CONTENT PROCESSING DEVICE AND METHOD FOR TRANSMITTING SEGMENT OF VARIABLE SIZE, AND COMPUTER-READABLE RECORDING MEDIUM

• US 20160140224A1
• Filed: 10/27/2015
• Published: 05/19/2016
• Est. Priority Date: 11/18/2014
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: JIN, Jang-ho, SONG, Myung-suk, RYU, Young-jun
• Granted Patent: US 9,910,919 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• 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
• CPC Class Codes: G10H 2210/046 for differentiation between music and non-music signals, based on the identification of musical parameters, e.g. based on tempo detection
• CPC Class Codes: G10H 2210/061 for extraction of musical phrases, isolation of musically relevant segments, e.g. musical thumbnail generation, or for temporal structure analysis of a musical piece, e.g. determination of the movement sequence of a musical work
• CPC Class Codes: G10H 2220/011 Lyrics displays, e.g. for karaoke applications
• CPC Class Codes: G10H 2240/141 Library retrieval matching, i.e. any of the steps of matching an inputted segment or phrase with musical database contents, e.g. query by humming, singing or playing; the steps may include, e.g. musical analysis of the input, musical feature extraction, query formulation, or details of the retrieval process
• CPC Class Codes: H04N 21/4394 involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams arrangements characterised by components specially adapted for monitoring, identification or recognition of audio in broadcast systems H04H60/58
• CPC Class Codes: H04N 21/8456 by decomposing the content in the time domain, e.g. in time segments

Abstract

A content processing device is provided. The content processing device includes a receiver configured to receive a content, an audio processor configured to extract an audio signal by decoding audio data included in the content, a processor configured to determine a characteristic section in the audio signal based on a ratio of music information of the audio signal, and detect a segment corresponding to the characteristic section in the audio signal; and a communicator configured to transmit the segment to a music recognition server, and a size of the segment is determined variably within a threshold range.

Claims

1. A content processing device, comprising:

a receiver configured to receive a content;

an audio processor configured to extract an audio signal by decoding audio data included in the content;

a processor configured to determine a characteristic section in the audio signal based on a ratio of music information of the audio signal, and detect a segment corresponding to the characteristic section in the audio signal; and

a communicator configured to transmit the segment to a music recognition server,

wherein a size of the segment is variably determined within a threshold range.

2. The content processing device of claim 1, wherein the processor is configured to calculate the ratio of the music information in the audio signal, determine at least one audio section in which the ratio of the music information in the audio signal is greater than or equal to a threshold value as the characteristic section, and generate the segment by labeling the characteristic section with a start point and an end point.

3. The content processing device of claim 2, wherein the processor is configured to combine the segment with a neighboring segment when the size of the segment is determined to be less than the threshold range, and divide the segment into a plurality of pieces when the size of the segment is determined to exceed the threshold range.

4. The content processing device of claim 1, wherein a plurality of segments including the segment are detected, and the processor is configured to group a number of segments among the plurality of segments including the segment and control the communicator to transmit the grouped segments to the music recognition server in an order.

5. The content processing device of claim 4, wherein the plurality of segments including the segment are grouped in segment groups, one of the segment groups is transmitted to the music recognition server, and

the processor is configured to transmit a segment group subsequent to the one of the segment groups to the music recognition server in response to a music recognition failure signal being received from the music recognition server through the communicator, and

wherein the processor is configured, upon a music recognition completion signal being received from the music recognition server, not to transmit the segment group subsequent to the one of the segment groups.

6. The content processing device of claim 1, further comprising:

a storage configured to store the music information in response to transmission of the music information , from the music recognition server, as being recognized according to the transmitted segment; and

a display configured to display the music information.

7. The content processing device of claim 1, wherein a plurality of segments are detected, and

the processor is configured to allocate priority to the plurality of segments in high order of the ratio of the music information in the audio signal, and sequentially transmit the plurality of segments to the music recognition server according to the priority.

8. The content processing device of claim 7, wherein the processor is configured to allocate the priority to the plurality of segments in response to the plurality of segments reaching a predetermined number.

9. The content processing device of claim 1, wherein the ratio of the music information in the audio signal is calculated by the following formula:

Ratio of music in the audio signal=music score/(noise score+speech score+other scores).

20. The content processing device of claim 1, wherein a plurality of segments including the segment are detected, and

the plurality of segments are correspondingly labeled with a score based on at least a size of the music information thereof so that transmission of the plurality of segments including the segment is controlled according to scoring of the plurality of segments including the segment.

10. A method for transmitting a segment of a content processing device, the method comprising:

receiving a content;

extracting an audio signal by decoding audio data included in the content;

determining a characteristic section in the audio signal based on a ratio of music information of the audio signal, and detecting a segment corresponding to the characteristic section in the audio signal; and

transmitting the segment to a music recognition server,

wherein a size of the segment is variably determined within a threshold range.

11. The method of claim 10, wherein the generating the segment comprises calculating the ratio of the music information in the audio signal, determining at least one audio section in which the ratio of the music information in the audio signal is greater than or equal to a threshold value as the characteristic section, and generating the segment by labeling the characteristic section with a start point and an end point.

12. The method of claim 11, further comprising:

combining the segment with a neighboring segment when the size of the segment being less than the threshold range, and dividing the segment into a plurality of pieces when the size of the segment exceeding the threshold range,.

13. The method of claim 10, wherein a plurality of segments including the segment are detected, and

the transmitting of the segment to the music recognition server comprises:

grouping a number of segments among the plurality of segments including the segment and transmitting the grouped segments to the music recognition server in an order.

14. The method of claim 13, wherein the plurality of segments including the segment are grouped in segment groups, and

the transmitting the segment to the music recognition server comprises, after having transmitted one segment groups to the music recognition server, transmitting a segment subsequent to the one of the segment groups to the music recognitions server in response to a music recognition failure signal being received from the music recognition server, and

the segment group subsequent to the one of the segment groups not being transmitted upon a music recognition completion signal being received from the music recognition server.

15. The method of claim 10, further comprising:

storing the music information in response to transmission of the music information, from the music recognition server, as being recognized according to the transmitted segment; and

displaying the music information.

16. The method of claim 10, wherein a plurality of segments are detected, and the method further comprises:

allocating priority to the plurality of segments in high order of the ratio of the music information in the audio signal,

wherein the transmitting comprises sequentially transmitting the plurality of segments to the music recognition server according to the priority.

17. The method of claim 16, wherein the allocating of the priority comprises allocating the priority to the detected segments in response to the plurality of segments reaching a predetermined number.

18. The method of claim 10, wherein the ratio of the music information in the audio signal is calculated by the following formula:

Ratio of music in the audio signal=music score/(noise score+speech score+other scores).

19. A computer program which is stored in a non-transitory recording medium to cause a content processing device to execute an operation, comprising:

receiving a content;

extracting an audio signal by decoding audio data included in the content;

determining a characteristic section in the audio signal based on a ratio of music information of the audio signal, and detecting a segment according to the characteristic section in the audio signal; and

transmitting the segment to a music recognition server, and

wherein a size of the segment is variably determined within a threshold range.

21. A content processing method, comprising:

generating at least one segment of an audio signal to have a variable size within a range, the at least one segment generated being determined to have characteristic of a ratio of music information relative to a remaining content of the audio signal; and

transmitting the at least one segment of the variable size within the range so as to implement music recognition.