Volume leveler controller and controlling method

Patent metadata

Field	Value
Publication number	US-9548713-B2
Application number	US-201414777271-A
Country	US
Kind code	B2
Filing date	Mar 17, 2014
Priority date	Mar 26, 2013
Publication date	Jan 17, 2017
Grant date	Jan 17, 2017

Abstract

Volume leveler controller and controlling method are disclosed. In one embodiment, A volume leveler controller includes an audio content classifier for identifying the content type of an audio signal in real time; and an adjusting unit for adjusting a volume leveler in a continuous manner based on the content type as identified. The adjusting unit may configured to positively correlate the dynamic gain of the volume leveler with informative content types of the audio signal, and negatively correlate the dynamic gain of the volume leveler with interfering content types of the audio signal.

First claim

What is claimed is:

1. A volume leveler controlling method comprising:
identifying the content type of an audio signal in real time; and
adjusting a volume leveler in a continuous manner based on the content type as identified, by increasing or decreasing the dynamic gain of the volume leveler with, respectively, the increasing or decreasing of the confidence value of informative content types of the audio signal, and increasing or decreasing the dynamic gain of the volume leveler with, respectively, the decreasing or increasing of the confidence value of interfering content types of the audio signal;
wherein the audio signal is classified into multiple content types with corresponding confidence values, and the adjusting operation is configured to consider at least some of the multiple content types through weighting the confidence values of the multiple content types based on the importance of the multiple content types and
wherein the volume leveler controlling method is implemented at least partially in computer hardware.

2. The volume leveler controlling method according to claim 1 , wherein the content type of the audio signal comprises one of: speech, short-term music, noise and background sound.

3. The volume leveler controlling method according to claim 2 , further comprising identifying the context type of the audio signal, wherein the adjusting operation is configured to adjust the range of the dynamic gain based on the confidence value of the context type.

4. The volume leveler controlling method according to claim 2 , further comprising identifying the context type of the audio signal, wherein the adjusting operation is configured to regard the content type of the audio signal as informative or interfering based on the context type of the audio signal.

5. The volume leveler controlling method according to claim 4 , further comprising measuring the lasting time during which the operation of identifying the context type continuously outputs the same context type, wherein the adjusting operation is configured to continue to use the present context type until the length of the lasting time of a new context type reaches a sixth threshold.

6. The volume leveler controlling method according to claim 5 , wherein different sixth thresholds are set for different transition pairs from one context type to another context type.

7. The volume leveler controlling method according to claim 5 , wherein the sixth threshold is negatively correlated with the confidence value of the new context type.

8. The volume leveler controlling method according to claim 4 , wherein the context type of the audio signal comprises one of: voice over internet protocol (VoIP), movie-like media, long-term music and game.

9. The volume leveler controlling method according to claim 4 , wherein, in the audio signal of the context type VoIP, the background sound is regarded as an interfering content type; while in the audio signal of the context type non-VoIP, the background sound and/or speech and/or music is regarded as an informative content type.

10. The volume leveler controlling method according to claim 4 , wherein the content type in an audio signal of a different context type is assigned a different weight depending on the context type of the audio signal.

11. The volume leveler controlling method according to claim 4 , wherein the audio signal is classified into multiple context types with corresponding confidence values, and the adjusting operation is configured to consider at least some of the multiple context types through weighting the effects of the multiple context types based on the confidence values.

12. The volume leveler controlling method according to claim 4 , wherein,
the operation of identifying the content type is configured to identify the content type on a basis of short-term segment of the audio signal; and
the operation of identifying the context type is configured to identify the context type on a basis of short-term segment of the audio signal at least partly based on the content type as identified.

13. The volume leveler controlling method according to claim 12 , wherein the operation of identifying the content type comprises classifying a short-term segment into the content type VoIP speech or the content type non-VoIP speech; and
the operation of identifying the context type is configured to classify the short-term segment into the context type VoIP or the context type non-VoIP based on confidence values of VoIP speech and non-VoIP speech.

14. The volume leveler controlling method according to claim 13 , wherein the operation of identifying the content type further comprises:
classifying the short-term segment into the content type VoIP noise or the content type non-VoIP noise; and
the operation of identifying the context type is configured to classify the short-term segment into the context type VoIP or the context type non-VoIP based on confidence values of VoIP speech, non-VoIP speech, VoIP noise and non-VoIP noise.

15. The volume leveler controlling method according to claim 14 , wherein the operation of identifying the context type is configured to:
classify the short-term segment as the context type VoIP if the confidence value of VoIP speech is greater than a first threshold or if the confidence value of VoIP noise is greater than a third threshold;
classify the short-term segment as the context type non-VoIP if the confidence value of VoIP speech is not greater than a second threshold, wherein the second threshold not larger than the first threshold; or if the confidence value of VoIP noise is not greater than a fourth threshold, wherein the fourth threshold not larger than the third threshold; otherwise
classify the short-term segment as the context type for the last short-term segment.

16. The volume leveler controlling method according to claim 13 , wherein the operation of identifying the context type is configured to:
classify the short-term segment as the context type VoIP if the confidence value of VoIP speech is greater than a first threshold;
classify the short-term segment as the context type non-VoIP if the confidence value of VoIP speech is not greater than a second threshold, wherein the second threshold not larger than the first threshold; otherwise,
classify the short-term segment as the context type for the last short-term segment.

17. The volume leveler controlling method according to claim 16 , wherein the first and/or second threshold is different depending on the context type of the last short-term segment.

18. The volume leveler controlling method according to claim 13 , wherein the short-term segment is classified based on a machine-learning model by using, as features, the confidence values of the content types of the short-term segment and other features extracted from the short-term segment.

19. The volume leveler controlling method according to claim 12 , further comprising smoothing the confidence value of the content type at the present time based on the past confidence values of the content type.

20. The volume leveler controlling method according to claim 19 , wherein the smoothing operation is configured to determine a smoothed confidence value of the present short-term segment by calculating a weighted sum of the confidence value of the present short-term segment and a smoothed confidence value of the last short-term segment.

21. The volume leveler controlling method according to claim 20 , further comprising identifying content type of speech

Assignees

• Dolby Laboratories Licensing Corp

Inventors

• Wang Jun
• Lu Lie
• Seefeldt Alan

Classifications

• H03G3/3089 Primary

  Control of digital or coded signals · CPC title

• H03G5/165

  Equalizers; Volume or gain control in limited frequency bands · CPC title

• H03G7/007

  of digital or coded signals · CPC title

• H03G7/002 Primary

  in untuned or low-frequency amplifiers, e.g. audio amplifiers (H03G7/007, H03G7/001, H03G7/008, H03G7/02, H03G7/06 take precedence) · CPC title

• G10L25/51 Primary

  for comparison or discrimination · CPC title