公开(公告)号：US11232799B1

公开(公告)日：2022-01-25

申请号：US16177164

申请日：2018-10-31

Applicant: Amazon Technologies, Inc.

Inventor： Apoorv Birthare ,  John Baker ,  Kranthi Kumar Boyapati ,  Krishna Chaitanya Gourishetti ,  Enrico Sartorello

IPC: G10L15/00 ,  G10L15/30 ,  G10L15/22 ,  H04L29/08 ,  G06N20/00 ,  G10L15/26

Abstract: Techniques for speech recognition are described. For example, a speech recognition service is to receive a request to perform speech recognition on speech data from a chatbot using a particular speech recognition service; determine a group of hosts to route the speech data to, the group of hosts to host a plurality of speech recognition services including the particular speech recognition service; determine a path to the determined group of hosts using a set of one or more rules; determine a particular host of the group of hosts to perform speech recognition on the speech data, the particular host having the speech recognition service in memory to process the request and being preferred for performing the speech recognition on the speech data; route the speech data to the particular host; perform speech recognition on the speech data using the particular host; and provide a text result of the speech recognition.

公开(公告)号：US10102114B1

公开(公告)日：2018-10-16

申请号：US15453468

申请日：2017-03-08

Applicant: Amazon Technologies, Inc.

Inventor： Gang Jing ,  John Baker ,  Ricardo Rodriguez Munoz

IPC: G06F11/36 ,  G06F9/445 ,  G06F8/60

Abstract: A system for testing candidate code to determine if the candidate code is approved for deployment to a production environment. The system may include a code testing engine configured to test a first code set of previously approved code to a testing server and a production environment including multiple production servers. At a deployment time, the code testing engine may then deploy candidate code to the testing server, while the production servers execute the first code set. Performance data for a time period before the deployment time and after the deployment time is collected. Latency data sets are fetched from the performance data sets and compared using multiple statistical tests. If the multiple statistical tests generate passing results, the candidate code is approved for deployment to the production environment.

公开(公告)号：US10699706B1

公开(公告)日：2020-06-30

申请号：US15716326

申请日：2017-09-26

Applicant: Amazon Technologies, Inc.

Inventor： Vishnu Jayavel ,  Ilana Rozanes ,  John Baker ,  Ryan Andrew Lathan ,  Bradley Lyman ,  Michael Richard Baglole ,  Katherine Ann Baker ,  Aparna Nandyal

IPC: G10L15/22 ,  G10L13/08 ,  G10L15/18 ,  H04L29/08

Abstract: Systems and methods for establishing a communications system between multiple electronic devices are described herein. In some embodiments, first audio data representing a first utterance may be received from an initiating device. A first user account associated with the initiating device may be determined. After determining that the utterance comprises an intent to communicate with a target, a list of entity names associated with the user account may be generated. Each entity name may represent a user contact associated with the first user account, a user device corresponding to the first user account, and/or a set of entity names representing user contacts and devices. Based on a relative comparison of each entity name to the target's name, an entity name may be selected from the plurality of entity names. A communications session may then be established between the initiating device and a device represented by the selected entity name.

公开(公告)号：US20250111850A1

公开(公告)日：2025-04-03

申请号：US18977703

申请日：2024-12-11

Applicant: Amazon Technologies, Inc.

Inventor： John Baker ,  Anubhav Mishra ,  Bangrui Liu ,  Christopher Michael Hittner ,  Sravan Babu Bodapati ,  Harshal Pimpalkhute ,  Katrin Kirchhoff ,  Anuj Gautam Surana ,  Yilai Su ,  Brandon Louis Mendez ,  Chengshun Zhang

IPC: G10L15/22 ,  G10L13/027 ,  G10L15/08

Abstract: A set of alternative vocal input styles for specifying a parameter of a dialog-driven application is determined. During execution of the application, an audio prompt requesting input in one of the styles is presented. A value of the parameter is determined by applying a collection of analysis tools to vocal input obtained after the prompt is presented. A task of the application is initiated using the value.

公开(公告)号：US12250180B1

公开(公告)日：2025-03-11

申请号：US17393124

申请日：2021-08-03

Applicant: Amazon Technologies, Inc.

Inventor： Sravan Babu Bodapati ,  Ashish Vishwanath Shenoy ,  Monica Lakshmi Sunkara ,  Katrin Kirchhoff ,  Anubhav Mishra ,  Harshal Pimpalkhute ,  John Baker ,  Ganesh Kumar Gella

IPC: H04L51/02 ,  G10L15/197 ,  G10L15/22

Abstract: Techniques for at least the generation of a chatbot built from a custom vocabulary and to use runtime hints during inference are described. In some examples, the generation of the chatbot includes receiving a request to build a chatbot using a bot definition and a custom vocabulary, wherein the chatbot is to use runtime hints during usage; building the chatbot from the bot definition and custom vocabulary by at least: generating automatic speech recognition (ASR) artifacts to be used in decoding audio input into the chatbot into text for at least one other component of the chatbot to use in determining a next act to be performed, the ASR artifacts including artifacts that use the custom vocabulary and artifacts that do not use the custom vocabulary, and storing the ASR artifacts.

公开(公告)号：US12205584B1

公开(公告)日：2025-01-21

申请号：US17532986

申请日：2021-11-22

Applicant: Amazon Technologies, Inc.

Inventor： John Baker ,  Anubhav Mishra ,  Bangrui Liu ,  Christopher Michael Hittner ,  Sravan Babu Bodapati ,  Harshal Pimpalkhute ,  Katrin Kirchhoff ,  Anuj Gautam Surana ,  Yilai Su ,  Brandon Louis Mendez ,  Chengshun Zhang

IPC: G10L15/22 ,  G10L13/027 ,  G10L15/08

Abstract: A set of alternative vocal input styles for specifying a parameter of a dialog-driven application is determined. During execution of the application, an audio prompt requesting input in one of the styles is presented. A value of the parameter is determined by applying a collection of analysis tools to vocal input obtained after the prompt is presented. A task of the application is initiated using the value.

公开(公告)号：US12136413B1

公开(公告)日：2024-11-05

申请号：US17710762

申请日：2022-03-31

Applicant: Amazon Technologies, Inc.

Inventor： Saket Dingliwal ,  Sravan Babu Bodapati ,  Katrin Kirchhoff ,  Ankur Gandhe ,  Anubhav Mishra ,  John Baker ,  Ashish Vishwanath Shenoy ,  Ravi Teja Gadde

IPC: G06F40/40 ,  G10L15/06 ,  G10L15/183

Abstract: Domain-specific parameters may be used for tuning speech processing. A pre-trained transformer-based language model may train domain-specific parameters using domain-specific unlabeled text data. This domain-specific parameters can then be appended to candidate texts produced by a speech model on received speech data and input to the transformer-based language model to score the candidate texts. The scores of the candidate texts determined using the pre-trained transformer-based language model can then be used to select a candidate text for further speech processing.

公开(公告)号：US20240333658A1

公开(公告)日：2024-10-03

申请号：US18642717

申请日：2024-04-22

Applicant: Amazon Technologies, Inc.

Inventor： Satya Naga Satis Kumar Gunuputi Alluri Venka ,  John Baker ,  Shahab Shekari ,  Kartik Natarajan ,  Ruhaab Markas ,  Ganesh Kumar Gella ,  Santosh Kumar Ameti

IPC: H04L47/762

CPC classification number: H04L47/762

Abstract: Based on analysis of a workload associated with a throttling key of a client request directed to a first service, a scale-out requirement of the throttling key is obtained at respective resource managers of a plurality of other services which are utilized by the first service to respond to client requests. The resource managers initiate, asynchronously with respect to one another, resource provisioning tasks at each of the other services to fulfill the scale-out requirement. A throttling limit associated with the throttling key is updated to a second throttling key after the resource provisioning tasks are completed by the resource managers, and the updated limit is used to determine whether to accept another client request associated with the throttling key.

公开(公告)号：US11997021B1

公开(公告)日：2024-05-28

申请号：US18193502

申请日：2023-03-30

Applicant: Amazon Technologies, Inc.

Inventor： Satya Naga Satis Kumar Gunuputi Alluri Venka ,  John Baker ,  Shahab Shekari ,  Kartik Natarajan ,  Ruhaab Markas ,  Ganesh Kumar Gella ,  Santosh Kumar Ameti

IPC: H04L47/762

CPC classification number: H04L47/762

Abstract: Based on analysis of a workload associated with a throttling key of a client request directed to a first service, a scale-out requirement of the throttling key is obtained at respective resource managers of a plurality of other services which are utilized by the first service to respond to client requests. The resource managers initiate, asynchronously with respect to one another, resource provisioning tasks at each of the other services to fulfill the scale-out requirement. A throttling limit associated with the throttling key is updated to a second throttling key after the resource provisioning tasks are completed by the resource managers, and the updated limit is used to determine whether to accept another client request associated with the throttling key.

公开(公告)号：US11252149B1

公开(公告)日：2022-02-15

申请号：US17039920

申请日：2020-09-30

Applicant: Amazon Technologies, Inc.

Inventor： Jin Hoon Bang ,  Kartik Rustagi ,  John Baker ,  Swapandeep Singh ,  Rama Krishna Sandeep Pokkunuri ,  Omkar Prakash Kurode

IPC: G06F7/04 ,  H04L29/06 ,  G06F9/54 ,  H04L29/08 ,  H04L12/26

Abstract: A resource of a dialog-driven management service is allocated for a first set of requests based on determining that a population of capacity indicators in a throttling data structure exceeds a threshold. One or more capacity indicator deduction iterations associated with the resource are conducted during a time interval for which the resource remains allocated for the first set of requests. In a given iteration, a number of capacity indicators is deducted from the throttling data structure based on a resource throttling setting. A second set of requests is rejected based on the population of the throttling data structure.