Voice-controlled selection of media files utilizing phonetic data

• US 9,153,233 B2
• Filed: 02/21/2006
• Issued: 10/06/2015
• Est. Priority Date: 02/21/2005
• Status: Active Grant

• Current Assignee: Harman Becker Automotive Systems GmbH (Samsung Electronics Co. Ltd.)
• Original Assignee: Harman Becker Automotive Systems GmbH (Samsung Electronics Co. Ltd.)
• Inventors: Hennecke, Marcus, Nle, Gerhard
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US11/360,034
• Publication Number:
  US 20060206327A1
• Time in Patent Office: 3,514 Days
• Field of Search: 704/235, 704/246, 704/251, 704/270, 704/275, 704/8, 704/255, 704/257, 707/3, 707/6
• US Class Current: 1/1
• CPC Class Codes: G10H 2240/131 Library retrieval, i.e. searching a database or selecting a specific musical piece, segment, pattern, rule or parameter set
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A voice-controlled data system is providing that has a storage medium for storing media files, the media files having associated file identification data for allowing the identification of the media files, the file identification data including phonetic data having phonetic information corresponding to the file identification data. The phonetic data is supplied to a speech recognition unit that compares the phonetic data to a speech command input into the speech recognition unit. The data system further includes a file selecting unit that selects one of the media files based on the comparison result.

Claims

1. A voice-controlled data system, comprising:

a storage medium for storing media files, the media files comprising audio files and including associated file identification data for allowing the identification of the media files, where the file identification data associated with each audio file includes first phonetic information that corresponds to first phonetic rules for pronouncing an artist and a song title associated with the audio file and second phonetic information that corresponds to second phonetic rules for pronouncing the artist and the song title associated with the audio file, where the first phonetic information and the second phonetic information included in the file identification data are part of the audio file;

a static vocabulary list including phonetic transcriptions of corresponding user commands;

a phonetic data extraction unit for extracting the first phonetic information and the second phonetic information from the file identification data;

a speech recognition unit for receiving voice data from a user, the voice data including a static vocabulary and a variable vocabulary, the static vocabulary including a user command and the variable vocabulary including the artist and the song title associated with a desired media file, where the speech recognition unit is configured to generate a control command based on comparing the received voice data to the phonetic transcriptions of the static vocabulary list and the first phonetic information and the second phonetic information extracted by the phonetic data extraction unit; and

a media player for playing the media files, the media player configured to select a media file based on the control command received from the speech recognition unit.

2. The data system of claim 1, where the media files are stored on the storage medium in a compressed format.

3. The data system of claim 1 where the control command is generated based on first comparing a phoneme sequence in the voice data to determine a candidate list of best matching media files and then determining the most likely entry in the candidate list by matching acoustic representations of the entries in the candidate list to the voice data.

4. The data system of claim 1, where the media file is stored in the MP3 format and the first phonetic information and the second phonetic information is stored in a tagging part of the media file.

5. The data system of claim 4, where the tagging part of the media file comprises an ID3 tag.

6. The data system of claim 1, where the first phonetic rules correspond to a first language and the second phonetic rules correspond to a second language.

7. The data system of claim 6, where the first phonetic information comprises a first identifier that identifies the first language, and the second phonetic information comprises a second identifier that identifies the second language.

8. A method for a voice-controlled selection of a media file stored on a data storage unit including a plurality of media files, the media files comprising audio files and including media data and associated file identification data, where the file identification data associated with each audio file includes first phonetic information that corresponds to first phonetic rules for pronouncing an artist and a song title associated with the audio file and second phonetic information that corresponds to second phonetic rules for pronouncing the artist and the song title associated with the audio file, where the first phonetic information and the second phonetic information included in the file identification data are part of the audio file, the method comprising:

inputting voice data for selecting one of the media files, the voice data including a static vocabulary and a variable vocabulary, the static vocabulary including a user command and the variable vocabulary including the artist and the song title associated with a desired media file;

supplying the voice data to a speech recognition unit;

providing a static vocabulary list including phonetic transcriptions of corresponding user commands;

extracting the first phonetic information and the second phonetic information from the file identification data;

supplying the phonetic transcriptions from the static vocabulary list and the first phonetic information and the second phonetic information extracted from the file identification data to the speech recognition unit as recognition vocabulary;

generating a control command by comparing the input voice data to the phonetic transcriptions and the extracted phonetic information;

using a media file player to select a media file from the data storage unit in accordance with the generated control command; and

executing a user command on the media file in accordance with the generated control command.

9. The method of claim 8, wherein the user commands of the static vocabulary list are selected from the group consisting of play, stop, go to, forward, and backwards.

10. The method of claim 8, where the step of generating a control command includes the step of comparing a phoneme sequence in the voice data to determine a candidate list of best matching media files and further determining the most likely entry in the candidate list by matching acoustic representations of the entries in the candidate list to the voice data.

11. The method of claim 8, where the media file is stored in the MP3 format and the first phonetic information and the second phonetic information is stored in a tagging part of the media file.

12. The method of claim 11, where the tagging part of the media file comprises an ID3 tag.

13. The method of claim 8, where the first phonetic rules correspond to a first language and the second phonetic rules correspond to a second language.

14. The method of claim 13, where the first phonetic information comprises a first identifier that identifies the first language, and the second phonetic information comprises a second identifier that identifies the second language.