Amazon Technologies, Inc.

Naresh Narayanan

Daniel Robert Rashid

Da Teng

Colin Wills Wightman

Adrian Evans

Hugh Evan Secker-Walker

Bharath Bhimanaik Kumar

Alexander David Rosen

Michael James Rodehorst

Muhammad Bilal Khokhar

This disclosure proposes systems and methods for processing natural language inputs using data associated with multiple language recognition contexts (LRC). A system using multiple LRCs can receive input data from a device, identify a first identifier associated with the device, and further identify second identifiers associated with the first identifier and representing candidate users of the device. The system can access language processing data used for natural language processing for the LRCs corresponding to each of the first and second identifiers, and process the input data using the language processing data at one or more stages of automatic speech recognition, natural language understanding, entity resolution, and/or command execution. User recognition can reduce the number of candidate users, and thus the amount of data used to process the input data. Dynamic arbitration can select from between competing hypotheses representing the first identifier and a second identifier, respectively.

Natural language processing using context

Systems and methods for determining that artificial commands, in excess of a threshold value, are detected by multiple voice activated electronic devices is described herein. In some embodiments, numerous voice activated electronic devices may send audio data representing a phrase to a backend system at a substantially same time. Text data representing the phrase, and counts for instances of that text data, may be generated. If the number of counts exceeds a predefined threshold, the backend system may cause any remaining response generation functionality that particular command that is in excess of the predefined threshold to be stopped, and those devices returned to a sleep state. In some embodiments, a sound profile unique to the phrase that caused the excess of the predefined threshold may be generated such that future instances of the same phrase may be recognized prior to text data being generated, conserving the backend system's resources.

Post-speech recognition request surplus detection and prevention

Techniques for prioritizing resources of various users, associated with a device, when responding to a user input received from the device are described. When a user input is received from a device, a system may generate a resource list for a group profile (e.g., a household profile) and each user profile (including any guest user profile) associated with the device. Each resource list may include the catalogs of resources (e.g., songs of a playlist, contacts of a contact list, etc.) of the group profile or user profile. The system may also generate a weight matrix including a respective weight for each catalog of each resource list. Various processing components (e.g., an automatic speech recognition component, a natural language understanding component, and an entity resolution component) may process using the resource lists and the weight matrix to determine an output responsive to the user input.

Resource selection for processing user inputs

Systems and methods for generating sound profiles of artificial commands detected by multiple voice activated electronic devices is described herein. In some embodiments, numerous voice activated electronic devices may send audio data representing a phrase to a backend system at a substantially same time. Text data representing the phrase, and counts for instances of that text data, may be generated. If the number of counts exceeds a predefined threshold, the backend system may cause any remaining response generation functionality that particular command that is in excess of the predefined threshold to be stopped, and those devices returned to a sleep state. In some embodiments, a sound profile unique to the phrase that caused the excess of the predefined threshold may be generated such that future instances of the same phrase may be recognized prior to text data being generated, conserving the backend system's resources.

Sound profile generation based on speech recognition results exceeding a threshold

Features are disclosed for transferring speech recognition workloads between pooled execution resources. For example, various parts of an automatic speech recognition engine may be implemented by various pools of servers. Servers in a speech recognition pool may explore a plurality of paths in a graph to find the path that best matches an utterance. A set of active nodes comprising the last node explored in each path may be transferred between servers in the pool depending on resource availability at each server. A history of nodes or arcs traversed in each path may be maintained by a separate pool of history servers, and used to generate text corresponding to the path identified as the best match by the speech recognition servers.

Growing community of inventors

Seattle, WA, United States of America

Naresh Narayanan