Voice feedback for user interface of media playback device

Patent metadata

Field	Value
Publication number	US-12283271-B2
Application number	US-202117323585-A
Country	US
Kind code	B2
Filing date	May 18, 2021
Priority date	Dec 28, 2017
Publication date	Apr 22, 2025
Grant date	Apr 22, 2025

Abstract

A method of providing voice feedback to a listener as part of a user interface of a media playback system may include: storing multiple different voice feedback recordings in at least one computer-readable storage device, where each of the multiple different voice feedback recordings is of a different voice artist; receiving a listener command corresponding to a musical selection; determining an identifying musical characteristic of the musical selection; selecting a first voice feedback recording from the multiple different voice feedback recordings, where the first voice feedback recording corresponds to the identifying musical characteristic; and playing the first voice feedback recording to the listener via the media playback system.

First claim

The invention claimed is:

1. A media delivery system comprising:
a processing device; and
a memory device coupled to the processing device and storing instructions that, when executed by the processing device, cause the media delivery system to:
generate a plurality of sets of voice feedback recordings, wherein each of the plurality of sets of voice feedback recordings is generated from at least one initial voice feedback recording using a machine learning model;
store the plurality of sets of voice feedback recordings, wherein each set corresponds to a different voice;
receive, from a media playback device located in a vehicle, a command received as input from a user of the media playback device, the command associated with playback of a media content item;
in response to receiving the command:
determine an action to be performed in response to the command;
pair a set of voice feedback recordings, from the plurality of sets of voice feedback recordings generated from the at least one initial voice feedback recording using the machine learning model, with the media content item based on a characteristic of the media content item;
select, from the set of voice feedback recordings paired with the media content item, a voice feedback recording that corresponds to the determined action; and
provide an instruction causing playback of the voice feedback recording to the media playback device in the vehicle.

2. The media delivery system of claim 1 , wherein each respective set of voice feedback recordings has a different tempo, different words, different pitches and/or different speaking styles.

3. The media delivery system of claim 1 , wherein the command associated with playback of the media content item includes a selection of at least one of the group consisting of: a song, an album, an artist, a style, a playlist, a shelf comprised of a plurality of cards each representing a media content item, and a card representing a media content item.

4. The media delivery system of claim 1 , wherein the characteristic of the media content item includes at least one of the group consisting of: a track identifier, a title of a song, a title of an album, a style, a tempo, a pitch, an artist, and a recording year.

5. The media delivery system of claim 1 , wherein the media delivery system is caused to further pair the set of voice feedback recordings with the media content item based on a characteristic of the user, the characteristic of the user including at least one of the group consisting of: a geographical location of the user and one or more predefined identifying characteristics provided by the user to the media delivery system.

6. The media delivery system of claim 1 , wherein the media delivery system is further caused to:
derive, from the plurality of sets of voice feedback recordings, an audio prompt; and
provide an instruction to play back the audio prompt to the media playback device, wherein the command received as input from the user at the media playback device is received in response to the playback of the audio prompt, and the voice feedback recording is provided as an audio confirmation.

7. The media delivery system of claim 1 , wherein the media playback device located in the vehicle is one of:
a media playback device integrated with a vehicle head unit of a vehicle media playback system of the vehicle;
a media playback device that is separate from and communicatively coupled to the vehicle media playback system of the vehicle; or
a media playback device that is communicatively coupled to an external speaker assembly that is positioned in the vehicle and is separate from the vehicle media playback system of the vehicle.

8. At least one non-transitory computer readable storage device storing instructions that, when executed by at least one processing device, cause the at least one processing device to:
generate a plurality of sets of voice feedback recordings, wherein each of the plurality of sets of voice feedback recordings is generated from at least one initial voice feedback recording using a machine learning model;
store the plurality of sets of voice feedback recordings, wherein each set corresponds to a different voice;
receive a command input by a user of a media playback device located in a vehicle, the command associated with playback of a media content item;
in response to receiving the command:
determine an action to be performed in response to the command;
pair a set of voice feedback recordings, from the plurality of sets of voice feedback recordings generated from the at least one initial voice feedback recording using the machine learning model, with the media content item based on a characteristic of the media content item;
select, from the set of voice feedback recordings paired with the media content item, a voice feedback recording that corresponds to the determined action; and
provide an instruction causing playback of the voice feedback recording to the media playback device in the vehicle.

9. A media playback device for media content playback in a vehicle, comprising:
a processing device; and
a memory device coupled to the processing device and storing instructions that when executed by the processing device, cause the media playback device to:
generate a plurality of sets of voice feedback recordings, wherein each of the plurality of sets of voice feedback recordings is generated from at least one initial voice feedback recording using a machine learning model;
receive, as input from a user of the media playback device, a command associated with playback of a media content item;
in response to receiving the command:
determine an action to be performed in response to the command;
pair a set of voice feedback recordings with the media content item based on a characteristic of the media content item, wherein a media server stores a plurality of sets of voice feedback recordings of different voices generated from the at least one initial voice feedback recording using the machine learning model, including the set of voice feedback recordings paired with the media content item;
select, from the set of voice feedback recordings paired with the media content item, a voice feedback recording that corresponds to the determined action;
receive, from the media server, the voice feedback recording; and
play the voice feedback recording in the vehicle.

10. The media playback device of claim 9 , wherein the media playback device is integrated with a vehicle head unit of a vehicle media playback system of the vehicle.

11. The media playback device of claim 10 , wherein the vehicle media playback system further includes a speaker assembly, and to play the voice feedback recording in the vehicle, the media playback device integrated with the vehicle head unit provides a signal to the speaker assembly to cause the voice feedback recording to be played as media output of the speaker assembly in the vehicle.

12. The media playback device of claim 9 , wherein the media playback device is a separate device that is communicatively coupled to a vehicle media playback system of the vehicle, the vehicle media playback system including:
a vehicle head unit that receives a first signal from the media playback device to play the voice feedback recording and generates media output based on the first signal; and
a speaker assembly that receives a second signal from the vehicle head unit and causes the voice feedback recording to be played as the media output of the speaker assembly in the vehicle.

13. The media playback device of claim 9 , wherein the media playback device is communicatively coupled to an external

Assignees

• Spotify Ab

Inventors

• Garmark Sten

Classifications

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10H2210/076

  for extraction of timing, tempo; Beat detection · CPC title

• G10H2210/066

  for pitch analysis as part of wider processing for musical purposes, e.g. transcription, musical performance evaluation; Pitch recognition, e.g. in polyphonic sounds; Estimation or use of missing fundamental · CPC title

• G11B27/34

  Indicating arrangements  {(indicating means incorporated in magazine or cassette G11B23/046 and G11B23/0875; indicating measured values in general G01D)} · CPC title

• G06F3/167 Primary

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title