公开(公告)号：US10032463B1

公开(公告)日：2018-07-24

申请号：US14982587

申请日：2015-12-29

Applicant: Amazon Technologies, Inc.

Inventor： Ariya Rastrow ,  Nikko Ström ,  Spyridon Matsoukas ,  Markus Dreyer ,  Ankur Gandhe ,  Denis Sergeyevich Filimonov ,  Julian Chan ,  Rohit Prasad

IPC: G10L15/183 ,  G10L15/197 ,  G10L15/16 ,  G10L25/30 ,  G10L15/26 ,  G10L15/06 ,  G10L15/22

Abstract: An automatic speech recognition (“ASR”) system produces, for particular users, customized speech recognition results by using data regarding prior interactions of the users with the system. A portion of the ASR system (e.g., a neural-network-based language model) can be trained to produce an encoded representation of a user's interactions with the system based on, e.g., transcriptions of prior utterances made by the user. This user-specific encoded representation of interaction history is then used by the language model to customize ASR processing for the user.

公开(公告)号：US11030999B1

公开(公告)日：2021-06-08

申请号：US16456959

申请日：2019-06-28

Applicant: Amazon Technologies, Inc.

Inventor： Boya Yu ,  Avani Deshpande ,  Adrian Mark McLeod ,  Naga Sai Likhitha Patha ,  Markus Dreyer

IPC: G10L15/18 ,  G10L15/30 ,  G10L15/22 ,  G06F40/295

Abstract: The present disclosure describes the generation and use of word embeddings as part of natural language understanding (NLU) processing performed by a natural language processing system. In at least some examples, the word embeddings may be generated from text corpuses including at least text (representing spoken user inputs) output from automatic speech recognition (ASR) processing. In at least some examples, the word embeddings may be generated from text output from ASR processing and natural language text corresponding to one or more Internet webpages.

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.

公开(公告)号：US10755177B1

公开(公告)日：2020-08-25

申请号：US14985704

申请日：2015-12-31

Applicant: Amazon Technologies, Inc.

Inventor： William Clinton Dabney ,  Arpit Gupta ,  Faisal Ladhak ,  Markus Dreyer ,  Anjishnu Kumar

IPC: G06N5/02 ,  G06F40/40

Abstract: A voice user interface (VUI) system use collaborative filtering to expand its own knowledge base. The system is designed to improve the accuracy and performance of the Natural Language Understanding (NLU) processing that underlies VUIs. The system leverages the knowledge of system users to crowdsource new information.

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：US09911413B1

公开(公告)日：2018-03-06

申请号：US15392718

申请日：2016-12-28

Applicant: Amazon Technologies, Inc.

Inventor： Anjishnu Kumar ,  Markus Dreyer

IPC: G10L15/00 ,  G10L15/18 ,  G06N3/08 ,  G06F17/24 ,  G06F17/27 ,  G10L15/16 ,  G10L15/02 ,  G10L15/06 ,  G10L15/22

CPC classification number: G10L15/1815 ,  G06F17/241 ,  G06F17/2785 ,  G06F17/279 ,  G06N3/08 ,  G10L15/02 ,  G10L15/063 ,  G10L15/16 ,  G10L15/22 ,  G10L2015/0635 ,  G10L2015/223

Abstract: A linguist classifier, for instance intent or slot classifier, is updated using data with only partial annotation indicating overall correctness rather that specific correct intent or slot values, which are treated as “latent” (i.e., unknown) variables. Full annotation of the data is not required. A small amount of fully annotated data may be combined with a substantially larger amount of partially annotated data to update the linguistic classifier. In a specific implementation, the linguistic classifier is a neural network and the weights are trained using a reinforcement learning approach.

公开(公告)号：US20250166609A1

公开(公告)日：2025-05-22

申请号：US19033851

申请日：2025-01-22

Applicant: Amazon Technologies, Inc.

Inventor： Markus Dreyer ,  Sujith Ravi

IPC: G10L13/08 ,  G06F16/34 ,  G10L15/16 ,  G10L15/197

Abstract: Techniques for generating a summary of text-based documents are described. A system may be configured to generate a summary with a certain level of originality as compared to the source document. The system may be provided a value indicating a number of consecutive words that can be copied from the source document, after which the system may copy words from another portion of the source document or generate original words to include in the summary. Different summaries may be generated using multiple documents relating to a particular entity, and one of the different summaries may be selected for output in response to a user input.

公开(公告)号：US10170107B1

公开(公告)日：2019-01-01

申请号：US15394167

申请日：2016-12-29

Applicant: Amazon Technologies, Inc.

Inventor： Markus Dreyer ,  Pavankumar Reddy Muddireddy ,  Anjishnu Kumar

IPC: G10L15/18 ,  G10L15/16 ,  G10L15/06 ,  G06N3/02

Abstract: An approach to extending the recognizable labels of a label recognizer makes use of an encoding of linguistic inputs and label attributes into comparable vectors. The encodings may be determined with artificial neural networks (ANNs) that are jointly trained, and a comparison between the encoding of a sentence input and the encoding of an intent attribute vector may use a fixed function, which does not have to be trained. The encoding of label attributes can generalize permitting adding of a new label via corresponding attributes, thereby avoiding the need to immediately retrain a label recognizer with example inputs.