Text to grammar enhancements for media files

• US 7,870,142 B2
• Filed: 09/08/2006
• Issued: 01/11/2011
• Est. Priority Date: 04/04/2006
• Status: Active Grant

• Current Assignee: Visteon Global Technologies Incorporated (Visteon Corporation)
• Original Assignee: Johnson Controls Technology Company (Johnson Controls International plc)
• Inventors: Zeinstra, Mark, Michmerhuizen, Mark, Douthitt, Brian L.
• Primary Examiner(s): Trujillo; James
• Assistant Examiner(s): Spieler; William
• Application Number:
  US11/517,832
• Publication Number:
  US 20070233725A1
• Time in Patent Office: 1,586 Days
• Field of Search: 707/1, 707/755, 709/219, 704/277, 704/1, 704/273, 704/275, 704/257, 704/258, 704/249, 705/14, 701/1, 701/29, 701/202, 434/167, 455/3.05, 455/574
• US Class Current: 707/755
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A control system in a vehicle for extracting meta data from a digital media storage device over a communication link. The system includes a communication module for establishing a communication link with the digital media storage device. The system also includes a processing module coupled to the communication module. The processing module is configured to retrieve, via the communication module, meta data associated with a media file from the digital media storage device. The meta data includes a plurality of entries, wherein at least one of the plurality of entries includes text data. The processing module is also configured to compare the text data of the entries with a set of data files stored in a database. The system also includes a memory module configured to store the plurality of entries retrieved from the digital media storage device.

Claims

1. A method for extracting meta data from a digital media storage device in a vehicle over a communication link between a control module of the vehicle and the digital media storage device, the method comprising:

retrieving meta data from the digital media storage device over the communication link using the control module of the vehicle, the meta data associated with a media file from the digital media storage device, the meta data comprising text data;

comparing the text data with a plurality of stored data entries using the control module;

providing to a processing module, for user a interface, a phonemic representation for the text data based on a pre-stored phonemic representation associated with a stored data entry when the text data matches the stored data entry, the phonemic representation provided by a memory device of the control module;

storing the meta data in the memory device of the vehicle; and

creating a link between the stored meta data and the phonemic representation for the text data; and

maintaining the link in the memory device across power cycles of the control module and using the link in the memory device to provide for phoneme-based speech recognition of the stored meta data.

2. The method according to claim 1, further comprising:

generating a new phonemic representation based on the text data when the text data does not match at least one of the stored data entries.

3. A method according to claim 1, wherein the meta data are retrieved in response to a command by a user.

4. A method according to claim 3, wherein the command from the user is received via a user interface.

5. A method according to claim 3, wherein the command is a spoken command.

6. A method according to claim 1, wherein the communication link between the control system and the digital media storage device is wireless.

7. A method according to claim 1, wherein the plurality of stored data entries includes any of the following:

song title, album title, artist, genre, time length, track number, elapsed time, recording label, recording date, composer, producer, and featured artist.

8. A method according to claim 1, wherein stored data entries are stored in memory associated with the control module and mounted in the vehicle.

9. A method according to claim 1, further comprising:

updating the stored data entries via a second communication link between the control module and an external source.

10. A method according to claim 1, further comprising:

recognizing speech received from a user at an audio input device by comparing the received speech to the phonemic representations.

19. The method according to claim 1, further comprising:

receiving a signal representative of an oral command from an audio input device;

processing the signal representative of the oral command to determine if a phonemic representation of the oral command matches a phonemic representation provided by the control module; and

conducting an action based on the presence of a match and using the maintained link.

11. A control system for mounting in a vehicle and for extracting meta data from a digital media storage device over a communication link, the control system comprising:

a communication module configured to establish a communication link with the digital media storage device;

a processing module coupled to the communication module, the processing module configured to retrieve, via the communication module, meta data associated with a media file from the digital media storage device, the meta data including a plurality of entries, wherein at least one of the plurality of entries includes text data, the processing module further configured to compare the text data of the entries with a set of stored data records; and

a memory module configured to store the plurality of entries retrieved from the digital media storage device,

wherein the processing module is configured to provide a phonemic representation of the text data based on a phonemic representation previously associated with a stored data record of the set of stored data records when the text data matches the stored data record;

wherein the processing module is further configured to store the meta data in a memory device of the vehicle and to create a link between the stored meta data and the phonemic representation for the text data; and

wherein the processing module is further configured to maintain the link in the memory device across power cycles of the control system and to use the link in the memory device to provide for phoneme-based speech recognition of the stored meta data.

12. A control system according to claim 11, wherein the processing module is further configured to generate a new phonemic representation of the text data when the text data does not match at least one of the stored data records.

13. A control system according to claim 11, wherein the processing module is configured to identify the text data of an entry and to generate a phonemic representation of the text data of the entry.

14. A control system according to claim 11,

wherein the processing module is further configured to use input received from a user interface to select at least one media file based on the media file'"'"'s associated meta data, and wherein the processing module is further configured to cause the playback of the media file'"'"'s audio data via an audio system.

15. A control system according to claim 14, wherein the user interface comprises a display and the processing module is configured to provide meta data to a user via the display.

16. A control system according to claim 11, further comprising:

an audio input device configured to receive oral input commands from a user.

17. A control system according to claim 16, further comprising:

a speech recognition module configured to compare the oral input commands to a predetermined set of input commands, wherein the speech recognition module determines an appropriate response based on the oral input commands.

18. A control system according to claim 11, further comprising:

a text conversion engine configured to convert the text data of an entry to an audible speech representation of the text data.

20. The system according to claim 11, wherein the processing module is configured to receive a signal representative of an oral command from an audio input device, wherein the processing module processes the signal representative of the oral command to determine if a phonemic representation of the oral command matches a phonemic representation previously associated with the stored data record, and the processing module conducts an action involving the meta data or the media file associated with the meta data based on the presence of a match and using the maintained link.