Amazon Technologies, Inc.

Chase Brown

Christopher Alan Wheeler

Kevin Bedell

A framework for efficiently importing content into a speech-controlled system in a manner that makes the content easily accessible using voice commands. A speech-controlled system that can be controlled using a variety of commands, including a command to retrieve audio content, can be configured using a framework of content organization that allows new content to be ingested using the framework, thus making the new content accessible to users of the system without manually adjusting the system to recognize when incoming commands call for the new content. The framework can include configured content demarcations (such as information demarcations that divide content into articles, or other sized portions), labels for those demarcations (such as topic descriptors or the like), etc. Various language processing components such as intent classification and named entity recognition can be configured to recognize words that relate to the new content such as recognizing intents to access the new content using the topic descriptors or other labels. In this manner data related to new content may be more efficiently incorporated into a speech processing system.

Multi-portion spoken command framework

A system for easily importing content related to a device into a speech-controlled system in a manner that makes the content easily accessible using voice commands. A speech-controlled system that detect a device type from which audio data is received and can determine if the utterance of the audio data includes a query related to the specific device. The system can then obtain and ingest content related to the device and analyze that content to identify the portion of the content responsive to the query. The remaining content can be stored to potentially respond to future queries.

Growing community of inventors

Boston, MA, United States of America

Chase Brown