SELECTING FROM A PLURALITY OF AUDIO CLIPS FOR ANNOUNCING MEDIA

• US 20110035222A1
• Filed: 08/04/2009
• Published: 02/10/2011
• Est. Priority Date: 08/04/2009
• Status: Abandoned Application

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Schiller, Jon
• Application Number:
  US12/534,980
• Publication Number:
  US 20110035222A1
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems

Abstract

Systems and methods for selecting one of several audio clips associated with a text item for playback are provided. The electronic device can determine which audio clip to play back at any point in time using different approaches, including for example receiving a user selection or randomly selecting audio clips. In some embodiments, the electronic device can intelligently select audio clips based on attributes of the media item, the electronic device operations, or the environment of the electronic device. The attributes can include, for example, metadata values of the media item, the type of ongoing operations of the electronic device, and environmental characteristics that can be measured or detected using sensors of or coupled to the electronic device. Different audio clips can be associated with particular attribute values, such that an audio clip corresponding to the detected or received attribute values are played back.

Claims

1. A method for selecting one from a plurality of audio clips each associated with the same content, comprising:

determining that a plurality of audio clips corresponding to particular content are available;

identifying characteristics of a media item selected for playback;

selecting one of the plurality of audio clips based on the identified characteristics; and

playing back the selected one of the plurality of audio clips.

2. The method of claim 1, wherein identifying further comprises identifying characteristics of at least one of:

a previously played back media item;

a currently played back media item; and

a media item scheduled for playback in the future.

3. The method of claim 1, wherein identifying further comprises:

identifying characteristics of a collection of media items selected for playback.

4. The method of claim 1, wherein the characteristics comprise at least one of:

artist;

title;

album;

composer;

tv show;

movie;

series;

duration;

genre;

year;

rating;

description;

playlist;

compilation;

beats per minute;

comments;

play count;

codec; and

lyrics.

5. The method of claim 1, wherein:

each of the plurality of audio clips is associated with a particular characteristic.

6. The method of claim 5, further comprising:

identifying the subset of the plurality of audio clips associated with the identified characteristics of the media item;

prioritizing the identified characteristics; and

selecting one of the subset of the plurality of audio clips based on the prioritization of the identified characteristics.

7. The method of claim 6, further comprising:

selecting several of the subset of the audio clips based on the prioritization; and

cycling playback through the selected several of the subset of audio clips.

8. The method of claim 1, wherein:

the plurality of audio clips are associated with the same text item.

9. The method of claim 8, wherein the plurality of audio clips comprise at least one of:

recordings of a person saying the text item; and

an audio clip generated by applying a text-to-speech engine to the text item.

10. An electronic device operative to play back audio clips to announce media items available for playback, comprising audio output circuitry and control circuitry, the control circuitry operative to:

identify a media item being played back by the playback circuitry;

identify a text item for which an audio clip is to be played back;

determine that a plurality of audio clips correspond to the identified text item;

select one of the plurality of audio clips based on attributes of the identified media item; and

direct the audio output circuitry to play back the selected one of the plurality of audio clips.

11. The electronic device of claim 10, wherein the control circuitry is further operative to:

retrieve associations of audio clips with attributes of the identified media item; and

identify the audio clip associated with the most attributes of the identified media item.

12. The electronic device of claim 10, wherein the control circuitry is further operative to:

retrieve associations of audio clips with attributes of the identified media item;

weigh the attributes; and

identify the audio clip associated with the highest weighed average of the attributes.

13. The electronic device of claim 10, wherein the control circuitry is further operative to:

identify a collection of media items available for playback;

identify the plurality of audio clips associated with the identified collection of media items; and

select a set of the plurality of audio clips, wherein the set of plurality of audio clips share similar audio properties and correspond to different text items.

14. The electronic device of claim 13, wherein:

the selected set of plurality of audio clips have the same voice speaking different text items.

15. The electronic device of claim 14, wherein:

the voice used for the set of plurality of audio clips is at least one of a recorded person'"'"'s voice and a voice from a text-to-speech engine.

16. The electronic device of claim 10, wherein the control circuitry is further operative to:

direct the audio output circuitry to play back an audio clip announcing at least one of;

a currently played back media item;

a currently played back collection of media items;

a collection of media items available for playback; and

the future media item scheduled for playback.

17. A method for selecting one of a plurality of audio clips to play back for announcing a media item, comprising:

identifying a media item for which an audio clip is to be played back, the audio clip corresponding to a text item;

determining that a plurality of audio clips corresponding to the text item are available;

detecting an attribute of the environment; and

selecting one of the plurality of audio clips for playback based on the detected attribute of the environment.

18. The method of claim 17, further comprising:

retrieving an association of environment attribute values and audio clips; and

selecting an audio clip associated with at least a minimum number of detected environment attribute values.

19. The method of claim 18, further comprising:

weighing the relative importance of the detected environment attribute values; and

selecting an audio clip based on the weighed importance of the detected environment attribute values.

20. The method of claim 17, wherein the detected attributes of the environment comprise at least one of:

ambient light;

a detected color palette of the environment;

ambient sound;

sound emitted by a user;

ambient temperature;

humidity;

device movement;

device location;

device orientation;

a user'"'"'s temperature;

a user'"'"'s heart rate;

a user'"'"'s pulse waveform;

a user'"'"'s breathing rate;

a user'"'"'s blood-oxygen content;

a user'"'"'s galvanic skin response;

a user'"'"'s heat flux; and

a user'"'"'s mood.

21. Computer readable media for selecting one from a plurality of audio clips each associated with the same content, the computer readable media comprising computer readable instructions recorded thereon for:

determining that a plurality of audio clips corresponding to particular content are available;

identifying characteristics of a media item selected for playback;

selecting one of the plurality of audio clips based on the identified characteristics; and

playing back the selected one of the plurality of audio clips.