System and method of media file access and retrieval using speech recognition

• US 20040054541A1
• Filed: 09/16/2002
• Published: 03/18/2004
• Est. Priority Date: 09/16/2002
• Status: Active Grant

• Current Assignee: Intertrust Technologies Corporation (Fidelio Acquisition Co LLC)
• Original Assignee: Matsushita Electric Industrial Company Limited (Panasonic Holdings Corporation)
• Inventors: Rigazio, Luca, Junqua, Jean-Claude, Kryze, David, Nguyen, Patrick
• Granted Patent: US 6,907,397 B2
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: G06F 16/433 using audio data
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access

Abstract

An embedded device for playing media files is capable of generating a play list of media files based on input speech from a user. It includes an indexer generating a plurality of speech recognition grammars. According to one aspect of the invention, the indexer generates speech recognition grammars based on contents of a media file header of the media file. According to another aspect of the invention, the indexer generates speech recognition grammars based on categories in a file path for retrieving the media file to a user location. When a speech recognizer receives an input speech from a user while in a selection mode, a media file selector compares the input speech received while in the selection mode to the plurality of speech recognition grammars, thereby selecting the media file.

Claims

1. An embedded device for playing media files and generating a play list of media files based on input speech from a user, comprising:

an indexer generating a plurality of speech recognition grammars, including at least one of;

(a) a first indexer generating a first speech recognition grammar based on contents of a media file header of the media file; and

(b) a second indexer generating a second speech recognition grammar based on categories in a file path for retrieving the media file to a user location;

a speech recognizer receiving an input speech from a user while in a selection mode; and

a media file selector comparing the input speech received while in the selection mode to the plurality of speech recognition grammars, thereby selecting the media file.

2. The device of claim 1, wherein said indexer generating the plurality of speech recognition grammars includes the first indexer generating the first speech recognition grammar based on contents of the media file header of the media file.

3. The device of claim 2, wherein said indexer generating the plurality of speech recognition grammars includes the second indexer generating the second speech recognition grammar based on categories in the file path for retrieving the media file from the user location.

4. The device of claim 1, wherein said indexer generating the plurality of speech recognition grammars includes the second indexer generating the second speech recognition grammar based on categories in the file path for retrieving the media file from the user location.

5. The device of claim 1, wherein the media file contains speech, and said indexer generating the plurality of speech recognition grammars includes a third indexer recognizing speech within the media file and generating a third speech recognition grammar based on the recognized speech within the media file.

6. The device of claim 1, wherein said speech recognizer receives an input speech from the user while in a non-selection mode, wherein said indexer generates a classification based on the input speech received while in the non-selection mode, and wherein said indexer includes a fourth indexer generating a fourth speech recognition grammar based on the generated classification.

7. The device of claim 1, wherein said indexer includes a fifth indexer generating a fifth speech recognition grammar based on supplemental descriptive text associated with the media file and provided in a data store on a computer network.

8. The device of claim 1 comprising:

a data link receiving the media file over a computer network; and

a data store storing the received media file in association with the plurality of speech recognition grammars.

9. The device of claim 1 comprising a play list generator operable to add the media file to the play list upon selection of the media file while in an insertion mode.

10. The device of claim 1 comprising a play list generator operable to remove the media file from a play list upon selection of the media file while in a deletion mode.

11. A method of selecting a media file using input speech, comprising:

generating a plurality of speech recognition grammars, including at least one of;

(a) generating a first speech recognition grammar based on contents of a media file header of the media file; and

(b) generating a second speech recognition grammar based on categories in a file path for retrieving the media file to a user location;

receiving an input speech from a user while in a selection mode; and

comparing the input speech received while in the selection mode to the plurality of speech recognition grammars, thereby selecting the media file.

12. The method of claim 11 wherein said generating a plurality of speech recognition grammars includes generating a first speech recognition grammar based on contents of the media file header of the media file.

13. The method of claim 12, wherein said generating a plurality of speech recognition grammars includes generating a second speech recognition grammar based on categories in a file path for retrieving the media file from a user location.

14. The method of claim 11, wherein said generating a plurality of speech recognition grammars includes generating a second speech recognition grammar based on categories in a file path for retrieving the media file from a user location.

15. The method of claim 11, wherein the media file contains speech, the method comprising recognizing speech within the media file, wherein said generating a plurality of speech recognition grammars includes generating a third speech recognition grammar based on the recognized speech within the media file.

16. The method of claim 11 comprising:

receiving an input speech from the user while in a non-selection mode;

generating a classification based on the input speech received while in the non-selection mode; and

associating the generated classification with the media file,

wherein said generating a plurality of speech recognition grammars includes generating a fourth speech recognition grammar based on the classification associated with the media file.

17. The method of claim 11, comprising generating a fifth speech recognition grammar based on supplemental descriptive text associated with the media file and provided in a data store on a computer network.

18. The method of claim 11 comprising:

receiving the media file over a computer network; and

storing the received media file in a data store in association with the plurality of speech recognition grammars.

19. The method of claim 11 comprising:

entering an insertion mode; and

adding the media file to a play list upon selection of the media file while in the insertion mode.

20. The method of claim 11 comprising:

entering a deletion mode; and

removing the media file from a play list upon selection of the media file while in the deletion mode.