Amazon Technologies, Inc.

Canyon IP Holdings, LLC

Rawles LLC

Ryan Paul Thomas

Frederic Johan Georges Deramat

Lambert Leo Mathias

Imre Attila Kiss

Ying Shi

Jeffrey Penrod Adams

Bjorn Hoffmeister

Nikko Strom

Kenneth John Basye

Gregory Michael Hart

Hugh Evan Secker-Walker

John Daniel Thimsen

Stan Weidner Salvador

Jeffrey C O'Neill

Jeffrey Paul Lilly

Shiv Naga Prasad Vitaladevuni

Arindam Mandal

Ming Sun

Frederick Victor Weber

Stephanie Moyerman

Minhua Wu

Sankaran Panchapagesan

Fletcher Liverance

Karthik Ramakrishnan

Donald Erik Schneider

Alex Guazzelli

Michael Maximilian Emanuel Bisani

David Said Martinez

Ramesh Sekaran

John Sitar

An audio controlled assistant captures environmental noise and converts the environmental noise into audio signals. The audio signals are provided to a system which analyzes the audio signals for a plurality of audio prompts, which have been customized for the acoustic environment surrounding the audio controlled assistant by an acoustic modeling system. The system configured to detect the presence of an audio prompt in the audio signals and transmit instructions associated with the detected audio prompt to at least one of the audio controlled assistant or one or more cloud based services, in response.

System for recognizing and responding to environmental noises

Features are disclosed for processing a user utterance with respect to multiple subject matters or domains, and for selecting a likely result from a particular domain with which to respond to the utterance or otherwise take action. A user utterance may be transcribed by an automatic speech recognition ('ASR') module, and the results may be provided to a multi-domain natural language understanding ('NLU') engine. The multi-domain NLU engine may process the transcription(s) in multiple individual domains rather than in a single domain. In some cases, the transcription(s) may be processed in multiple individual domains in parallel or substantially simultaneously. In addition, hints may be generated based on previous user interactions and other data. The ASR module, multi-domain NLU engine, and other components of a spoken language processing system may use the hints to more efficiently process input or more accurately generate output.

Architecture for multi-domain natural language processing

Watch stand

An approach to wakeword detection uses an explicit representation of non-wakeword speech in the form of subword (e.g., phonetic monophone) units that do not necessarily occur in the wakeword and that broadly represent general speech. These subword units are arranged in a 'background' model, which at runtime essentially competes with the wakeword model such that a wakeword is less likely to be declare as occurring when the input matches that background model well. An HMM may be used with the model to locate possible occurrences of the wakeword. Features are determined from portions of the input corresponding to subword units of the wakeword detected using the HMM. A secondary classifier is then used to process the features to yield a decision of whether the wakeword occurred.

Monophone-based background modeling for wakeword detection

Methods, systems, and computer-readable media for unified code and data management for machine learning models are disclosed. A plurality of dependency graphs, including a first dependency graph and a second dependency graph, are generated. The graphs comprise nodes associated with a software development model or machine learning model, and the nodes represent transforms. One or more transforms of the first dependency graph are used to generate first output corresponding to a node in the second dependency graph. One or more transforms of the second dependency graph are used to generate second output based at least in part on the first output.

Unified code and data management for model development

An efficient audio streaming method and apparatus includes a client process implemented on a client or local device and a server process implemented on a remote server or server(s). The client process and server process each have speech recognition components and communicate over a network, and together efficiently manage the detection of speech in an audio signal streamed by the local device to the server for speech recognition and potentially further processing at the server. The client process monitors audio input and in a first detection stage, implements endpointing on the local device to determine when speech is detected. The client process may further determine if a 'wakeword' is detected, and then the client process opens a connection and begins streaming audio to the server process via the network. The server process receives the speech audio stream and monitors the audio, implementing endpointing in the server process, to determine when to tell the client process to close the connection and stop streaming audio. The client process continues streaming audio to the server until the server process determines disconnect criteria have been met and tells the client process to stop streaming audio.

Distributed endpointing for speech recognition

Approaches are described for detecting when an electronic device (such as a mobile phone) has been stolen or is otherwise being used by someone other than an authorized user of the device. At least one sensor of the device can obtain data during a current use of the device, and the device can determine from the data a set of available features. The features can be compared to a corresponding model associated with an owner (or other authorized user) of the device to generate a confidence value indicative of whether the current user operating the device is likely the owner of the device. The confidence value can be compared to at least one confidence threshold, for example, and based on the comparison, the current user can be provided access to at least a portion of functionality of the device and/or a security action can be performed when the confidence value does not at least meet at least one confidence threshold.

Security measures for an electronic device

Features are disclosed for reducing errors in speech recognition processing. Methods for reducing errors can include receiving multiple speech recognition hypotheses based on an utterance indicative of a command or query of a user and determining a command or query within a grammar having a least amount of difference from one of the speech recognition hypotheses. The determination of the least amount of difference may be based at least in part on a comparison of individual subword units along at least some of the sequence paths of the speech recognition hypotheses and the grammar. For example, the comparison may be performed on the phoneme level instead of the word level.

Error reduction in speech processing

In an automatic speech recognition (ASR) processing system, ASR processing may be configured to process speech based on multiple channels of audio received from a beamformer. The ASR processing system may include a microphone array and the beamformer to output multiple channels of audio such that each channel isolates audio in a particular direction. The multichannel audio signals may include spoken utterances/speech from one or more speakers as well as undesired audio, such as noise from a household appliance. The ASR device may simultaneously perform speech recognition on the multi-channel audio to provide more accurate speech recognition results.

Speech recognizer with multi-directional decoding

Natural language controlled devices may be configured to activate command recognition in response to one or more wake words. Techniques are provided to receive a candidate word for evaluation as a wake word that activates a natural language control functionality of a computing device. The candidate word may include one or more words or sounds. Values for multiple wake word metrics are then determined. The candidate word is evaluated based on the various wake word metrics.

Wake word evaluation

Growing community of inventors

Redmond, WA, United States of America

Ryan Paul Thomas