Amazon Technologies, Inc.

Rawles LLC

Ramy Sammy Sadek

Robert Ramsey Flenniken

Menashe Haskin

Heinz-Dominik Langhammer

Daniel Christopher Bay

Jason Zimmer

Edward Dietz Crump

Joshua Pollack

Christopher D Coley

Yue Liu

Jeffrey Penrod Adams

Olusanya Temitope Soyannwo

Robert Warren Sjoberg

Renwei Yan

Siddarth Raghunathan

A voice controlled assistant has a housing to hold one or more microphones, one or more speakers, and various computing components. The housing has an elongated cylindrical body extending along a center axis between a base end and a top end. The microphone(s) are mounted in the top end and the speaker(s) are mounted proximal to the base end. A control knob is rotatably mounted to the top end of the housing to rotate about the center axis. A light indicator is arranged on the control knob to exhibit various appearance states to provide visual feedback with respect to the one or more functions being performed by the assistant. In one case, the light indicator is used to uniquely identify participants involved in a call.

Voice controlled assistant with light indicator

An audio device may be configured to detect proximity of a user hand based on analysis of audio signals captured by the audio device. For example, the audio device may be configured to perform acoustic echo cancellation based on dynamically calculated filter coefficients. The coefficients may be analyzed to determine proximity of the user hand. The proximity of the hand may be evaluated over time to detect user hand gestures.

Audio-based gesture detection

An audio device may be configured to work in conjunction with a handheld remote controller to receive voice commands from a user. The audio device may have multiple local microphones that are used for sound source localization, to determine the position of the user. A remote audio signal may be received from the remote controller and used in conjunction with local microphone signals generated by the local microphones to aid in determining the position of the user. The last known position of the user may be recorded whenever the user speaks into the remote controller. When the user is unable to find the remote controller, the audio device may direct the user toward the last known position of the user.

Determining user location with remote controller

A posture for a user is derived and used in conjunction with a known physical location of a tangible object or a presented virtual object to determine when the user selects at least a portion of the object. The derived posture comprises a model having a user origin and a gestural terminus, from which a designation vector intersecting with the selected object is determined. The designation vector may extend from a user origin of the dominant eye through a gestural terminus comprising a tip of an outstretched finger. For example, the user may point to a chair in the room to select the physical chair, or point to a picture of a chair presented via a display device to select the picture.

Gestural object selection

In a content browsing environment, a system analyzes content to identify audio commands to be made available to users. The audio commands may be chosen so that they are easily differentiable from each other when using machine-based speech recognition techniques. When the content is displayed, the system monitors a user's speech to detect user utterances corresponding to the audio commands and performs content navigation in response to the user utterances.

Navigating content utilizing speech-based user-selectable elements

Techniques are described for selecting audio from locations that are most likely to be sources of spoken commands or words. Directional audio signals are generated to emphasize sounds from different regions of an environment. The directional audio signals are processed by an automated speech recognizer to generate recognition confidence values corresponding to each of the different regions, and the region resulting in the highest recognition confidence value is selected as the region most likely to contain a user who is speaking commands.

Directed audio for speech recognition

Techniques are described for determining locations of audio sources. Audio signals are captured from multiple locations. Pairs of the audio signals are analyzed to create correlograms, indicating correlation scores corresponding to different time offsets between the signals. Based on the correlograms, various locations are analyzed to determine probabilities of audio originating from those locations. The highest probabilities are found, indicating locations containing audio sources. In some situations, the audio sources may be reflective sources, and the locations of the reflective sources may be used to determine locations of objects or surfaces.

Growing community of inventors

Mountain View, CA, United States of America

Ramy Sammy Sadek