Apparatus and method for providing various audio environments in multimedia content playback system

Patent metadata

Field	Value
Publication number	US-10782928-B2
Application number	US-201816212637-A
Country	US
Kind code	B2
Filing date	Dec 6, 2018
Priority date	Dec 11, 2017
Publication date	Sep 22, 2020
Grant date	Sep 22, 2020

Abstract

An apparatus and method for providing various audio environments in a multimedia content playback system are disclosed. The content processing terminal of the multimedia content playback system includes an audio signal processor for processing the audio source of multimedia content to produce a voice source and a background source, a controller for controlling the audio signal processor to adjust at least one of the voice source and the background source in accordance with a volume control signal, a GUI processor for acquiring a graphical user interface (GUI) component corresponding to the volume control signal, and a display processor for processing the GUI component and providing the processed GUI component to a display device.

First claim

What is claimed is:

1. A content processing terminal of a multimedia content playback system, comprising:
an audio signal processor for processing a voice signal separated from an audio source of multimedia content to produce a voice source and for processing a background signal separated from the audio source to produce a background source;
a controller for controlling the audio signal processor to adjust at least one of the voice source and the background source in accordance with a volume control signal;
a GUI processor for acquiring a graphical user interface (GUI) component corresponding to the volume control signal; and
a display processor for processing the GUI component and providing the processed GUI component to a display device,
wherein the audio signal processor sequentially separates the audio source through an audio separation algorithm based on a support vector machine (SVM) and an audio separation algorithm based on Probabilistic Latent Component Analysis (PLCA).

2. The content processing terminal according to claim 1 , wherein the audio signal processor separates an audio source of the multimedia content into a first voice signal and a first background signal using a first audio separation procedure and separates the audio source into a second voice signal and a second background signal using a second audio separation procedure.

3. The content processing terminal according to claim 2 , wherein the audio signal processor comprises a first audio signal separator for separating the audio source into the first voice signal and the first background signal;
a second audio signal separator for separating the audio source into the second voice signal and the second background signal;
a voice enhancer for generating enhanced voice sources based on signal features of each of the first and second voice signals; and
a background enhancer for generating enhanced background sources based on signal features of each of the first and second background signals.

4. The content processing terminal according to claim 3 , wherein the voice enhancer compares a feature value of the first voice signal and a feature value of the second voice signal by unit time or unit frequency, identifies differences between the feature values by the unit time or the unit frequency, and determines feature values of the enhanced voice sources in consideration of characteristics of the voice signals.

5. The content processing terminal according to claim 3 , wherein the background enhancer compares a feature value of the first background signal and a feature value of the second background signal by unit time or unit frequency, identifies differences between the feature values by the unit time or the unit frequency, and determines feature values of the enhanced voice sources in consideration of characteristics of the background signals.

6. The content processing terminal according to claim 3 , wherein the first audio signal separator comprises a first preprocessor for preprocessing the audio source and classifying the audio source into a first voice segment and a first background segment using a first audio separation algorithm; and
a first separator for outputting the first voice signal and the first background signal by applying a probabilistic latent component analysis (PLCA)-based audio separation algorithm to the first voice segment and the first background segment, and
the second audio signal separator comprises a second preprocessor for preprocessing the audio source and classifying the audio source into a second voice segment and a second background segment using a second audio separation algorithm different from the first audio separation algorithm; and
a second separator for outputting the second voice signal and the second background signal by applying a probabilistic latent component analysis (PLCA)-based audio separation algorithm to the second voice segment and the second background segment.

7. The content processing terminal according to claim 6 , wherein the first audio separation algorithm is a support vector machine (SVM)-based audio separation algorithm, and the second audio separation algorithm is a Gaussian mixture model (GMM)-based audio separation algorithm.

8. The content processing terminal according to claim 2 , further comprising:
a first production buffer for buffering the voice source; and
a second production buffer for buffering the background source,
wherein the controller transmits a control signal for controlling at least one of buffering time and synchronization of the voice source and the background source to the first and second production buffers.

9. The content processing terminal according to claim 2 , wherein the audio signal processor comprises a first preprocessor for classifying the audio source into a first voice segment and a first background segment using a first audio separation algorithm;
a second preprocessor for classifying the audio source into a second voice segment and a second background segment using a second audio separation algorithm different from the first audio separation algorithm;
a voice enhancer for generating enhanced voice segments based on signal features of each of the first and second voice segments;
a background enhancer for generating enhanced background segments based on signal features of each of the first and second background signals; and
a separator for outputting an enhanced voice source and an enhanced background source by applying a probabilistic latent component analysis-based audio separation algorithm to the enhanced voice segment and the enhanced background segment.

10. The content processing terminal according to claim 2 , wherein the audio signal processor comprises a selector for selecting a voice enhancement procedure or a background enhancement procedure according to a type of the multimedia content or user setting;
a voice enhancement audio source part activated in the voice enhancement procedure; and
a background enhancement audio source part activated in the background enhancement procedure,
wherein the voice enhancement audio source part outputs a sound in which the voice source is enhanced among the voice source and the background source; and
the background enhancement audio source part outputs a sound in which the background source is enhanced among the voice source and the background source.

11. The content processing terminal according to claim 1 , wherein the volume control signal comprises at least one of a signal for adjusting a volume level of the voice source independently of the background source, a signal for adjusting a volume level of the background source independently of the voice source, and a signal for adjusting a volume level of a combination of the voice source and the background source.

12. The content processing terminal according to claim 1 , wherein the volume control signal is received from a remote controller, wherein the remote controller comprises volume adjustment buttons capable of independent volume control of voice and background,
wherein, when the volume control signal is input through the volume adjustment buttons, the remote controller transmits the volume control signal to the content processing terminal; and
when input signals of number keys are received from the remote controller within a predetermined time after receiving the volume control signal, the controller controls the audio signal processor to adjust at least one of the voice source and the background source at a volume level corresponding to the input signals of number keys.

13. The content processing terminal according to claim 1 , wherein the controller stores the volume

Assignees

• Humax Co Ltd

Inventors

• An Byoung Man

Classifications

• G10L21/0316 Primary

  by changing the amplitude · CPC title

• G06F3/165 Primary

  Management of the audio stream, e.g. setting of volume, audio stream path · CPC title

• H04N21/42215

  by measuring the time interval during which a key is pressed, e.g. for inputting sequences of digits when selecting a television channel · CPC title

• G10L21/0272

  Voice signal separating · CPC title

• H04N21/4394

  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 title