公开(公告)号：US20190318737A1

公开(公告)日：2019-10-17

申请号：US16275074

申请日：2019-02-13

Applicant: Amazon Technologies, Inc.

Inventor： Imre Attila Kiss ,  Arthur Richard Toth ,  Lambert Mathias

IPC: G10L15/22 ,  G10L15/26 ,  G06F17/27 ,  G10L17/00

Abstract: In speech processing systems personalization is added in the Natural Language Understanding (NLU) processor by incorporating external knowledge sources of user information to improve entity recognition performance of the speech processing system. Personalization in the NLU is effected by incorporating one or more dictionaries of entries, or gazetteers, with information personal to a respective user, that provide the user's information to permit disambiguation of semantic interpretation for input utterances to improve quality of speech processing results.

公开(公告)号：US10283119B2

公开(公告)日：2019-05-07

申请号：US15966400

申请日：2018-04-30

Applicant: Amazon Technologies, Inc.

Inventor： Lambert Mathias ,  Ying Shi ,  Imre Attila Kiss ,  Ryan Paul Thomas ,  Frederic Johan Georges Deramat

IPC: G10L15/00 ,  G10L15/22 ,  G10L15/26 ,  G06F17/28 ,  G06F17/27 ,  G10L13/08

Abstract: Features are disclosed for processing a user utterance with respect to multiple subject matters or domains, and for selecting a likely result from a particular domain with which to respond to the utterance or otherwise take action. A user utterance may be transcribed by an automatic speech recognition (“ASR”) module, and the results may be provided to a multi-domain natural language understanding (“NLU”) engine. The multi-domain NLU engine may process the transcription(s) in multiple individual domains rather than in a single domain. In some cases, the transcription(s) may be processed in multiple individual domains in parallel or substantially simultaneously. In addition, hints may be generated based on previous user interactions and other data. The ASR module, multi-domain NLU engine, and other components of a spoken language processing system may use the hints to more efficiently process input or more accurately generate output.

公开(公告)号：US10176802B1

公开(公告)日：2019-01-08

申请号：US15091722

申请日：2016-04-06

Applicant: Amazon Technologies, Inc.

Inventor： Faisal Ladhak ,  Ankur Gandhe ,  Markus Dreyer ,  Ariya Rastrow ,  Björn Hoffmeister ,  Lambert Mathias

IPC: G10L15/16 ,  G10L19/038 ,  G06N3/04

Abstract: An automatic speech recognition (ASR) system may convert an ASR output lattice into a matrix form, thus maintaining certain information included in the lattice that might otherwise be lost in an N-best list output. The matrix representation of the lattice may be encoded using a recurrent neural network (RNN) to create a vector representation of the lattice. The vector representation may then be used by the system to perform additional operations, such as ASR results confirmation.

公开(公告)号：US20180315425A1

公开(公告)日：2018-11-01

申请号：US15966400

申请日：2018-04-30

Applicant: Amazon Technologies, Inc.

Inventor： Lambert Mathias ,  Ying Shi ,  Imre Attila Kiss ,  Ryan Paul Thomas ,  Frederic Johan Georges Deramat

IPC: G10L15/22 ,  G10L15/26 ,  G06F17/28 ,  G06F17/27 ,  G10L13/08

CPC classification number: G10L15/22 ,  G06F17/277 ,  G06F17/278 ,  G06F17/279 ,  G06F17/28 ,  G06F17/2881 ,  G10L13/08 ,  G10L15/26

Abstract: Features are disclosed for processing a user utterance with respect to multiple subject matters or domains, and for selecting a likely result from a particular domain with which to respond to the utterance or otherwise take action. A user utterance may be transcribed by an automatic speech recognition (“ASR”) module, and the results may be provided to a multi-domain natural language understanding (“NLU”) engine. The multi-domain NLU engine may process the transcription(s) in multiple individual domains rather than in a single domain. In some cases, the transcription(s) may be processed in multiple individual domains in parallel or substantially simultaneously. In addition, hints may be generated based on previous user interactions and other data. The ASR module, multi-domain NLU engine, and other components of a spoken language processing system may use the hints to more efficiently process input or more accurately generate output.

公开(公告)号：US09959869B2

公开(公告)日：2018-05-01

申请号：US15694996

申请日：2017-09-04

Applicant: Amazon Technologies, Inc.

Inventor： Lambert Mathias ,  Ying Shi ,  Imre Attila Kiss ,  Ryan Paul Thomas ,  Frederic Johan Georges Deramat

IPC: G10L15/00 ,  G10L15/22 ,  G10L15/26 ,  G06F17/27 ,  G10L13/08

CPC classification number: G10L15/22 ,  G06F17/277 ,  G06F17/278 ,  G06F17/279 ,  G06F17/28 ,  G06F17/2881 ,  G10L13/08 ,  G10L15/26

Abstract: Features are disclosed for processing a user utterance with respect to multiple subject matters or domains, and for selecting a likely result from a particular domain with which to respond to the utterance or otherwise take action. A user utterance may be transcribed by an automatic speech recognition (“ASR”) module, and the results may be provided to a multi-domain natural language understanding (“NLU”) engine. The multi-domain NLU engine may process the transcription(s) in multiple individual domains rather than in a single domain. In some cases, the transcription(s) may be processed in multiple individual domains in parallel or substantially simultaneously. In addition, hints may be generated based on previous user interactions and other data. The ASR module, multi-domain NLU engine, and other components of a spoken language processing system may use the hints to more efficiently process input or more accurately generate output.

公开(公告)号：US20170278514A1

公开(公告)日：2017-09-28

申请号：US15196540

申请日：2016-06-29

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： Lambert Mathias ,  Thomas Kollar ,  Arindam Mandal ,  Angeliki Metallinou

IPC: G10L15/22 ,  G06F17/30 ,  G10L15/18 ,  G10L15/14 ,  G10L15/26 ,  G10L15/02

CPC classification number: G10L15/22 ,  G06F17/277 ,  G06F17/279 ,  G06F17/30637 ,  G06F17/30654 ,  G06F17/30705 ,  G10L15/02 ,  G10L15/142 ,  G10L15/1815 ,  G10L15/26 ,  G10L2015/223

Abstract: A system capable of performing natural language understanding (NLU) without the concept of a domain that influences NLU results. The present system uses a hierarchical organizations of intents/commands and entity types, and trained models associated with those hierarchies, so that commands and entity types may be determined for incoming text queries without necessarily determining a domain for the incoming text. The system thus operates in a domain agnostic manner, in a departure from multi-domain architecture NLU processing where a system determines NLU results for multiple domains simultaneously and then ranks them to determine which to select as the result.

公开(公告)号：US20150340033A1

公开(公告)日：2015-11-26

申请号：US14283017

申请日：2014-05-20

Applicant: Amazon Technologies, Inc.

Inventor： Giuseppe Di Fabbrizio ,  Shishir Sridhar Bharathi ,  Ying Shi ,  Lambert Mathias

IPC: G10L15/18 ,  G10L15/00

Abstract: Features are disclosed for processing and interpreting natural language, such as interpretations of user utterances, in multi-turn dialog interactions. Context information regarding interpretations of user utterances and system responses to the user utterances can be maintained. Subsequent user utterances can be interpreted using the context information, rather than being interpreted without context. In some cases, interpretations of subsequent user utterances can be merged with interpretations of prior user utterances using a rule-based framework. Rules may be defined to determine which interpretations may be merged and under what circumstances they may be merged.

Abstract translation: 公开了用于处理和解释自然语言的特征，例如用户话语的解释，在多圈对话交互中。 可以保持关于用户话语的解释和对用户话语的系统响应的上下文信息。 可以使用上下文信息来解释随后的用户话语，而不是在没有上下文的情况下被解释。 在某些情况下，使用基于规则的框架，对后续用户话语的解释可以与先前用户话语的解释相结合。 可以定义规则来确定哪些解释可以合并，以及在什么情况下可以合并。

公开(公告)号：US20220148590A1

公开(公告)日：2022-05-12

申请号：US17454716

申请日：2021-11-12

Applicant: Amazon Technologies, Inc.

Inventor： Lambert Mathias ,  Ying Shi ,  Imre Attila Kiss ,  Ryan Paul Thomas ,  Frederic Johan Georges Deramat

IPC: G10L15/22 ,  G10L15/26 ,  G06F40/35 ,  G06F40/40 ,  G06F40/56 ,  G06F40/284 ,  G06F40/295 ,  G10L13/08

Abstract: Features are disclosed for processing a user utterance with respect to multiple subject matters or domains, and for selecting a likely result from a particular domain with which to respond to the utterance or otherwise take action. A user utterance may be transcribed by an automatic speech recognition (“ASR”) module, and the results may be provided to a multi-domain natural language understanding (“NLU”) engine. The multi-domain NLU engine may process the transcription(s) in multiple individual domains rather than in a single domain. In some cases, the transcription(s) may be processed in multiple individual domains in parallel or substantially simultaneously. In addition, hints may be generated based on previous user interactions and other data. The ASR module, multi-domain NLU engine, and other components of a spoken language processing system may use the hints to more efficiently process input or more accurately generate output.

公开(公告)号：US20190325873A1

公开(公告)日：2019-10-24

申请号：US16400905

申请日：2019-05-01

Applicant: Amazon Technologies, Inc.

Inventor： Lambert Mathias ,  Ying Shi ,  Imre Attila Kiss ,  Ryan Paul Thomas ,  Frederic Johan Georges Deramat

IPC: G10L15/22 ,  G10L15/26 ,  G06F17/28 ,  G06F17/27 ,  G10L13/08

Abstract: Features are disclosed for processing a user utterance with respect to multiple subject matters or domains, and for selecting a likely result from a particular domain with which to respond to the utterance or otherwise take action. A user utterance may be transcribed by an automatic speech recognition (“ASR”) module, and the results may be provided to a multi-domain natural language understanding (“NLU”) engine. The multi-domain NLU engine may process the transcription(s) in multiple individual domains rather than in a single domain. In some cases, the transcription(s) may be processed in multiple individual domains in parallel or substantially simultaneously. In addition, hints may be generated based on previous user interactions and other data. The ASR module, multi-domain NLU engine, and other components of a spoken language processing system may use the hints to more efficiently process input or more accurately generate output.

公开(公告)号：US10210862B1

公开(公告)日：2019-02-19

申请号：US15091871

申请日：2016-04-06

Applicant: Amazon Technologies, Inc.

Inventor： Faisal Ladhak ,  Ankur Gandhe ,  Markus Dreyer ,  Ariya Rastrow ,  Björn Hoffmeister ,  Lambert Mathias

IPC: G06F17/20 ,  G10L15/00 ,  G10L15/16 ,  G10L19/038 ,  G06N3/04

Abstract: Neural networks may be used in certain automatic speech recognition systems. To improve performance at these neural networks, the present system converts the lattice into a matrix form, thus maintaining certain information included in the lattice that might otherwise be lost while also placing the lattice in a form that may be manipulated by other components to perform operations such as checking ASR results. The matrix representation of the lattice may be transformed into a vector representation by calculations performed at a recurrent neural network (RNN). By representing the lattice as a vector representation the system may perform additional operations, such as ASR results confirmation.