METHOD AND APPARATUS FOR ACCESSING AN AUDIO FILE FROM A COLLECTION OF AUDIO FILES USING TONAL MATCHING

• US 20110238666A1
• Filed: 05/22/2007
• Published: 09/29/2011
• Est. Priority Date: 05/23/2006
• Status: Active Grant

• Current Assignee: Creative Technology Ltd.
• Original Assignee: Creative Technology Ltd.
• Inventors: Xu, Jun, Zhang, Huayun
• Granted Patent: US 8,892,565 B2
• Time in Patent Office: Days
• US Class Current: 707/741
• CPC Class Codes: G06F 16/40 of multimedia data, e.g. slideshows comprising image and additional audio data retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70
• CPC Class Codes: G06F 16/634 Query by example, e.g. query by humming
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content

Abstract

There is provided a method for accessing at least one audio file from a collection comprising more than one audio file stored within or accessible with an electronic device. The method includes generating one index comprising of information entries obtained from each of the more than one audio file in the collection, with each audio file in the collection information being linked to at least one information entry; receiving an input during an input reception mode; converting the input into a digital signal using an analog-digital converter; analysing the digital signal using either frequency spectrum analysis or melody contour analysis into discrete portions; and comparing the discrete portions with the entries in the index. It is advantageous that the audio file is accessed when the discrete portions substantially coincide with at least one of the information entries in the index. The discrete portions may be musical notes, melody contours or waveforms. The at least one information entry may also be musical notes, melody contours or waveforms. An apparatus employing the aforementioned method is also disclosed.

Claims

1. A method for accessing at least one audio file from a collection comprising more than one audio file stored within or accessible with an electronic device, including:

generating one index comprising of information entries obtained from each of the more than one audio file in the collection, with each audio file in the collection being linked to at least one information entry;

receiving an input during an input reception mode;

converting the input into a digital signal using an analog-digital converter;

analysing the digital signal using either frequency spectrum analysis or melody contour analysis into discrete portions; and

comparing the discrete portions with the information entries in the index,

wherein the at least one audio file is accessed when the discrete portions substantially match at least one information entry in the index.

2. The method of claim 1, wherein the discrete portions are selected from the group consisting of:

musical notes, melody contours and waveforms.

3. The method of claim 1, wherein the input is selected from the group consisting of:

singing, humming, whistling, MIDI signals and musical notes.

4. The method of claim 1, wherein the at least one information entry is selected from the group consisting of:

musical notes, melody contours and waveforms.

5. The method of claim 1, wherein the audio file accessible from a source selected from the group consisting of:

the electronic device, any device functionally connected to the electronic device and a connected computer network.

6. The method of claim 3, wherein the input is set by means selected from the group consisting of:

manual selection and automatic selection.

7. The method of claim 1, wherein the input is speaker independent.

8. The method of claim 1, wherein the at least one information entry is received from a source selected from the group consisting of:

the audio file, a pre-recorded vocal entry linked to the audio file, and a connected computer network.

9. The method of claim 1, wherein the electronic device is selected from the group consisting of:

vehicle audio system, desktop computer, notebook computer, PDA, portable media player and mobile phone.

10. The method of claim 1, further including selecting a facility to access the audio files by depressing a pre-determined button at least once.

11. The method of claim 1, further including filtering the input.

12. The method of claim 1, wherein the melody contour analysis is based on analyzing a first order melody contour (UDR), a second order melody contour (udr) and a duration contour (LSK) for an audio output for each audio file.

13. The method of claim 12, wherein analyzing the first order melody contour (UDR), the second order melody contour (udr) and the duration contour (LSK) for an audio output for each audio file generates a “

closeness”

score used for audio file matching.

14. An apparatus for accessing at feast one audio file from a collection comprising more than one audio file stored within or accessible with the apparatus, including:

an indexer configured to generate an index comprising information entries obtained from each of the more than one audio files in the collection, with each audio file in the collection being linked to at least one information entry;

a receiver configured to receive an input during an input reception mode;

an analog-digital converter configured to convert the input into a digital signal; and

a processor configured to analyse the digital signal using either frequency spectrum analysis or melody contour analysis into discrete portions and to compare the discrete portions with the information entries in the index,

wherein the at least one audio file is accessed when the discrete portions substantially match at least one information entry in the index.

15. The apparatus of claim 14, wherein the apparatus is selected from the group consisting of:

vehicle audio system, desktop computer, notebook computer, PDA, portable media player and mobile phone.

16. The apparatus of claim 14, wherein the input is selected from the group consisting of:

singing, humming, whistling, MIDI signals and musical notes.

17. The apparatus of claim 16, wherein the input is set by means selected from the group consisting of:

manual selection and automatic selection.

18. The apparatus of claim 14, wherein the at least one information entry is selected from the group consisting of:

musical notes, melody contours and waveforms.

19. The apparatus of claim 14, wherein the input is speaker independent.

20. The apparatus of claim 14, wherein the at least one information entry is received from a source selected from the group consisting of:

the audio file, a pre-recorded vocal entry linked to the audio file, and a connected computer network.

21. The apparatus of claim 14, wherein the input reception mode is activated by depressing at least one button at least once.

22. The apparatus of claim 14, further including a display.

23. The apparatus of claim 14, wherein the input is filtered.

24. The apparatus of claim 14, wherein the discrete portions are selected from the group comprising:

musical notes, melody contours and waveforms.

25. The apparatus of claim 14, wherein the audio file is accessible from a source selected from the group consisting of:

the electronic device, any device functionally connected to the electronic device and a connected computer network.

26. The apparatus of claim 14, wherein the melody contour analysis is based on analyzing a first order melody contour (UDR), a second order melody contour (udr) and a duration contour (LSK) for an audio output for each audio file.

27. The apparatus of claim 26, wherein analyzing the first order melody contour (UDR), the second order melody contour (udr) and the duration contour (LSK) for an audio output for each audio file generates a “

closeness”

score used for audio file matching.

28. A method of determining a level of quality for vocal input using the apparatus of claim 14.