjusts to the level and type of blending applied to the blended combinations to increase and improve learning efficiency.

公开(公告)号：US11328706B2

公开(公告)日：2022-05-10

申请号：US16319430

申请日：2017-07-21

Applicant: OSLABS PTE. LTD.

Inventor： Sudhir Bangarambandi ,  Akash Motilal Dongre

IPC: G06F17/00 ,  G10L13/08 ,  G06F40/42 ,  G06F40/263 ,  G06F3/0482

Abstract: The present invention provides a system and method for converting text data into speech data. Initially, the system enables a user to select a language from a plurality of languages supported by the operating system (OS) of a computing device. Further, on selecting and copying any text data, the system provides the user with options to listen to an audio output of the text data. The user is provided with options to listen to text data in either English or the selected language, when the language of the text data is one among the plurality of languages supported by the OS. Further, the user is provided with options to listen to text data in English, for the text data in any language. Once the user selects the option, the system converts the text data to speech data. The speech data is provided as the audio output to the user.

公开(公告)号：US20220108079A1

公开(公告)日：2022-04-07

申请号：US17064445

申请日：2020-10-06

Applicant: SAP SE

Inventor： Pablo Roisman

IPC: G06F40/35 ,  G06N20/00 ,  G06K9/62 ,  G06F40/42 ,  G06F40/154 ,  H04L12/58

Abstract: A computer implemented system and method of generating chatbots. The system uses a machine learning model to identify elements on the webpage. The system associates intents with the elements, and associates expressions and skills related to the intent. The system generates a chatbot according to the intents, expressions and skills.

公开(公告)号：US20220036409A1

公开(公告)日：2022-02-03

申请号：US17290422

申请日：2019-11-04

Applicant: Yeogirl Yun

Inventor： Yeogirl Yun

IPC: G06Q30/02 ,  G06F16/23 ,  G06F40/42 ,  G06F40/169

Abstract: A multilingual tag-based review system where users from around the world, can browse and submit review over the Internet, for product purchases or other reviews related to the user's interests. The system has a server with a database. The database has authorized, pre-written tags and stored ratings associated with the product or the items being reviewed, and displays the tags and ratings on the website with the product or item being reviewed. Users can quickly gauge the ratings in their own language to determine their interest in the item or whether or not to purchase the product by browsing the reviews or leaving a review of the product, if the user has purchased the product, or item of interest.

公开(公告)号：US20220027577A1

公开(公告)日：2022-01-27

申请号：US17291772

申请日：2019-12-06

Applicant: Microsoft Technology Licensing, LLC

Inventor： Nan DUAN ,  Ming ZHOU ,  Yaobo Liang

IPC: G06F40/42 ,  G06F40/30

Abstract: Implementations of the present disclosure relate to text generation with a customizable style. In a method, a first natural language is received; the first natural language text is converted, via a text generation model, into a second natural language text that at least partly reflects the meaning of the first natural language text and has a style distinguishable from the first natural language text, the text generation model comprising a modifiable parameter; and in response to receiving a modification to the parameter, the first natural language text is converted, via the text generation model, into a third natural language text that at least partly reflects the meaning of the first natural language text and includes a style distinguishable from both the first natural language text and the second natural language text.

公开(公告)号：US20210352460A1

公开(公告)日：2021-11-11

申请号：US17313608

申请日：2021-05-06

Applicant: Kant AI Solutions LLC

Inventor： Gregory L. Rohde ,  Michael M. Kangior ,  Tyler S. Tappan

IPC: H04W4/90 ,  G06F40/30 ,  G06F40/42 ,  H04W4/021 ,  H04M3/51 ,  H04W76/50

Abstract: A method and apparatus for providing emergency assistance includes receiving audio, visual, or text data about an ongoing emergency at a public safety answering point, comparing that data to a database of other emergencies with an artificial intelligence engine, recognizing patterns in aggregated and correlated data by the artificial intelligence engine, and generating appropriate audio, visual, and text output for a human operator to respond to the emergency. An AI engine receives audio data, visual data, and text data related to ongoing emergencies being received at public safety answering points and compares it with data from other emergencies. The AI engine identifies key words and patterns and generates appropriate messages for operators. The system continuously generates feedback to the AI engine to aid in machine learning. The feedback includes: “the message was correct; continue drawing this conclusion”; and “the message was wrong; do not continue drawing this conclusion.”

公开(公告)号：US20210312144A1

公开(公告)日：2021-10-07

申请号：US17354211

申请日：2021-06-22

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Kaito MIZUSHIMA

IPC: G06F40/58 ,  G06F40/51 ,  G06F40/42

Abstract: A translation device includes: an input interface that acquires an input sentence in a first language; and a controller that controls machine translation for the input sentence acquired by the input interface, wherein the controller acquires, based on the input sentence, a translated sentence showing a result of machine translation of the input sentence from the first language to a second language, acquires, based on the translated sentence, a reverse-translated sentence showing a result of machine translation of the translated sentence from the second language to the first language, and corrects, based on the input sentence, a part including a translated word in the acquired reverse-translated sentence to change the translated word into a phrase corresponding to a polysemous word in the input sentence, the translated word corresponding to the polysemous word of the translated sentence in the reverse-translated sentence.

公开(公告)号：US20210232760A1

公开(公告)日：2021-07-29

申请号：US17119902

申请日：2020-12-11

Applicant: AI IP INVESTMENTS LTD

Inventor： Robert J. Munro ,  Schuyler D. Erle ,  Jason Brenier ,  Paul A. Tepper ,  Tripti Saxena ,  Gary C. King ,  Jessica D. Long ,  Brendan D. Callahan ,  Tyler J. Schnoebelen ,  Stefan Krawczyk ,  Veena Basavaraj

IPC: G06F40/169 ,  G06F16/35 ,  G06F16/93 ,  G06F16/242 ,  G06F16/28 ,  G06F16/36 ,  G06F16/951 ,  G06F16/332 ,  G06F16/2453 ,  G06Q50/00 ,  G06F40/30 ,  G06F40/40 ,  G06F40/42 ,  G06F40/137 ,  G06F40/221 ,  G06N20/00 ,  G06F3/0482

Abstract: Methods, apparatuses and computer readable medium are presented for generating a natural language model. A method for generating a natural language model comprises: selecting from a pool of documents, a first set of documents to be annotated; receiving annotations of the first set of documents elicited by first human readable prompts; training a natural language model using the annotated first set of documents; determining documents in the pool having uncertain natural language processing results according to the trained natural language model and/or the received annotations; selecting from the pool of documents, a second set of documents to be annotated comprising documents having uncertain natural language processing results; receiving annotations of the second set of documents elicited by second human readable prompts; and retraining a natural language model using the annotated second set of documents.