CN114003193B - Electronic device and sound mode adjusting method - Google Patents
Electronic device and sound mode adjusting method Download PDFInfo
- Publication number
- CN114003193B CN114003193B CN202010737614.3A CN202010737614A CN114003193B CN 114003193 B CN114003193 B CN 114003193B CN 202010737614 A CN202010737614 A CN 202010737614A CN 114003193 B CN114003193 B CN 114003193B
- Authority
- CN
- China
- Prior art keywords
- type
- application
- application program
- voice
- sound
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
- G06F3/162—Interface to dedicated audio devices, e.g. audio drivers, interface to CODECs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
- G06F3/165—Management of the audio stream, e.g. setting of volume, audio stream path
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
A sound mode adjusting method comprises the following steps: detecting whether an application program provides a sound stream; when the application program provides the sound stream, confirming the application program type of the application program according to the application program, and providing the application program type; the sound pattern is adjusted according to the type of application.
Description
Technical Field
The present invention relates to a mode adjustment technique, and more particularly, to an electronic device and a method for adjusting a sound mode.
Background
In recent years, with the progress of technology and networks, electronic devices (e.g., electronic competition computers) have become indispensable equipment for most users. In order to provide better sound effects, most electronic devices provide different sound modes for users to use.
However, the different modes still require the user to manually select and switch, which reduces the user experience. Therefore, how to automatically adjust the appropriate sound pattern and enhance the user's experience is currently an important topic.
Disclosure of Invention
The invention provides an electronic device and a sound mode adjusting method, which are used for automatically adjusting a proper sound mode so as to improve the experience of a user.
The invention provides a sound mode adjusting method which comprises the following steps. Detecting whether an application program provides a sound stream. When the application program provides the sound stream, the application program type of the application program is confirmed according to the application program, and the application program type is provided. The sound pattern is adjusted according to the type of application.
The invention provides an electronic device, which comprises a sound detection module, an application program confirmation module and a sound mode adjustment module. The voice detection module detects whether an application program provides a voice stream. The application program confirmation module confirms the application program type of the application program according to the application program when the application program provides the sound stream and provides the application program type. The sound mode adjusting module adjusts the sound mode according to the type of the application program.
According to the electronic device and the sound mode adjusting method disclosed by the invention, when the sound streaming provided by the application program is detected, the application program type of the application program is confirmed according to the application program, and the sound mode is adjusted according to the application program type. Therefore, the proper sound mode can be effectively and automatically adjusted, so that the experience of a user is improved.
Drawings
FIG. 1 is a schematic diagram of an electronic device according to an embodiment of the invention.
FIG. 2 is a flow chart of a method for adjusting a sound pattern according to an embodiment of the invention.
Fig. 3 is a detailed flowchart of step S202 of fig. 2.
Fig. 4 is a detailed flowchart of step S306 of fig. 3.
Fig. 5 is a detailed flowchart of step S308 of fig. 3.
Wherein:
100: an electronic device;
110: a sound detection module;
120: an application program confirmation module;
130: a sound mode adjustment module;
140: a database;
150: an application detection module;
160: an application program discriminating module;
170: a multimedia player discriminating module;
180: a game category discriminating module;
s202 to S206, S302 to S310, S402 to S412, S502 to S508: and (3) step (c).
Detailed Description
It should be understood that the terms "comprises" and "comprising," when used in this specification, are taken to specify the presence of stated features, integers, method steps, operations, elements, and/or components, but do not preclude the addition of further features, integers, method steps, operations, elements, components, or groups thereof.
The terms "first," "second," and the like are used for modifying elements and are not intended to denote a prior order or relationship, but rather are used to distinguish one element from another by the same name.
In the various embodiments listed below, the same or similar elements or components will be denoted by the same reference numerals.
FIG. 1 is a schematic diagram of an electronic device according to an embodiment of the invention. In this embodiment, the user can start an application program through the electronic device 100 to execute a game, a movie, music or voice playing, etc. Referring to fig. 1, the electronic device 100 includes a voice detection module 110, an application confirmation module 120, a voice pattern adjustment module 130, and a database 140.
The voice detection module 110 detects whether an application provides a voice stream. That is, when the user starts the application program through the electronic device 100, the application program provides a corresponding sound. At this time, the voice detection module 110 can detect that an application provides a voice stream.
The application confirmation module 120 confirms the application type of the application according to the application when the application provides the audio stream, and provides the application type. That is, when the voice detection module 110 detects that the application provides the voice stream, it indicates that a new voice stream is generated, and the voice detection module 110 may generate a detection signal to the application confirmation module 120, for example, so that the application confirmation module 120 may know that the electronic device 100 executes a new application. Thereafter, the application validation module 120 may analyze the current application to validate the application type of the current application and provide the identified application type. In the present embodiment, the application types include, for example, a game type and a multimedia player type. Further, game types may include General games (gambling-General), first-person shooter (gambling-FPS), sports-like games (gambling-Sports). The multimedia player types may include movies, music, and audio.
The sound mode adjusting module 130 adjusts the sound mode according to the application type. That is, the sound pattern adjustment module 130 may adjust the sound pattern corresponding to the game type or the multimedia player type according to the game type or the multimedia player type. In this way, the electronic device 100 can adjust a suitable sound mode, for example, a sound mode corresponding to a game type or a multimedia player type, according to the current application type, so that a user can hear better sound effects during the execution of the application, thereby increasing the user experience.
In this embodiment, the application confirmation module 120 may include an application detection module 150, an application determination module 160, a multimedia player determination module 170, and a game category determination module 180.
The application detection module 150 detects whether the application type of the application is a preset application type according to the application, and when the application type is the preset application type, the application detection module 150 can provide the preset application type to the sound mode adjustment module 130, so that the sound mode module adjusts the corresponding sound mode according to the preset application type.
In this embodiment, the application detection module 150 can detect the window being operated by the user according to the application, and obtain the title (title) of the operating window in the electronic device 100 by the first extraction function, and obtain the program name (process name) of the operating window by the second extraction function. In addition, the database 140 may store a preset title and a preset program corresponding to the preset application type. Then, the application detection module 150 can compare the obtained title and the obtained program name with the preset title and the preset program name corresponding to the preset application type in the database 140 to determine whether the application started by the electronic device 100 is the same as the preset application type stored in the database 140, that is, to determine whether the application type of the application is the preset application type.
In one embodiment, the preset titles and preset program names stored in the database 140 may be previously obtained and stored by the application detection module 150 through the first extraction function and the second extraction function, but the embodiment of the invention is not limited thereto. In another embodiment, the common preset title and preset program name may also be pre-stored in the database 140 by the manufacturer.
In an embodiment, the first extraction function and the second extraction function may be functions in a dynamic link library (Dynamic Link Library, DLL) supported by an operating system of the electronic device 100. For example, when the operating system is a Microsoft Windows operating system, the first extraction function may include a GetForeground Window () function, a GetWindowTextLength () function, a GetWindowText () function, a combination thereof, or any other suitable function. The second extraction function may include a GetWindowThreadProcessId () function, a getmodulebasetname () function, a combination thereof, or any other suitable function. In addition, the database 140 may store preset titles and preset program names in a tabular manner. Furthermore, the database 140 may be a local database provided in the electronic device 100, but the embodiment of the invention is not limited thereto. In one embodiment, the database 140 may be a cloud database, and is remotely connected to the application verification module 120.
When detecting that the application type is not the preset application type, the application discriminating module 160 discriminates that the application type of the application belongs to the game type or the multimedia player type according to the speech decoding engine utilization rate, the three-dimensional engine utilization rate and the multimedia application interface call number. That is, when the application detection module 150 detects that the application type is not the preset application type, for example, a start message is generated to the application determination module 160, so that the application determination module 160 can determine the application to confirm that the application type of the application belongs to the game type or the multimedia player type.
In this embodiment, the graphics processor (graphics processing unit, GPU) uses the speech decoding engine (video decode engine) to compute the core, and in particular, uses hardware to decode the video stream while the application is playing the video stream. Therefore, the application discriminating module 160 can discriminate the application type of the application according to the speech decoding engine usage rate.
In addition, when an application is rendering pictures (whether movies or games), the graphics processor may use a three-dimensional engine (3D engine) computing core, particularly to play movies or games using soft decoding. Therefore, the application discriminating module 160 may discriminate the application type of the application according to the three-dimensional engine usage rate.
In addition, when the application is playing a movie, the graphics processor calls the multimedia application interface (multimedia api) of the movie decoder to decode. On the contrary, when the application program is a game, the graphic processor only uses the three-dimensional engine operation core to conduct picture rendering and does not call the multimedia application program interface of the film decoder. Therefore, the application discriminating module 160 can discriminate the application type of the application according to the number of multimedia application interface calls.
For example, when the application detection module 150 detects that the application type is not the preset application type, the application determination module 160 determines whether the speech decoding engine usage rate Sdc of the application is greater than or equal to the first threshold value Sdc-th. When determining that the speech decoding engine usage rate Sdc of the application is greater than or equal to the first threshold value Sdc-th (i.e., sdc+.sdc-th), the application determination module 160 determines that the application type of the application belongs to the first type of the multimedia player type, such as a movie.
When determining that the speech decoding engine usage rate Sdc of the application is not greater than or equal to the first threshold value Sdc-th (i.e., sdc < Sdc-th), the application determination module 160 determines whether the three-dimensional engine usage rate S3d of the application is less than the second threshold value S3d-thm. When determining that the three-dimensional engine usage S3d of the application is less than the second threshold S3d-thm (i.e. S3d < S3 d-thm), the application determining module 160 determines that the application type of the application belongs to a second type of multimedia player type, such as music or voice.
When the three-dimensional engine usage S3d of the application is determined not to be smaller than the second threshold S3d-thm (i.e. S3d +.s3d-thm), the application determining module 160 determines whether the number of multimedia application interface calls Cma of the application is greater than or equal to the third threshold Cma-th. When determining that the number of multimedia application interface calls Cma of the application is greater than or equal to the third threshold value Cma-th (i.e., cma + Cma-th), the application determining module 160 determines that the application type of the application belongs to the first type of multimedia player type, such as movie. When the number of multimedia application interface calls Cma of the application is determined to be not greater than or equal to the third threshold value Cma-th (i.e. Cma < Cma-th), the application determining module 160 determines that the application type of the application belongs to the game type.
The multimedia player discriminating module 170 obtains a sound stream when the application type belongs to the multimedia player type, extracts a plurality of frames from the sound stream, and discriminates the voice type corresponding to the application type according to the first confidence score and the second confidence score corresponding to each frame. That is, when the application detection module 150 detects that the application type of the application is the multimedia player type or the application discriminating module 160 determines that the application type of the application belongs to the multimedia player type, a start signal may be provided to the multimedia player discriminating module 170, so that the multimedia player discriminating module 170 may discriminate the voice class corresponding to the application type.
In the present embodiment, after the multimedia player determining module 170 obtains the audio stream, the multimedia player determining module 170 may extract a plurality of frames from the audio stream. Then, the multimedia player discriminating module 170 may calculate N first confidence scores and N second confidence scores corresponding to the previous N frames of the frame according to the first algorithm, where N is a positive integer greater than 1. In this embodiment, the first algorithm is, for example, a time-frequency domain (time-frequency domain) analysis method or a frequency domain (frequency domain) analysis method. In addition, the first confidence score may be a music category confidence score Cm and the second confidence score may be a voice category confidence score Cv.
For example, after the multimedia player determining module 170 obtains a plurality of frames, the multimedia player determining module 170 extracts features in the previous N frames using a first algorithm (e.g., a time-frequency domain analysis method), and classifies the features in the N frames using a hidden Markov model (hidden Markov model) to calculate N first confidence scores (i.e., a music category confidence score) and N second confidence scores (i.e., a voice category confidence score) corresponding to the N frames.
The multimedia player discrimination module 170 may then calculate an average of the N first confidence scores and an average of the N second confidence scores. In the present embodiment, the average value of the N first confidence scores may be calculated by the following formula (1).
Wherein Cm tuberculosis is the average value of the N first confidence scores, and Cmn is the N first confidence scores.
In addition, the average value of the N second confidence scores may be calculated by the following formula (2).
Wherein Cv tuberculosis is an average value of the N second confidence scores, and Cvn is the N second confidence scores.
The multimedia player discriminating module 170 may then discriminate the initial voice category corresponding to the application type according to the average of the N first confidence scores and the average of the N second confidence scores. For example, when the average value of the N first confidence scores is greater than the average value of the N second confidence scores (i.e. Cm consumption > Cv consumption), the multimedia player discriminating module 170 may discriminate that the initial voice category corresponding to the application type is music. When the average value of the N first confidence scores is smaller than the average value of the N second confidence scores (i.e. Cm consumption < Cv consumption), the multimedia player discriminating module 170 may discriminate that the initial voice class corresponding to the application type is voice.
Then, the multimedia player discriminating module 170 calculates the first confidence score and the second confidence score corresponding to the remaining sound box by using the second algorithm. In this embodiment, the second algorithm is, for example, a time domain (time domain) analysis method. For example, the multimedia player determining module 170 extracts the features in the remaining frames by using a second algorithm, and classifies the features in the remaining frames by using a neural network (neural network) to calculate a first confidence score (i.e., a music category confidence score) and a second confidence score (i.e., a voice category confidence score) corresponding to the remaining frames.
Then, the multimedia player determining module 170 analyzes the first confidence score and the second confidence score corresponding to the remaining voice frame, that is, determines whether the difference (|cm-cv|) between the first confidence score and the second confidence score is greater than a threshold Cth, so as to determine whether the voice category is changed. When the multimedia player discriminating module 170 determines that the difference (|cm-cv|) between the first confidence scores and the second confidence scores corresponding to the remaining sound frames is greater than the threshold Cth (i.e., |cm-cv| > Cth) and the estimated speech class is different from the initial speech class, the multimedia player discriminating module 170 calculates the first confidence score and the second confidence score corresponding to the remaining sound frames by using the first algorithm to discriminate the speech class corresponding to the application type.
The game type discriminating module 180 recognizes an image corresponding to an application program when the application program type belongs to the game type, so as to discriminate a game type corresponding to the application program type. That is, when the application discriminating module 160 determines that the application type of the application belongs to the game type, an activation signal may be generated to the game type discriminating module 180, so that the game type corresponding to the application type is discriminated. In this embodiment, the game category determination module 180 may perform screenshot from an image displayed by an application program, and determine an object body in the screenshot image by using an artificial intelligence object detection algorithm to determine a game category of the application program type, such as a general game, a first person shooter game, or a sports game.
In this embodiment, the sound mode adjusting module 130 can adjust the sound mode according to the preset application type provided by the application detecting module 150, and can adjust the sound mode according to the first type of the application type provided by the application discriminating module 160, the voice type corresponding to the application type provided by the multimedia player discriminating module 170, or the game type corresponding to the application type provided by the game type discriminating module 180, such as a movie, music, voice, general game, first person shooting game, and sports game. Therefore, the embodiment of the invention can effectively and automatically adjust the proper sound mode so as to increase the experience of a user.
In addition, in the present embodiment, the computation amount and accuracy of the first algorithm are higher than those of the second algorithm. The multimedia player discriminating module 170 of the present embodiment calculates the previous N frames by using the first algorithm (with a large amount of computation), calculates the remaining frames by using the second algorithm (with a small amount of computation), and calculates the remaining frames by using the first algorithm when the confidence score of the remaining frames is too large and the estimated speech class is different from the initial speech class. In this way, the embodiment can give consideration to the real-time performance of the operation performance and the accuracy of the recognition result, and ensure the stability of the voice mode.
By the above description of the embodiments, the embodiments of the present invention provide a sound mode adjusting method. FIG. 2 is a flow chart of a method for adjusting a sound pattern according to an embodiment of the invention. In step S202, it is detected whether an application provides a sound stream. When the application provides the audio stream, step S204 is performed to confirm the application type of the application according to the application and provide the application type. In step S206, the sound mode is adjusted according to the application type.
Fig. 3 is a detailed flowchart of step S202 of fig. 2. In step S302, according to the application program, it is detected whether the application program type of the application program is a preset application program type. When the application type is the preset application type, the step goes to step S304 to provide the preset application type. When the application type is detected not to be the preset application type, step S306 is performed to determine that the application type of the application belongs to the game type or the multimedia player type according to the speech decoding engine utilization, the three-dimensional engine utilization, and the multimedia application interface call number. In step S308, when the application type belongs to the multimedia player type, a sound stream is obtained, a plurality of frames are extracted from the sound stream, and the voice type corresponding to the application type is determined according to the first confidence score and the second confidence score corresponding to each frame. In step S310, when the application type belongs to the game type, the image corresponding to the application is identified to determine the game type corresponding to the application type.
Fig. 4 is a detailed flowchart of step S306 of fig. 3. In step S402, it is determined whether the speech decoding engine usage rate of the application program is greater than or equal to a first threshold value. When the speech decoding engine usage rate of the application is determined to be greater than or equal to the first threshold, step S404 is performed to determine that the application type of the application belongs to the first type of the multimedia player type.
When it is determined that the speech decoding engine usage rate of the application is not greater than or equal to the first threshold value, step S406 is performed to determine whether the three-dimensional engine usage rate of the application is less than the second threshold value. When the three-dimensional engine usage rate of the application is determined to be smaller than the second threshold value, step S408 is performed to determine that the application type of the application belongs to the second type of the multimedia player type. When it is determined that the three-dimensional engine usage rate of the application is not less than the second threshold, step S410 is performed to determine whether the number of calls in the multimedia application interface of the application is greater than or equal to the third threshold.
When the number of multimedia application interface calls of the application is determined to be greater than or equal to the third threshold, step S404 is performed to determine that the application type of the application belongs to the first type of the multimedia player type. When the number of multimedia application interface calls of the application is determined to be not greater than or equal to the third threshold, step S412 is performed to determine that the application type of the application belongs to the game type. In this embodiment, the first type comprises movies and the second type comprises music or speech.
Fig. 5 is a detailed flowchart of step S308 of fig. 3. In step S502, a frame is extracted from the audio stream, and N first confidence scores and N second confidence scores corresponding to N previous frames of the frame are calculated according to a first algorithm, where N is a positive integer greater than 1. In step S504, an initial speech category corresponding to the application type is determined according to the average value of the N first confidence scores and the average value of the N second confidence scores.
In step S506, the second algorithm is used to calculate the first confidence score and the second confidence score corresponding to the remaining frames. In step S508, when it is determined that the difference between the first confidence score and the second confidence score corresponding to the remaining frame is greater than the threshold value and the estimated speech class is different from the initial speech class, the first confidence score and the second confidence score corresponding to the remaining frame are calculated by using the first algorithm to determine the speech class corresponding to the application type. In this embodiment, the first confidence score is a music category confidence score and the second confidence score is a voice category confidence score. The first algorithm is a time-frequency domain analysis or a frequency domain analysis, and the second algorithm is a time domain algorithm.
In summary, the electronic device and the sound mode adjusting method according to the present invention determine the application type of the application according to the application when detecting that the application provides the sound stream, and adjust the sound mode according to the application type. In addition, the embodiment can further judge that the application type of the application belongs to a game type or a multimedia player type according to the utilization rate of the voice decoding engine, the utilization rate of the three-dimensional engine and the calling number of the multimedia application interface, calculate confidence scores of a plurality of voice frames of the sound stream, judge the voice type corresponding to the application type, identify the image corresponding to the application, and judge the game type corresponding to the application type. Therefore, the proper sound mode can be effectively and automatically adjusted, so that the experience of a user is improved.
Although the present invention has been described with reference to the above embodiments, it should be understood that the present invention is not limited to the above embodiments, and that various changes and modifications can be made by one skilled in the art without departing from the spirit and scope of the invention.
Claims (7)
1. A sound pattern adjustment method, comprising:
detecting whether an application program provides a sound stream;
when the application program provides the sound stream, confirming an application program type of the application program according to the application program, and providing the application program type; wherein said validating the application type of the application and providing the application type according to the application comprises:
detecting whether the application type of the application is a preset application type according to the application;
providing the preset application type when the application type is the preset application type;
when detecting that the application type is not the preset application type, judging that the application type of the application belongs to a game type or a multimedia player type according to the utilization rate of a voice decoding engine, the utilization rate of a three-dimensional engine and the calling number of a multimedia application interface;
when the application program type belongs to the multimedia player type, the sound stream is obtained, a plurality of sound frames are extracted from the sound stream, and the voice type corresponding to the application program type is judged according to a first confidence score and a second confidence score corresponding to each sound frame; the method for determining the voice class of the application program type according to the first confidence score and the second confidence score of the voice stream comprises the steps of:
extracting the voice frames from the sound stream, and calculating N first confidence scores and N second confidence scores corresponding to the previous N voice frames of the voice frames by a first algorithm, wherein N is a positive integer greater than 1, and the first algorithm is a time domain-frequency domain analysis method or a frequency domain analysis method;
judging an initial voice category corresponding to the application program type according to the average value of the N first confidence scores and the average value of the N second confidence scores;
calculating the first confidence scores and the second confidence scores corresponding to the rest voice frames by a second algorithm, wherein the second algorithm is a time domain algorithm;
when the difference value between the first confidence scores and the second confidence scores corresponding to the remaining frames is larger than a threshold value and an estimated voice class is different from the initial voice class, calculating the first confidence scores and the second confidence scores corresponding to the remaining frames by using the first algorithm so as to judge the voice class corresponding to the application program type;
when the application program type belongs to the game type, identifying an image corresponding to the application program to judge a game type corresponding to the application program type;
a sound mode is adjusted according to the application type.
2. The method of claim 1, wherein the step of determining whether the application type of the application belongs to the game type or the multimedia player type according to the speech decoding engine usage rate, the three-dimensional engine usage rate and the multimedia application interface call number comprises:
judging whether the utilization rate of the voice decoding engine of the application program is greater than or equal to a first threshold value;
when judging that the utilization rate of the voice decoding engine of the application program is greater than or equal to the first threshold value, judging that the application program type of the application program belongs to a first type of the multimedia player type;
when judging that the utilization rate of the voice decoding engine of the application program is not greater than or equal to the first threshold value, judging whether the utilization rate of the three-dimensional engine of the application program is smaller than a second threshold value;
when the three-dimensional engine utilization rate of the application program is smaller than the second threshold value, judging that the application program type of the application program belongs to a second type of the multimedia player type;
when the three-dimensional engine utilization rate of the application program is not less than the second threshold value, judging whether the calling number of the multimedia application program interface of the application program is greater than or equal to a third threshold value;
when the calling number of the multimedia application program interface of the application program is larger than or equal to the third threshold value, judging that the application program type of the application program belongs to the first type of the multimedia player type; and
and when the calling number of the multimedia application program interface of the application program is not larger than or equal to the third threshold value, judging that the application program type of the application program belongs to the game type.
3. The sound pattern adjustment method of claim 2, wherein the first type comprises a movie and the second type comprises music or voice.
4. An electronic device, comprising:
a sound detection module for detecting whether an application program provides a sound stream;
an application program confirming module for confirming an application program type of the application program according to the application program when the application program provides the sound stream and providing the application program type; wherein the application program confirmation module comprises:
an application detection module for detecting whether the application type of the application is a preset application type according to the application, and providing the preset application type when the application type is the preset application type;
an application program judging module for judging the application program type of the application program to be a game type or a multimedia player type according to the utilization rate of a voice decoding engine, the utilization rate of a three-dimensional engine and the calling number of a multimedia application program interface when detecting that the application program type is not the preset application program type;
a multimedia player judging module, when the application program type belongs to the multimedia player type, obtaining the sound series flow, extracting a plurality of sound frames from the sound series flow, and judging the voice type corresponding to the application program type according to a first confidence score and a second confidence score corresponding to each sound frame; the multimedia player judging module extracts the voice frames from the sound stream, calculates N first confidence scores and N second confidence scores corresponding to N previous voice frames of the voice frames by a first algorithm, judges an initial voice category corresponding to the application program type according to the average value of the N first confidence scores and the average value of the N second confidence scores, calculates the first confidence scores and the second confidence scores corresponding to the remaining voice frames by a second algorithm, and judges that the difference value of the first confidence scores and the second confidence scores corresponding to the remaining voice frames is larger than a threshold value and the first estimated voice category and the initial voice category are different, the multimedia player judging module calculates the first confidence scores and the second confidence scores corresponding to the remaining voice frames by the first algorithm so as to judge the voice category corresponding to the application program type, wherein N is an integer greater than 1, the first confidence score and the second confidence score are the first algorithm, the time domain score is the first algorithm is the second algorithm, and the time domain score is the first algorithm is the second algorithm;
a game category discriminating module for discriminating an image corresponding to the application program when the application program type belongs to the game type, so as to discriminate a game category corresponding to the application program type;
and the sound mode adjusting module adjusts a sound mode according to the type of the application program.
5. The electronic device of claim 4, wherein when detecting that the application type is not the predetermined application type, the application discriminating module discriminates whether the speech decoding engine usage of the application is greater than or equal to a first threshold, when discriminating that the speech decoding engine usage of the application is greater than or equal to a second threshold, the application discriminating module discriminates that the application type of the application belongs to a first type of the multimedia player type, when discriminating that the speech decoding engine usage of the application is not greater than or equal to the first threshold, the application discriminating module discriminates whether the three-dimensional engine usage of the application is less than or equal to a second threshold, when discriminating that the three-dimensional engine usage of the application is less than or equal to the second threshold, the application discriminating module discriminates that the application belongs to a second type of the multimedia player type, when discriminating that the three-dimensional engine usage of the application is not less than or equal to the second threshold, the application discriminating that the three-dimensional engine usage of the application is not equal to the first threshold, the application discriminating that the three-dimensional engine usage of the application is greater than or equal to the first threshold, the three-dimensional engine usage of the application is not equal to the first threshold, the application program judging module judges that the application program type of the application program belongs to the game type.
6. The electronic device of claim 5, wherein the first type comprises movies and the second type comprises music or speech.
7. The electronic device as recited in claim 4, further comprising:
a database for storing the preset application program type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010737614.3A CN114003193B (en) | 2020-07-28 | 2020-07-28 | Electronic device and sound mode adjusting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010737614.3A CN114003193B (en) | 2020-07-28 | 2020-07-28 | Electronic device and sound mode adjusting method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114003193A CN114003193A (en) | 2022-02-01 |
| CN114003193B true CN114003193B (en) | 2023-10-17 |
Family
ID=79920415
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010737614.3A Active CN114003193B (en) | 2020-07-28 | 2020-07-28 | Electronic device and sound mode adjusting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114003193B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1941883A (en) * | 2005-09-29 | 2007-04-04 | 上海乐金广电电子有限公司 | Method for automatically adjusting image and speech by type data |
| CN104135705A (en) * | 2014-06-24 | 2014-11-05 | 惠州Tcl移动通信有限公司 | Method and system for automatically adjusting multimedia volume according to different scene modes |
| CN107819958A (en) * | 2017-11-30 | 2018-03-20 | 河南浩德科技有限公司 | Method for regulation of sound volume, device, mobile terminal and computer-readable storage medium |
| CN108133712A (en) * | 2016-11-30 | 2018-06-08 | 华为技术有限公司 | A kind of method and apparatus for handling audio data |
| CN109388367A (en) * | 2018-09-04 | 2019-02-26 | Oppo广东移动通信有限公司 | Audio method of adjustment, device, electronic equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201026014A (en) * | 2008-12-29 | 2010-07-01 | Inventec Appliances Corp | Method for volume adaptation, mobile electronic device and computer program product using the method thereof |
| TWI384457B (en) * | 2009-12-09 | 2013-02-01 | Nuvoton Technology Corp | System and method for audio adjustment |
-
2020
- 2020-07-28 CN CN202010737614.3A patent/CN114003193B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1941883A (en) * | 2005-09-29 | 2007-04-04 | 上海乐金广电电子有限公司 | Method for automatically adjusting image and speech by type data |
| CN104135705A (en) * | 2014-06-24 | 2014-11-05 | 惠州Tcl移动通信有限公司 | Method and system for automatically adjusting multimedia volume according to different scene modes |
| CN108133712A (en) * | 2016-11-30 | 2018-06-08 | 华为技术有限公司 | A kind of method and apparatus for handling audio data |
| CN107819958A (en) * | 2017-11-30 | 2018-03-20 | 河南浩德科技有限公司 | Method for regulation of sound volume, device, mobile terminal and computer-readable storage medium |
| CN109388367A (en) * | 2018-09-04 | 2019-02-26 | Oppo广东移动通信有限公司 | Audio method of adjustment, device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 钢琴调音软件的设计;苏江峰;《中国优秀硕士学位论文全文数据库 (信息科技辑)》;第2009卷(第02期);第I136-53页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114003193A (en) | 2022-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110446115B (en) | Live broadcast interaction method and device, electronic equipment and storage medium | |
| EP3611895B1 (en) | Method and device for user registration, and electronic device | |
| KR100785076B1 (en) | Method for detecting real time event of sport moving picture and apparatus thereof | |
| US20160275403A1 (en) | Information processing apparatus, information processing method, program | |
| CN109788345B (en) | Live broadcast control method and device, live broadcast equipment and readable storage medium | |
| CN110996153B (en) | Scene recognition-based sound and picture quality enhancement method and system and display | |
| JP2017535809A (en) | Sound sample validation to generate a sound detection model | |
| US20120237042A1 (en) | Signal clustering apparatus | |
| CN109739354B (en) | Voice-based multimedia interaction method and device | |
| CN111770356A (en) | Interaction method and device based on live game | |
| WO2018018685A1 (en) | Screen control method, and terminal | |
| KR20150093059A (en) | Method and apparatus for speaker verification | |
| CN107181986A (en) | The matching process and device of video and captions | |
| CN109640165B (en) | Multimedia playing method for switching audio tracks, terminal equipment and readable storage medium | |
| CN114003193B (en) | Electronic device and sound mode adjusting method | |
| TWI757797B (en) | Electronic device and sound mode adjustment method | |
| CN112307260A (en) | Video identification method, video identification device, electronic equipment and computer readable storage medium | |
| CN112668408A (en) | Face key point generation method and device, storage medium and electronic equipment | |
| JP7466087B2 (en) | Estimation device, estimation method, and estimation system | |
| CN112333531B (en) | Audio data playing method, device and readable storage medium | |
| JP2002159741A (en) | Game device and information storage medium | |
| CN103915106B (en) | Title generation method and system | |
| CN115811589A (en) | Infrared remote control video device and infrared remote control video playing method | |
| CN108877808B (en) | Mistaken touch prevention voice awakening method and family education equipment | |
| CN111128227A (en) | Sound detection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |