SYSTEM AND METHOD FOR PERFORMING AUTOMATIC AUDIO PRODUCTION USING SEMANTIC DATA

• US 20150066481A1
• Filed: 08/28/2014
• Published: 03/05/2015
• Est. Priority Date: 08/28/2013
• Status: Active Grant

• Current Assignee: LANDR Audio, Inc.
• Original Assignee: Mixgenius Inc.
• Inventors: Terrell, Michael John, Mansbridge, Stuart, Reiss, Joshua D., De Man, Brecht
• Granted Patent: US 9,304,988 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G10H 1/0091 Means for obtaining special acoustic effects combined with modulation G10H1/043
• CPC Class Codes: G10H 1/46 Volume control
• CPC Class Codes: G10H 2240/091 Info, i.e. juxtaposition of unrelated auxiliary information or commercial messages with or between music files
• 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: H04H 60/04 Studio equipment; Interconnection of studios

Abstract

There is described a computer implemented method for performing automatic audio production, comprising: receiving an audio signal to be processed; receiving semantic information; determining at least one semantic-based rule using the received semantic information, the semantic-based rule comprising production data that defines how the audio signal to be processed should be produced; processing the audio signal to be processed using the production data, thereby obtaining a produced audio signal; outputting the produced audio signal.

Claims

1. A computer implemented method for performing automatic audio production, comprising:

receiving an audio signal to be processed;

receiving semantic information;

determining at least one semantic-based rule using the received semantic information, the semantic-based rule comprising production data that defines how the audio signal to be processed should be produced;

processing the audio signal to be processed using the production data, thereby obtaining a produced audio signal;

outputting the produced audio signal.

2. The method of claim 1, wherein the semantic information relates to the audio signal to be processed.

3. The method of claim 2, wherein the semantic information is received from a user interface.

4. The method of claim 2, further comprising determining the semantic information from the received audio signal.

5. The method of claim 1, wherein the semantic information relates to a reference audio signal, the method further comprising:

receiving the reference audio signal; and

extracting the semantic information from the reference audio signal.

6. The method of claim 1, wherein the semantic information comprises at least one of chromosomal features, classification features, and production features.

7. The method of claim 6, wherein the production data comprises at least one of given audio processing actions to be performed and respective static characteristics for the given audio processing actions, a configuration for the audio processing actions, and target production features for the produced audio signal.

8. The method of claim 7, wherein said determining the semantic-based rule comprising production data comprises:

accessing a database containing a plurality of reference records each comprising respective reference classification features, respective reference chromosomal features, a respective reference configuration for reference processing actions, respective reference static characteristics for the reference processing actions, and respective reference production features;

identifying at least one reference record that match the at least one of chromosomal features, classification features, and production features contained in the semantic information; and

assigning a value for the at least one of the given audio processing actions to be performed and the respective static characteristics for the given audio processing actions, the configuration for the audio processing actions, and the target production features for the produced audio signal using the at least one identified reference record.

9. The method of claim 8, further comprising determining dynamic characteristics for the given processing actions using the value assigned to the target production features.

10. The method of claim 9, said processing the audio signal comprises performing the given audio processing actions on the audio signal according to the configuration and using the static and dynamic characteristics.

11. The method of claim 10, further comprising determining a value of the production features between the given audio processing actions and modifying the dynamic characteristics accordingly.

12. The method of claim 1, wherein said receiving the audio signal to be processed and outputting the produced audio signal are performed in substantially real-time so that the audio signal to be processed and the produced audio signal be synchronized.

13. The method of claim 1, wherein the production data is determined for only one region of the audio signal to be processed.

14. The method of claim 1, further comprising receiving user production preferences, said processing the audio signal being performed using the production data and the user production preferences.

15. The method of claim 14, further comprising evaluation of the produced audio signal from a user and determining the user production preferences using the received evaluation.

16. A computer readable medium having recorded thereon statements and instructions for execution by a processing unit to perform the steps of the method of claim 1.

17. An automatic audio production system comprising:

a semantic analysis module for receiving semantic information and determining at least one semantic-based rule using the received semantic information, the semantic-based rule comprising production data that defines how an audio signal to be processed should be produced; and

an audio processing module for receiving the audio signal to be processed, processing the audio signal to be processed using the production data, in order to obtain a produced audio signal, and outputting the produced audio signal.

18. The automatic audio production system of claim 17, wherein the semantic information relates to the audio signal to be processed.

19. The automatic audio production system of claim 18, wherein the semantic analysis module is adapted to receive the semantic information from a user interface.

20. The automatic audio production system of claim 18, wherein the semantic analysis module is further adapted to receive the audio signal to be processed and determine the semantic information from the audio signal to be processed.

21. The automatic audio production system of claim 17, wherein the semantic information relates to a reference audio signal, the semantic analysis module being further adapted to:

receive the reference audio signal; and

extract the semantic information from the reference audio signal.

22. The automatic audio production system of claim 17, wherein the semantic information comprises at least one of chromosomal features, classification features, and production features.

23. The automatic audio production system of claim 22, wherein the production data comprises at least one of given audio processing actions to be performed and respective static control parameters for the given audio processing actions, a configuration for the audio processing actions, and target production features for the produced audio signal.

24. The automatic audio production system of claim 23, further comprising a production database containing a plurality of reference records each comprising respective reference classification features, respective reference chromosomal features, a respective reference configuration for reference processing actions, respective reference static control parameters for the reference processing actions, and respective reference production features, the semantic analysis module being adapted to:

identify at least one reference record that match the at least one of chromosomal features, classification features, and production features contained in the semantic information; and

assign a value for the at least one of the given audio processing actions to be performed and the respective static control parameters for the given audio processing actions, the configuration for the audio processing actions, and the target production features for the produced audio signal using the at least one identified reference record.

25. The automatic audio production system of claim 24, wherein the audio processing module is adapted to determine dynamic control parameters for the given processing actions using the value assigned to the target production features.

26. The automatic audio production system of claim 25, wherein the audio processing module comprises a plurality of audio processors and is adapted to organize the plurality of audio processors according to the configuration and control the plurality of audio processors according to the static and dynamic control parameters.

27. The automatic audio production system of claim 26, wherein the audio processing module is further adapted to determine a value of the production features between the audio processors and modify the dynamic parameters accordingly.

28. The automatic audio production system of claim 17, wherein an input of the audio signal to be processed and an output of the produced audio signal are performed in substantially real-time so that the audio signal to be processed and the produced audio signal be synchronized.

29. The automatic audio production system of claim 17, wherein the semantic analysis module is adapted to determine the production data for only one region of the audio signal to be processed.

30. The automatic audio production system of claim 17, the semantic analysis module is further adapted to receive user production preferences and determine the production data using the user production preferences.

31. The automatic audio production system of claim 30, further a production evaluation module for receiving an evaluation of the produced audio signal from a user and determine the user production preferences using the received evaluation.