Sonos, Inc.

Akkio, Inc.

Jonathon Reilly

Jonathan P Lang

Steven R Beckhardt

Niels Van Erven

Neil W Griffiths

Christopher Kallai

Romi Kadri

Michael Darrell Andrew Ericson

Craig Wisneski

Seamus Daly

Todd Mansfield

Gregory B Burlingame

Paul Andrew Bates

Mieko Kusano

Wai-Loong Lim

Mark W Triplett

David Duayne Taylor

Brendan Welch

Thomas Calatayud

Adrian Sesto

Christopher D Butts

Andrej Sarkic

Zivthan Dubrovsky

Adrian Eiben

Nicholas Salzman

Jason Heffernan

Hilmar Lehnert

Luis R Vega-Zayas

Mike Chamness

James Y Koo

Wei Hean Liew

Nicholas A J Millington

Luis Vega

Mark Polomski

Steven Robert Beckhardt

Aperahama Parangi

Nate Gillman

Nadia Lahlaf

Nathan Wies

Jonathan Paul Lang

Gregory Burlingame

Michael Darrell Andrew Ericsson

Example techniques relate to playback based on acoustic signals in a system including a first network device and a second network device. A first network device may detect a presence of a user using a camera and/or infrared sensors. The first network device sends, in response to detecting the presence of the user, a particular signal via the first network interface. The second network device receives data corresponding to the particular signal and plays back an audio output corresponding to the particular signal.

Media playback based on sensor data

A method for automatically generating and executing computer code includes receiving, by a machine learning engine, a user-specified data set and a user-specified task. The machine learning engine analyzes at least one characteristic of the user-specified data set and at least one characteristic of the user-specified task and generates at least one machine learning model for processing the user-specified data set. The machine learning model generates a first output by processing the user-specified data set. The machine learning engine receives a natural language description of a user-requested data transformation task for execution with a subset of the first output and directs a large language model to identify an archetype of the user-requested data transformation task. The large language model applies the user-requested data transformation task to the subset of the first output using the archetype to generate a second output.

Methods and systems for automatically generating and executing computer code using a natural language description of a data manipulation to be performed on a data set

Embodiments are provided for replacing media items in a queue of a playback device. An example implementation involves receiving, at the playback device, first data indicating an addition of a first media item to a queue. The playback device determines that the first media item is no longer accessible to the playback device at a later second time. The playback device initiates a query for a media item similar to the first media item and receives second data indicating that a second media item has replaced the first media item in the queue, the second media item being similar to the first media item. In response, the playback device initiates playback of the second media item on the playback device.

Playback device media item replacement

Embodiments are provided for intelligently activating an amplifier in a playback device based on proximity detection. The playback device may be in a quasi-idle state when the playback device is not rendering media content. The quasi-idle state of the playback device may involve an amplifier in the playback device being inactive, while some other components or modules of the playback devices remain active. The playback device may include a proximity sensor configured to detect movement relative to the playback device. If movement is detected indicating that a user input to cause the playback device to render media content is anticipated, the amplifier may be pre-emptively activated such that the playback device enters an active state from the quasi-idle state. In some cases, the playback device may send a message to one or more other playback devices to cause the other playback devices to enter an active state.

Intelligent amplifier activation

Techniques for shaping sound based on a speaker orientation are disclosed. In an embodiment, an audio data stream is obtained by a zone player having one or more speaker drivers, an orientation of the zone player is determined, and sound is reproduced by the zone player based on the orientation. The sound may be further shaped based on other states of the zone player in addition to orientation. The overall sound may be shaped from one zone player or from a collection of zone players.

Position-based playback of multichannel audio

An example embodiment includes a playback device comprising a wireless communications interface including a wireless (e.g., a radio frequency (RF) antenna), a capacitive sensor comprising an electrode that is coupled to the RF antenna, one or more processors, and a data storage having stored therein instructions executable by the one or more processors to cause the playback device to perform operations. The operations include operating the playback device in a first power state, detecting that an object is in proximity to the capacitive sensor, and in response to detecting the object, adjusting operation of the playback device from the first power state to a second power state.

Wireless antenna sensing in a playback device

Embodiments are disclosed for providing play/pause content. An example method includes receiving a command to play audio from a zone, the zone including one or more playback devices, wherein the zone is configured to play items from a playback queue responsive to the command to play audio. The example method also includes determining that the playback queue includes no playable items. The example method also includes automatically placing information identifying at least one playable item in the playback queue. The example method also includes, responsive to the command to play audio, causing to play the at least one playable item by the zone.

Providing media for playback

Embodiments described herein provide for detecting presence of an object in proximity to a playback device and responsively performing one or more operations. In an example implementation, a playback device detects, via a proximity detector of the playback device, presence of an object in proximity to the playback device. In response to detecting the presence of the object, the playback device performs one or more operations.

Control based on proximity

Disclosed embodiments include systems and methods for position-based playback of multichannel audio. Some embodiments include (i) determining first and second positions of first and second playback devices, respectively, (ii) receiving media content comprising multichannel content, (iii) generating first audio according to a first sound characteristic based on the received multichannel audio content and the first position of the first playback device, (iv) generating first audio according to a first sound characteristic based on the received multichannel audio content and the first position of the first playback device, and (v) causing synchronous playback of the generated first audio via the first playback device and the generated second audio via the second playback device.

Disclosed embodiments include systems and methods for position-based playback of multichannel audio. Some embodiments include (i) receiving, via a network interface of a first playback device, an indication of a position of a second playback device, (ii) determining, based on the received indication of the position of the second playback device, an audio characteristic of the first playback device, and (iii) playing back, via one or more transducers associated with the first playback device, a first portion of media content according to the determined audio characteristic in substantial synchrony with playback, via the second playback device, of a second portion of the media content.

Example techniques involve pre-caching media content. An example implementation involves a first playback device detecting, via at least one proximity sensor, motion in proximity to the proximity sensor. In response, the first playback device sends, to a second playback device, one or more first messages indicating that the first playback device detected motion. Afterwards, the first playback device receives, via the network interface from the second playback device in response to the one or more first messages, one or more second messages that instruct the first playback device to pre-cache, from a network source, a portion of audio content indicated in a playback queue associated with a playback device group including the first playback device and the second playback device. The first playback device receives a command to play back the playback queue and plays back the audio content indicated in the playback queue jointly with the second playback device.

Pre-caching of media

System, method, and apparatus including receiving an identification of content played by a playback system and an identification of location of the playback system. A playlist of content is associated with the location. A request is received to retrieve the playlist of content and the requested playlist of content is sent to a playback system.

Providing aggregate playback information

Systems, methods, and apparatus for frequency routing based on orientation are disclosed. An example method includes receiving, by a playback device, an audio data stream. The example method includes determining, by the playback device, an orientation of the playback device. The example method includes routing, by the playback device, a first set of frequencies in the audio data stream to at least one of a plurality of speaker drivers based on the first orientation. The example method includes routing, by the playback device, a second set of frequencies in the audio data stream to the at least one of the plurality of speaker drivers based on the second orientation, wherein the first set of frequencies is different than the second set of frequencies.

Frequency routing based on orientation

An example implementation may involve a group of wearable playback devices including a first wearable playback device and a second wearable playback device. The wearable playback devices render multi-channel audio content according to particular playback responsibilities in the group. When a failure or other issue with the second wearable playback device occurs, the first playback device assumes at least part of the playback responsibility of the second playback device.

Failure recovery of wearable playback device

Growing community of inventors

Cambridge, MA, United States of America

Jonathon Reilly