公开(公告)号：US10192544B2

公开(公告)日：2019-01-29

申请号：US15487189

申请日：2017-04-13

Applicant: Yactraq Online Inc.

Inventor： Lee Allan Iverson

IPC: G10L15/06 ,  G06F17/28 ,  G06F17/27 ,  G10L15/19 ,  G10L15/18 ,  G10L15/26 ,  G10L15/08

Abstract: Disclosed herein are various embodiments of methods and systems for constructing a first language model for use by a first Language Processing (LP) application of a plurality of LP applications. Each LP application of the plurality of LP applications receives one or more of a language based input, a derivative of the language based input, a response to the language based input and a derivative of the response. The method includes processing at least one input by a second LP application of the plurality of LP applications. Based on the processing of the second LP application, at least one output is generated. Subsequently, at least a portion of the first language model is constructed based on the at least one output.

公开(公告)号：US10186259B2

公开(公告)日：2019-01-22

申请号：US15679232

申请日：2017-08-17

Applicant: Nuance Communications, Inc.

Inventor： Michael Czahor

IPC: G10L21/00 ,  G10L15/19 ,  G06F17/28 ,  G10L15/22

Abstract: Disclosed herein are systems, computer-implemented methods, and computer-readable media for enhancing speech recognition accuracy. The method includes dividing a system dialog turn into segments based on timing of probable user responses, generating a weighted grammar for each segment, exclusively activating the weighted grammar generated for a current segment of the dialog turn during the current segment of the dialog turn, and recognizing user speech received during the current segment using the activated weighted grammar generated for the current segment. The method can further include assigning probability to the weighted grammar based on historical user responses and activating each weighted grammar is based on the assigned probability. Weighted grammars can be generated based on a user profile. A weighted grammar can be generated for two or more segments. The weighted grammar is weighted based on a user profile which includes of information about a number called from, account information, a time of day, and a date. Exclusively activating each weighted grammar can include a transition period blending the previously activated grammar and the grammar to be activated.

公开(公告)号：US10170114B2

公开(公告)日：2019-01-01

申请号：US15811586

申请日：2017-11-13

Applicant: Promptu Systems Corporation

Inventor： Harry William Printz

IPC: G10L15/22 ,  G10L15/18 ,  G06F17/27 ,  G10L15/16 ,  G10L15/19 ,  G01C21/36 ,  G10L15/32 ,  G10L15/02 ,  G06F3/16

Abstract: Various embodiments contemplate systems and methods for performing automatic speech recognition (ASR) and natural language understanding (NLU) that enable high accuracy recognition and understanding of freely spoken utterances which may contain proper names and similar entities. The proper name entities may contain or be comprised wholly of words that are not present in the vocabularies of these systems as normally constituted. Recognition of the other words in the utterances in question, e.g. words that are not part of the proper name entities, may occur at regular, high recognition accuracy. Various embodiments provide as output not only accurately transcribed running text of the complete utterance, but also a symbolic representation of the meaning of the input, including appropriate symbolic representations of proper name entities, adequate to allow a computer system to respond appropriately to the spoken request without further analysis of the user's input.

公开(公告)号：US10163440B2

公开(公告)日：2018-12-25

申请号：US15399070

申请日：2017-01-05

Applicant: SRI International

Inventor： Osher Yadgar ,  Neil Yorke-Smith ,  Bart Peintner ,  Gokhan Tur ,  Necip Fazil Ayan ,  Michael J. Wolverton ,  Girish Acharya ,  Venkatarama Satyanarayana Parimi ,  William S. Mark ,  Wen Wang ,  Andreas Kathol ,  Regis Vincent ,  Horacio E. Franco

IPC: G10L15/18 ,  G10L15/22 ,  G10L15/19 ,  G06F17/28 ,  H04M3/493

Abstract: A method for assisting a user with one or more desired tasks is disclosed. For example, an executable, generic language understanding module and an executable, generic task reasoning module are provided for execution in the computer processing system. A set of run-time specifications is provided to the generic language understanding module and the generic task reasoning module, comprising one or more models specific to a domain. A language input is then received from a user, an intention of the user is determined with respect to one or more desired tasks, and the user is assisted with the one or more desired tasks, in accordance with the intention of the user.

公开(公告)号：US10063701B2

公开(公告)日：2018-08-28

申请号：US14290446

申请日：2014-05-29

Applicant: Angel.com Incorporated

Inventor： Praphul Kumar ,  Aaron Wellman

IPC: H04M1/64 ,  H04M3/493 ,  G10L15/19 ,  G10L15/22 ,  H04M11/00 ,  G10L15/06 ,  G10L15/183 ,  H04M3/42 ,  H04M3/51

CPC classification number: H04M3/4936 ,  G10L15/183 ,  G10L15/19 ,  G10L15/22 ,  G10L2015/0635 ,  G10L2015/0638 ,  G10L2015/223 ,  H04M3/42382 ,  H04M3/4938 ,  H04M3/51

Abstract: A request to execute an interaction site associated with a custom grammars file is received from a user device and by a communications system. An interaction flow document to execute the interaction site is accessed by the communications system. The custom grammars file is accessed by the communications system, the custom grammars file being configured to enable the communications system to identify executable commands corresponding to utterances spoken by users of user devices. An utterance spoken by a user of the user device is received from the user device and by the communications system. The utterance is stored by the communications system. The custom grammars file is updated by a grammar generation system to include a representation of the stored utterance for processing utterances in subsequent communications with users.

公开(公告)号：US20180122382A1

公开(公告)日：2018-05-03

申请号：US15859176

申请日：2017-12-29

Applicant: Intellisist, Inc.

Inventor： David Milstein

IPC: G10L15/26 ,  H04M3/51 ,  H04M3/42 ,  G10L15/19 ,  G10L15/01 ,  G10L15/18 ,  G10L15/10 ,  G10L15/06

CPC classification number: G10L15/26 ,  G10L15/01 ,  G10L15/06 ,  G10L15/063 ,  G10L15/10 ,  G10L15/1822 ,  G10L15/19 ,  G10L15/22 ,  G10L2015/0631 ,  G10L2015/0638 ,  H04M3/42221 ,  H04M3/51 ,  H04M3/5183

Abstract: A computer-implemented system and method for transcription error reduction is provided. A transcribed value and a confidence score are assigned to each utterance in a stream of audio data. Those utterances with confidence scores that fall below a confidence threshold are identified as questionable utterances. At least one of the questionable utterances is placed into a pool of related utterances also determined to be questionable. A determination is made as to whether the pool satisfies a size threshold within a predetermined amount of time. A sample of the questionable utterances from the pool is obtained when the pool satisfies the size threshold within the predetermined amount of time. The sample of questionable utterances is provided to at least one human transcriber for verification.

公开(公告)号：US09786276B2

公开(公告)日：2017-10-10

申请号：US14467242

申请日：2014-08-25

Applicant: Honeywell International Inc.

Inventor： Jayaprakash Meruva ,  Bhabesh Chandra Acharya ,  Sekhar Kommoju ,  Steve Huseth ,  Chandrakantha Reddy

IPC: G10L15/22 ,  G10L15/19 ,  H04N7/18 ,  H04N5/232

CPC classification number: G10L15/22 ,  G10L15/19 ,  G10L2015/223 ,  H04N5/232 ,  H04N7/181

Abstract: A speech-enabled management system is described herein. One system includes a grammar building tool configured to create a set of grammar keys based on ontology analytics corresponding to data received from a digital video manager (DVM) server, a speech recognition engine configured to recognize a speech command from a set of grammar files, a command translator configured to translate the recognized speech command to an executable command, and a processor configured to execute the speech command based on a particular grammar key from the set of grammar keys.

公开(公告)号：US09761220B2

公开(公告)日：2017-09-12

申请号：US14711447

申请日：2015-05-13

Applicant: Microsoft Technology Licensing, LLC

Inventor： Michael Levit ,  Shuangyu Chang ,  Benoit Dumoulin

IPC: G10L15/06 ,  G10L15/10 ,  G10L15/14 ,  G10L15/18 ,  G10L15/19

CPC classification number: G10L15/063 ,  G10L15/10 ,  G10L15/14 ,  G10L15/18 ,  G10L15/19 ,  G10L2015/0633 ,  G10L2015/0635

Abstract: A computer system for language modeling may collect training data from one or more information sources, generate a spoken corpus containing text of transcribed speech, and generate a typed corpus containing typed text. The computer system may derive feature vectors from the spoken corpus, analyze the typed corpus to determine feature vectors representing items of typed text, and generate an unspeakable corpus by filtering the typed corpus to remove each item of typed text represented by a feature vector that is within a similarity threshold of a feature vector derived from the spoken corpus. The computer system may derive feature vectors from the unspeakable corpus and train a classifier to perform discriminative data selection for language modeling based on the feature vectors derived from the spoken corpus and the feature vectors derived from the unspeakable corpus.

公开(公告)号：US09756185B1

公开(公告)日：2017-09-05

申请号：US15391962

申请日：2016-12-28

Applicant: TETON1, LLC

Inventor： Robert T. Madden, Jr. ,  Christopher P. Derikart ,  Edward A. Donnelly

IPC: H04M3/00 ,  H04M3/51 ,  H04M3/42 ,  G10L15/19 ,  G10L15/18

CPC classification number: H04M3/5175 ,  G10L15/08 ,  G10L2015/088 ,  H04M3/42221 ,  H04M2203/403

Abstract: A system and method for automated call analysis using context specific lexicons. A system includes memory and a processor configured to executed instructions. The system includes a recording component, a lexicon component, an analysis component, and a display component. The lexicon component defines a plurality of context specific lexicons, with each context specific lexicon having elements associated with one of a plurality of unique conversation segments. The analysis component configured to identify elements of the context specific lexicons, and associate each identified element with a time location in a telephonic conversation. The display component configured to graphically present a multi-line graph such that the intersections of the lines indicate transitions between the unique conversation segments.

公开(公告)号：US09741340B2

公开(公告)日：2017-08-22

申请号：US14535869

申请日：2014-11-07

Applicant: Nuance Communications, Inc.

Inventor： Michael Czahor

IPC: G10L21/00 ,  G10L15/19 ,  G06F17/28 ,  G10L15/22

CPC classification number: G10L15/19 ,  G06F17/289 ,  G10L2015/227 ,  G10L2015/228

Abstract: Disclosed herein are systems, computer-implemented methods, and computer-readable media for enhancing speech recognition accuracy. The method includes dividing a system dialog turn into segments based on timing of probable user responses, generating a weighted grammar for each segment, exclusively activating the weighted grammar generated for a current segment of the dialog turn during the current segment of the dialog turn, and recognizing user speech received during the current segment using the activated weighted grammar generated for the current segment. The method can further include assigning probability to the weighted grammar based on historical user responses and activating each weighted grammar is based on the assigned probability. Weighted grammars can be generated based on a user profile. A weighted grammar can be generated for two or more segments. The weighted grammar is weighted based on a user profile which consists of information about a number called from, demographic information, account information, a time of day, and a date. Exclusively activating each weighted grammar can include a transition period blending the previously activated grammar and the grammar to be activated.