公开(公告)号：US11526512B1

公开(公告)日：2022-12-13

申请号：US16452363

申请日：2019-06-25

Applicant: Amazon Technologies, Inc.

Inventor： Nissim Halabi ,  Natali Arieli ,  Sagi Bernstein ,  Iftah Gamzu ,  Marina Haikin ,  Yochai Zvik

IPC: G06F16/2453 ,  G06F16/2452 ,  G06K9/62 ,  G10L15/16 ,  G06N20/00 ,  G10L15/22 ,  G06F40/289

Abstract: Systems and methods are described for mitigating errors introduced during processing of user input such as voice input. A query may be derived from processed user input. A performance predictor analyzes the query and uses historical data to predict whether the query will return relevant results if executed. If the query's predicted performance is below a threshold, a query rewriter may identify potential alternatives to the query from a library of “known good” queries. Different analyzers may be applied to identify different sets of alternatives, and machine learning models may be applied to rank the outputs of the analyzers. The best-matching alternatives from each analyzer may then be provided as inputs to a further machine learning model, which assesses the probability that each of the identified alternatives reflects the intent of the user. A most likely alternative may then be selected to execute in place of the original query.

公开(公告)号：US11488581B1

公开(公告)日：2022-11-01

申请号：US16706628

申请日：2019-12-06

Applicant: Amazon Technologies, Inc.

Inventor： Shlomi Chovel ,  Adriano Devillaine ,  Omer Shabtai Jakobinsky ,  Colin Zhen De Kho ,  Kawshik Karur Rangaraju ,  Ajay Soni ,  Yochai Zvik ,  Yunqiang Zhu

IPC: G10L15/06 ,  G10L15/187 ,  G10L15/22

Abstract: A new approach to automatic speech recognition is disclosed. An example method include receiving a first text representing speech recognition of a phrase spoken by a user, isolating a candidate named entity from within the phrase, receiving a first phonetic representation of the candidate named entity, comparing the first phonetic representation to phonetic representations in a mapping database which map the phonetic representations to words to yield a comparison, based on the comparison, identifying a second phonetic representation in the mapping database that matches a second text in the mapping database to the second phonetic representation and replacing the candidate named entity with the second text. The approach can be used for new brands for which automatic speech recognition error rates are high.

公开(公告)号：US12020690B1

公开(公告)日：2024-06-25

申请号：US17489250

申请日：2021-09-29

Applicant: Amazon Technologies, Inc.

Inventor： Iftah Gamzu ,  Marina Haikin ,  Nissim Halabi ,  Yossi Shasha ,  Yochai Zvik ,  Moshe Peretz

IPC: G10L15/08 ,  G06N20/00 ,  G06Q30/0601 ,  G10L21/00

CPC classification number: G10L15/08 ,  G06N20/00 ,  G06Q30/0631 ,  G10L21/00

Abstract: Devices and techniques are generally described for adaptive targeting for voice notifications. In various examples, first data representing a predicted likelihood that a first user will interact with first content within a predefined amount of time may be received. A first set of features including features related to past voice notifications sent to the first user may be determined. A second set of features including features related to interaction with the first content when past voice notifications were sent may be received. A first machine learning model may generate a prediction that a voice notification will increase a probability that the first user interacts with the first content based on the first data, the first set of features, and the second set of features. Audio data comprising the voice notification may be sent to a first device associated with the first content.

公开(公告)号：US11482214B1

公开(公告)日：2022-10-25

申请号：US16711914

申请日：2019-12-12

Applicant: Amazon Technologies, Inc.

Inventor： Natali Arieli ,  Eran Fainman ,  Yochai Zvik ,  Yaniv Ben-Yehuda

IPC: G10L15/22 ,  G10L15/00 ,  G10L15/197 ,  G06F16/9538 ,  G06N7/00 ,  G06N20/00

Abstract: Techniques for speech-to-text hypothesis generation and hypothesis selection described. A text input representing at least part of a voice recording is received from a speech-to-text component. A first text alternative is generated using a finite state transducer based at least in part on the text input. A hypothesis from a hypothesis set is selected using a language model that includes probabilities for sequences of words, the hypothesis set including the text input and the first text alternative. A selected hypothesis text associated with the selected hypothesis is sent to a search engine.