CN114093362A

CN114093362A - Audio conversion method and device, electronic equipment and readable storage medium

Info

Publication number: CN114093362A
Application number: CN202111448918.9A
Authority: CN
Inventors: 王建辉; 杜新凯; 吕超; 卢世成; 赵日新; 张艳雄
Original assignee: Sunshine Insurance Group Co Ltd
Current assignee: Sunshine Insurance Group Co Ltd
Priority date: 2021-12-01
Filing date: 2021-12-01
Publication date: 2022-02-25

Abstract

The application belongs to the technical field of audio, and discloses an audio conversion method, an audio conversion device, electronic equipment and a readable storage medium, wherein the method comprises the steps of respectively obtaining the set completion time length and the audio conversion time length corresponding to each audio in a target audio set; respectively determining the margin duration of each audio frequency according to the set completion duration and the audio frequency conversion duration corresponding to each audio frequency in the target audio frequency set; sorting the audios according to the margin duration of each audio in the target audio set to obtain audio conversion sorting; and respectively carrying out audio conversion on each audio according to the audio conversion sequence of each audio in the target set. Therefore, the time efficiency of audio conversion can be improved when the off-line audio conversion is carried out.

Description

Audio conversion method and device, electronic equipment and readable storage medium

Technical Field

The present application relates to the field of audio technologies, and in particular, to an audio conversion method, an audio conversion apparatus, an electronic device, and a readable storage medium.

Background

With the rapid development of the internet, the scenes of the audio conversion application are increasing. For example, in the sales industry or customer service industry, the customer needs to be contacted in the form of a telephone or voice, a large amount of audio is generated in the process, and the audio is generally required to be converted into text for content analysis, so that the analysis result is used for better serving the customer.

In the prior art, an on-line speech recognition or an off-line speech recognition is usually adopted to perform audio conversion.

However, the delay of the online audio conversion is low, but the efficiency is also low, resulting in high use cost; off-line audio conversion delays are high, resulting in poor conversion timeliness.

Therefore, when performing off-line audio conversion, how to improve the timeliness of the audio conversion is a technical problem to be solved.

Disclosure of Invention

An object of the embodiments of the present application is to provide an audio conversion method, an audio conversion device, an electronic device, and a readable storage medium, so as to improve the time efficiency of audio conversion when performing offline audio conversion.

In one aspect, a method of audio conversion is provided, including:

respectively acquiring a set completion time length and an audio conversion time length corresponding to each audio in a target audio set;

respectively determining the margin duration of each audio frequency according to the set completion duration and the audio frequency conversion duration corresponding to each audio frequency in the target audio frequency set;

sorting the audios according to the margin duration of each audio in the target audio set to obtain audio conversion sorting;

and respectively carrying out audio conversion on each audio according to the audio conversion sequence of each audio in the target set.

In the implementation process, when audio conversion is carried out, the audios are sorted according to the margin duration of the audios, and are converted according to the audio conversion sorting, so that the time efficiency of audio conversion is improved.

In one embodiment, the method further comprises:

when the preset set updating condition is determined to be reached, the following steps are executed:

respectively acquiring the priority of each audio in the audio set to be processed;

and screening each audio in the audio set to be processed according to the priority of each audio in the audio set to be processed to obtain a target audio set, wherein the target audio set is a set of screened audios.

In the implementation process, the audios are screened according to the priorities of the audios.

In one embodiment, determining that a preset set update condition is reached includes:

when a set updating instruction sent by a user is determined to be received, judging that a preset set updating condition is reached;

when determining that all audios in the target audio set complete audio conversion, judging that a preset set updating condition is reached;

and when the preset set updating period is determined to be reached, judging that the preset set updating condition is reached.

In the implementation process, when the preset set updating condition is determined to be reached, the new set audio is followed.

In one embodiment, the filtering each audio in the audio set to be processed according to the priority of each audio in the audio set to be processed to obtain the target audio set includes:

according to the priority of each audio in the set to be processed, sorting each audio in the set to be processed to obtain audio priority sorting;

according to the audio priority sequence, sequentially aiming at each audio in the audio set to be processed, executing the following steps:

determining the sum of the audio time lengths of all the audios in the target audio set to obtain a first total audio time length;

determining the sum of the audio time length of one audio in the audio set to be processed and the total first audio time length to obtain a second total audio time length;

and if the total duration of the second audio is lower than the set audio duration threshold, adding one audio into the target audio set.

In the implementation process, when the audio is added to the target audio set, it is ensured that the total audio duration of the target audio set does not exceed the set audio duration threshold.

In one embodiment, the method for ranking the audios according to the margin duration of each audio in the target audio set and before obtaining the audio conversion ranking, further includes:

screening out parallel conversion audios of which the margin duration is smaller than a set duration threshold from the target audio set;

the parallel conversion audio is segmented, and a plurality of audio segments of each parallel conversion audio are obtained respectively;

adding a plurality of audio segments of each parallel converted audio to a target audio set;

acquiring audio conversion duration of a plurality of audio segments of each parallel conversion audio;

and respectively determining the margin duration of the plurality of audio segments of each parallel conversion audio according to the audio conversion duration of the plurality of audio segments of each parallel conversion audio.

In the implementation process, if the parallel conversion audio with the margin duration smaller than the set duration threshold exists, the parallel audio is segmented, and the margin duration of each audio segment is determined respectively.

In one embodiment, after performing audio conversion on each audio according to the audio conversion sequence of the audios, the method further includes:

if at least one audio segment of the parallel conversion audio exists in the target audio set, merging the audio conversion results of the audio segments after the segmentation of each parallel conversion audio respectively to obtain the merged conversion result of each parallel conversion audio respectively.

In the implementation process, the audio conversion results of each audio segment are combined to obtain the combined conversion result of the parallel conversion audio.

In one aspect, an apparatus for audio conversion is provided, including:

the acquisition unit is used for respectively acquiring the set completion time length and the audio conversion time length corresponding to each audio in the target audio set;

the setting unit is used for respectively determining the margin duration of each audio frequency according to the set completion duration and the audio frequency conversion duration corresponding to each audio frequency in the target audio frequency set;

the sequencing unit is used for sequencing the audios according to the margin duration of each audio in the target audio set to obtain audio conversion sequencing;

and the conversion unit is used for respectively carrying out audio conversion on each audio according to the audio conversion sequence of each audio in the target set.

In one embodiment, the obtaining unit is further configured to:

In one embodiment, the obtaining unit is specifically configured to:

In one embodiment, the sorting unit is further configured to:

In one embodiment, the conversion unit is further configured to:

In one aspect, an electronic device is provided that includes a processor and a memory, the memory storing computer readable instructions that, when executed by the processor, perform the steps of the method provided in any of the various alternative implementations of audio conversion described above.

In one aspect, a readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, is adapted to carry out the steps of the method as provided in any of the various alternative implementations of audio conversion as described above.

In one aspect, a computer program product is provided, which when run on a computer causes the computer to perform the steps of the method as provided in any of the various alternative implementations of audio conversion described above.

In the method, the device, the electronic equipment and the readable storage medium for audio conversion provided by the embodiment of the application, the set completion time length and the audio conversion time length corresponding to each audio in the target audio set are respectively obtained; respectively determining the margin duration of each audio frequency according to the set completion duration and the audio frequency conversion duration corresponding to each audio frequency in the target audio frequency set; sorting the audios according to the margin duration of each audio in the target audio set to obtain audio conversion sorting; and respectively carrying out audio conversion on each audio according to the audio conversion sequence of each audio in the target set. Therefore, when audio conversion is carried out, the audios can be sequenced according to the margin duration of the audios, and each audio can be converted according to the audio conversion sequencing, so that the time efficiency of audio conversion is improved.

Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.

Fig. 1 is a schematic view of an audio conversion application scenario provided in an embodiment of the present application;

fig. 2 is a flowchart illustrating an implementation of a method for audio conversion according to an embodiment of the present disclosure;

FIG. 3 is a diagram illustrating an example of a method for obtaining a duration of an audio margin according to an embodiment of the present application;

fig. 4 is a flowchart illustrating a detailed implementation of a method for audio conversion according to an embodiment of the present disclosure;

fig. 5 is a block diagram illustrating an apparatus for audio conversion according to an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of an electronic device in an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.

First, some terms referred to in the embodiments of the present application will be described to facilitate understanding by those skilled in the art.

The terminal equipment: may be a mobile terminal, a fixed terminal, or a portable terminal such as a mobile handset, station, unit, device, multimedia computer, multimedia tablet, internet node, communicator, desktop computer, laptop computer, notebook computer, netbook computer, tablet computer, personal communication system device, personal navigation device, personal digital assistant, audio/video player, digital camera/camcorder, positioning device, television receiver, radio broadcast receiver, electronic book device, gaming device, or any combination thereof, including the accessories and peripherals of these devices, or any combination thereof. It is also contemplated that the terminal device can support any type of interface to the user (e.g., wearable device), and the like.

A server: the cloud server can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and can also be a cloud server for providing basic cloud computing services such as cloud service, a cloud database, cloud computing, cloud functions, cloud storage, network service, cloud communication, middleware service, domain name service, security service, big data and artificial intelligence platform and the like.

Automatic Speech Recognition technology (ASR): is a technique for converting human speech into text.

Natural language processing (Neuro-linear Programming, NLP): the natural language used by human communication is a technology for interactive communication with machines.

In order to improve the time efficiency of audio conversion when audio conversion is performed, embodiments of the present application provide an audio conversion method, an audio conversion apparatus, an electronic device, and a readable storage medium.

Fig. 1 is a schematic view of an audio conversion application scenario provided in an embodiment of the present application. In fig. 1, a server generates a target audio set based on a to-be-processed audio set, and performs audio conversion on audio in the target audio set.

In one embodiment, a server respectively obtains a set completion time length and an audio conversion time length corresponding to each audio frequency in a target audio frequency set, respectively determines a margin time length of each audio frequency according to the set completion time length and the audio conversion time length corresponding to each audio frequency in the target audio frequency set, sorts the audio frequencies according to the margin time lengths of each audio frequency in the target audio frequency set to obtain an audio frequency conversion sort, and respectively converts each audio frequency according to the audio frequency conversion sort of each audio frequency in the target set.

For example, the server respectively obtains priorities of four audios in the collected audio set to be processed, sorts the four audios in the set to be processed according to the priorities of the four audios in the set to be processed, obtains an audio priority ranking, and executes the following steps for the four audios in the audio set to be processed in sequence according to the audio priority ranking: determining the sum of the audio time lengths of three audios in the target audio set, obtaining a first total audio time length, determining the sum of the audio time length of an audio 1 in the audio set to be processed and the first total audio time length, obtaining a second total audio time length, and if the second total audio time length is lower than a set audio time length threshold, adding the audio 1 to the target audio set. The server respectively obtains the set completion time length and the audio conversion time length corresponding to the three audios in the target audio set, and respectively determines the margin time lengths of the four audios according to the set completion time length and the audio conversion time length corresponding to the three audios in the target audio set. The server screens out parallel conversion audios with margin duration smaller than a set duration threshold from a target audio set, divides the parallel conversion audios, respectively obtains a plurality of audio segments of each parallel conversion audio, adds the plurality of audio segments of each parallel conversion audio to the target audio set, obtains audio conversion durations of the plurality of audio segments of each parallel conversion audio, and respectively determines the margin duration of the plurality of audio segments of each parallel conversion audio according to the audio conversion durations of the plurality of audio segments of each parallel conversion audio. The server sorts the audios according to the margin durations of the four audios in the target audio set to obtain an audio conversion sorting, respectively performs audio conversion on each audio according to the audio conversion sorting of the four audios in the target set to obtain an audio conversion result, and if at least one audio fragment of the parallel conversion audio exists in the target audio set, the server respectively merges the audio conversion results of the audio fragments obtained after the parallel conversion audio is split, and respectively obtains a merged conversion result of each parallel conversion audio.

Therefore, when audio conversion is carried out, the audio is sequentially added into the target audio set according to the priority of the audio, the audios are sorted according to the margin duration of each audio in the target audio, and each audio is converted according to the audio conversion sorting, so that the time efficiency of the audio conversion is improved.

In the embodiment of the present application, only the execution subject is taken as an example for description, and in practical applications, the execution subject may also be other electronic devices such as a terminal device, and is not limited herein.

Referring to fig. 2, a flowchart of an implementation of a method for audio conversion according to an embodiment of the present application is shown, where the method is implemented in the following steps:

step 200: and respectively acquiring the set completion time length and the audio conversion time length corresponding to each audio in the target audio set.

Specifically, the server obtains a set completion time length and an audio conversion time length corresponding to each audio in the target audio set.

Wherein the set completion time duration is preset, and is a time duration from the time when the system confirms that the reception is successful to the time when the audio conversion is completed, which is expected by the user.

Optionally, the set completion duration may be set according to an actual application situation, and is not limited herein.

The audio conversion duration is the duration of audio conversion operation of one tone, and is determined based on the audio conversion efficiency.

The audio conversion efficiency may be one hour of the audio conversion service, and the duration of the converted audio may be represented by R.

Alternatively, the setting completion time period may be denoted by Tf, and the audio conversion time period may be denoted by Tl.

Further, before step 200 is executed, it may be determined that a preset set update condition is reached, and the target audio set is updated.

When the target audio set is updated, the following steps may be performed:

the method comprises the following steps: and respectively acquiring the priority of each audio in the audio set to be processed.

Specifically, the server obtains the priority of each audio in the audio set to be processed.

The priority of the audio can be an agent, a team, a district, a business scene and the like, and the priority of the audio is set in advance.

Step two: and screening each audio in the audio set to be processed according to the priority of each audio in the audio set to be processed to obtain a target audio set.

Specifically, when step two is executed, the following steps may be adopted:

step 1: and sequencing the audios according to the priorities of the audios to obtain audio priority sequencing.

Specifically, the server sorts the audios in the audio set to be processed according to the priorities of the audios in the audio set to be processed, so as to obtain the audio priority ranks of the audios in the audio set to be processed.

The audio priority sequence of each audio in the audio set to be processed can be obtained by comparing the priority of each audio in the audio set to be processed pairwise.

In practical applications, the sorting may be performed in other manners according to practical application situations, and is not limited herein.

Step 2: according to the audio priority sequence, sequentially aiming at each audio in the audio set to be processed, executing the following steps:

step A: and determining the sum of the audio time lengths of the audios in the target audio set to obtain a first total audio time length.

Specifically, the server adds the audio time lengths of the audios in the target audio set to obtain the total audio time length of each audio in the target audio set as a first total audio time length.

In an embodiment, five audios in the target audio set have audio durations of 1 hour, 2 hours, 3 hours, and 2 hours, respectively, and then the audio durations of the audios in the target audio set are added, so that the total audio duration of the audios in the target audio set is 9 hours, and then the total first audio duration is 9 hours.

In practical applications, the sum of the audio durations of the audios in the target audio set may be determined in other manners according to practical application conditions, which is not limited herein.

And B: and determining the sum of the audio time length of one audio in the audio set to be processed and the total first audio time length to obtain a second total audio time length.

Specifically, the server adds the audio time length of one audio in the audio set to be processed to the obtained first total audio time length to obtain a second total audio time length.

And C: and if the total duration of the second audio is lower than the set audio duration threshold, adding the audio into the target audio set.

Specifically, the server compares the total second audio time length with a set audio time length threshold, and adds one audio to the target audio set when the total second audio time length is determined not to be higher than the set audio time length threshold.

Wherein, the target audio set is the set of the screened audio.

In practical applications, the set audio duration may be set according to practical application conditions, for example, the set audio duration is 1 hour, which is not limited herein.

Further, if the total time length of the second audio is higher than the set audio time length threshold, one audio is refused to be added into the target audio set, and an abnormal warning is sent out.

Specifically, the server compares the total second audio time length with a set audio time length threshold, and when the total second audio time length is higher than the set audio time length threshold, one audio is rejected to be added into the target audio set, and an abnormal warning is sent out.

Optionally, the abnormal warning may be an error report, and the user is prompted in a form of a pop-up box, and in practical application, the abnormal warning may be performed in other manners according to practical application conditions, which is not limited herein.

In one embodiment, the audio duration of one audio in the audio set to be processed is added to the total audio duration of the target audio set to obtain a first total audio duration, the first total audio duration is compared with a second total audio duration, if the first total audio duration is smaller than the second total audio duration, one audio in the audio set to be processed is added to the target audio set, otherwise, one audio in the audio set to be processed is rejected from being added to the target audio set. And the second total audio time length is the maximum audio time length capacity value of the sum of the target audio.

Wherein, the maximum audio duration capacity value may be 500 hours.

Wherein, the condition for determining that the preset set update condition is reached may be any one of the following conditions:

the first condition is as follows: and when a set updating instruction sent by a user is determined to be received, judging that a preset set updating condition is reached.

Specifically, the user sets a set update instruction, and when the set update instruction issued by the user is received, the server can determine that the preset set update condition is met.

The preset set updating condition is a condition for updating the target audio set, and the preset set updating condition is set according to an actual application situation, which is not limited herein.

For example, the preset set update condition may be a priority.

And a second condition: and when determining that all the audios in the target audio set complete audio conversion, judging that the preset set updating condition is reached.

Specifically, when it is determined that each audio in the target audio set completes audio conversion, the server may determine that the preset set update condition is reached.

And (3) carrying out a third condition: and when the preset set updating period is determined to be reached, judging that the preset set updating condition is reached.

Specifically, when it is determined that the preset set update period is reached, the server may determine that the preset set update condition is reached, and update the condition of the target audio.

The preset set update period may be a period of time, or may be a period of the number of audios for audio recognition.

In one embodiment, when the target audio in the target audio set is subjected to audio conversion, the server determines that a preset set update condition is reached, updates the condition of the filtered audio of the target audio set, and adds the filtered audio to the target audio according to the updated condition.

In one embodiment, each audio in the audio set to be processed is screened according to the priority of the audio, and the audio with higher priority is screened out to obtain the target audio set. When the fact that the audio conversion of each audio in the target audio set is completed is determined, the server judges that a preset set updating condition is met, then the remaining audio with lower priority is selected from the audio set to be processed, and the audio is sequentially added into the target audio set to be subjected to audio conversion.

In practical applications, the preset set update period may be set according to practical application conditions, and is not limited herein.

In practical application, the condition for achieving the preset set update may also be other conditions, and may be set according to practical application conditions, which is not limited herein.

Step 201: and respectively determining the margin duration of each audio frequency according to the set completion duration and the audio frequency conversion duration corresponding to each audio frequency in the target audio frequency set.

Specifically, the server subtracts the audio conversion duration from the set completion duration corresponding to each audio according to the set completion duration and the audio conversion duration corresponding to each audio in the acquired target audio set, and the obtained result is the margin duration of each audio.

The margin duration is the duration which is more than the set completion duration after the audio conversion is completed.

Alternatively, the margin duration may be represented by To.

Referring to fig. 3, an exemplary diagram of a method for obtaining an audio margin duration according to an embodiment of the present application is shown, where the exemplary diagram includes two modules, a traffic module and an audio identification module. And after the voice is hung up, the telephone traffic module stores the audio, and the set completion time length of the audio is acquired after the audio is stored. And downloading the audio by the audio identification module, wherein the set finishing time length comprises a conversion waiting time length, an audio conversion time length and a margin time length. And the server acquires the margin duration of the audio according to the set completion duration, the conversion waiting duration and the audio conversion duration of the audio.

And after the telephone traffic module stores the audio, recording audio information.

Optionally, the traffic module stores audio by using data structures such as a circular queue or a red-black tree.

The audio information may include a priority of the audio, an audio duration, an identification duration, a time when the recording is received, a setting completion duration, and the like.

Wherein the transition waiting period may be a period from when the audio is ready to start to when the audio is transitioned.

Alternatively, we can denote Tw.

Thus, the margin duration of the audio can be obtained through the set completion duration, the conversion waiting duration and the audio conversion duration of the audio.

In one embodiment, the set completion time of one audio is 3 hours, wherein the audio conversion time of the audio is 2 hours, and the margin time of the audio is 1 hour.

Step 202: and sequencing the audios according to the margin duration of each audio in the target audio set to obtain audio conversion sequencing.

Specifically, the server sorts each audio in the target audio set according to the obtained margin duration of each audio in the target audio set, so as to obtain the audio conversion sorting of each audio in the target audio set.

The audio conversion sequence of each audio in the target audio set can be obtained by comparing each audio in the target audio set pairwise.

In practical applications, the sorting may also be performed in other manners according to practical application situations, and is not limited herein.

Further, before step 202 is executed, the parallel conversion audio with the margin duration smaller than the set duration threshold may also be sliced.

When the parallel conversion audio with the margin duration smaller than the set duration threshold is divided, the following steps can be executed:

the method comprises the following steps: and screening out the parallel conversion audio with the margin duration less than the set duration threshold from the target audio set.

Specifically, the server compares the margin duration of each audio in the target audio set with a set duration threshold, and screens out the parallel conversion audio of which the margin duration is smaller than the set duration threshold.

In practical applications, the set time length threshold may be set according to practical application conditions, and is not limited herein.

Step two: and segmenting the parallel conversion audio to respectively obtain a plurality of audio segments of each parallel conversion audio.

Specifically, the server divides each of the screened parallel conversion audios to obtain a plurality of audio clips of each of the parallel conversion audios.

Furthermore, the multiple audio segments after the parallel conversion audio segmentation may be specially marked, for example, the multiple sub-steps are numbered, and in practical application, other special marks may also be used, which is not limited herein.

Step three: multiple audio segments of each parallel converted audio are added to the target audio set.

Specifically, the server adds a plurality of audio clips obtained by segmenting each parallel conversion audio into the target audio set.

Step four: audio conversion durations for a plurality of audio segments of each of the parallel-converted audios are obtained.

Specifically, the server acquires audio conversion durations of a plurality of audio pieces of each of the parallel-converted audios.

Wherein the audio transition duration is related to the audio duration.

Step five: and respectively determining the margin duration of the plurality of audio segments of each parallel conversion audio according to the audio conversion duration of the plurality of audio segments of each parallel conversion audio.

Specifically, the server determines margin durations of the multiple audio segments of each parallel conversion audio respectively according to the acquired audio conversion durations of the multiple audio segments of each parallel conversion audio and the previously acquired set completion duration.

And determining the difference between the set completion time length and the audio conversion time length to obtain the margin time length.

In one embodiment, the server obtains the margin duration of each audio frequency in the target audio frequency set, if the margin duration of each audio frequency is greater than 0, sorts the audio frequencies according to the margin duration of each audio frequency in the target audio frequency set, obtains an audio frequency conversion sequence, and performs audio frequency conversion operation according to the audio frequency conversion sequence. If the audio with the margin duration less than 0 exists in the audios, screening the audio with the margin duration less than 0, segmenting the audio, recalculating the segmented margin duration, and selecting the audio with the minimum margin duration to perform audio conversion operation.

The method for dividing the audio frequency can divide the audio frequency into at least two sections in average, can also determine the product of the margin duration and the set coefficient as a new margin duration, and calculates the audio frequency duration according to the new margin duration, so that the audio frequency can be divided.

The set coefficient may be a coefficient greater than 0 and smaller than 1, or may be set according to an actual application, for example, the set coefficient may be 0.5, which is not limited herein.

Step 203: and respectively carrying out audio conversion on each audio according to the audio conversion sequence of each audio in the target set.

Specifically, the server performs audio conversion on each audio according to the audio conversion sequence of each audio in the target set, and obtains an audio conversion result.

After step 203 is executed, if at least one audio segment of the parallel conversion audio exists in the target audio set, merging the audio conversion results of the audio segments after the segmentation of each parallel conversion audio, and obtaining the merged conversion result of each parallel conversion audio.

Specifically, if at least one audio segment of the parallel conversion audio exists in the target audio set, the server respectively merges the audio conversion results of the audio segments after the segmentation of each parallel conversion audio, and respectively obtains the merged conversion result of each parallel conversion audio.

In one embodiment, the server may perform special marking on the multiple audio segments after each parallel conversion audio is split, perform audio conversion on the audio segment after each parallel conversion audio is split, and merge audio conversion results of the audio segments after each parallel conversion audio is split according to the special marking of the multiple audio segments after each parallel conversion audio is split, so as to obtain a merged conversion result of each parallel conversion audio respectively.

For example, the sub-steps are numbered, and other special marks may be used in practical applications, which are not limited herein.

Referring to fig. 4, a detailed implementation flowchart of a method for audio conversion according to an embodiment of the present application is shown, and the detailed implementation flow of the method is as follows:

step 400: the server respectively acquires the priority of each audio in the audio set to be processed.

Step 401: and the server sorts the audios in the set to be processed according to the priorities of the audios in the set to be processed to obtain the audio priority sequence.

Step 402: the server obtains the total duration of the current target audio set.

Step 403: the server judges whether the sum of the audio time length of one audio in the audio priority sequence and the total time length of the current target audio set is not lower than a set audio time length threshold value, if so, the step 405 is executed, and if not, the step 404 is executed.

Step 404: and the server adds the audio to the target audio set according to the audio priority.

It should be noted that after step 404 is executed, step 402 is executed.

Step 405: the server refuses to add the audio to the target audio set.

Step 406: the server respectively obtains the set completion time length and the audio conversion time length corresponding to each audio in the target audio set.

Step 407: and the server respectively determines the margin duration of each audio frequency according to the set completion duration and the audio frequency conversion duration corresponding to each audio frequency in the target audio frequency set.

Step 408: and the server screens out the parallel conversion audio with the margin duration less than the set duration threshold from the target audio set.

Step 409: the server divides each parallel conversion audio to obtain a plurality of audio fragments of each parallel conversion audio respectively.

Step 410: the server adds a plurality of audio clips of each parallel converted audio to the target audio set.

Step 411: the server obtains the audio conversion duration of the plurality of audio segments of each parallel conversion audio and respectively determines the margin duration of the plurality of audio segments of each parallel conversion audio.

Step 412: and the server sorts the audios according to the margin duration of each audio in the target audio set to obtain audio conversion sorting.

Step 413: and the server performs audio conversion on each audio according to the audio conversion sequence of each audio in the target set to obtain an audio conversion result.

Step 414: and the server respectively merges the audio conversion results of the audio segments after the segmentation of each parallel conversion audio to respectively obtain the merged conversion result of each parallel conversion audio.

Specifically, when step 400 to step 414 are executed, the specific steps refer to step 200 to step 203, which are not described herein again.

The traditional audio conversion usually adopts an automatic voice recognition technology and a natural language processing technology, and adopts two technical schemes, one is online audio conversion and real-time conversion, and the traditional audio conversion is generally used in scenes such as voice customer service and robot conversation and has high cost. The other method is off-line audio conversion, which is generally used in scenes such as voice quality inspection, recording analysis and the like, and the operation of audio conversion can be started only after the voice call is disconnected, so that the time efficiency of audio conversion is poor, and both methods need a large amount of hardware resources.

In the embodiment of the application, when audio conversion is carried out, audio is sequentially added into a target audio set according to the priority of the audio, the margin duration of each audio in the target audio is determined, the audio smaller than a set duration threshold is divided into a plurality of audio segments, the audios are sequenced according to the margin duration, the audio conversion is carried out on each audio according to the audio conversion sequencing, the audio conversion timeliness is improved, the online audio conversion efficiency can be approached on the basis of an offline audio conversion scheme on the premise of not increasing hardware resources, the audio conversion timeliness is improved, the hardware resources are fully utilized, and the hardware resource investment is reduced.

Based on the same inventive concept, the embodiment of the present application further provides an audio conversion apparatus, and as the principle of the apparatus and the device for solving the problem is similar to that of an audio conversion method, the implementation of the apparatus can refer to the implementation of the method, and repeated details are omitted.

As shown in fig. 5, which is a schematic structural diagram of an apparatus for audio conversion according to an embodiment of the present application, the apparatus includes:

an obtaining unit 501, configured to obtain a set completion duration and an audio conversion duration corresponding to each audio in a target audio set respectively;

a setting unit 502, configured to determine a margin duration of each audio according to a set completion duration and an audio conversion duration corresponding to each audio in the target audio set;

the sorting unit 503 is configured to sort the audios according to the margin durations of the audios in the target audio set, so as to obtain an audio conversion sort;

the converting unit 504 is configured to perform audio conversion on each audio according to the audio conversion sequence of the audios in the target set.

In one embodiment, the obtaining unit 501 is further configured to:

In one embodiment, the obtaining unit 501 is specifically configured to:

In one embodiment, the sorting unit 503 is further configured to:

In one embodiment, the conversion unit 504 is further configured to:

Fig. 6 shows a schematic structural diagram of an electronic device 6000. Referring to fig. 6, the electronic device 6000 includes: processor 6010 and memory 6020 may optionally further include a power supply 6030, a display unit 6040, and an input unit 6050.

The processor 6010 is a control center of the electronic apparatus 6000, connects various components using various interfaces and lines, and performs various functions of the electronic apparatus 6000 by running or executing software programs and/or data stored in the memory 6020, thereby integrally monitoring the electronic apparatus 6000.

In the embodiment of the present application, the processor 6010, when calling the computer program stored in the memory 6020, executes the method of audio conversion as provided in the embodiment shown in fig. 2.

Alternatively, processor 6010 may include one or more processing units; preferably, processor 6010 may integrate an application processor that handles mainly the operating system, user interfaces, applications, etc. and a modem processor that handles mainly wireless communications. It is to be appreciated that the modem processor described above may not be integrated into processor 6010. In some embodiments, the processor, memory, and/or memory may be implemented on a single chip, or in some embodiments, they may be implemented separately on separate chips.

The memory 6020 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, various applications, and the like; the storage data area may store data created according to the use of the electronic device 6000, and the like. In addition, the memory 6020 may include high-speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.

The electronic device 6000 further includes a power supply 6030 (e.g., a battery) for powering the various components, which may be logically connected to the processor 6010 via a power management system to manage charging, discharging, and power consumption via the power management system.

The display unit 6040 may be configured to display information input by a user or information provided to the user, various menus of the electronic device 6000, and the like, and in the embodiment of the present invention, the display unit is mainly configured to display a display interface of each application in the electronic device 6000 and objects such as texts and pictures displayed in the display interface. The display unit 6040 may include a display panel 6041. The Display panel 6041 may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like.

The input unit 6050 may be used to receive information such as numbers or characters input by a user. The input unit 6050 may include a touch panel 6051 and other input devices 6052. Touch panel 6051, also referred to as a touch screen, may collect touch operations by a user on or near touch panel 6051 (e.g., operations by a user on or near touch panel 6051 using a finger, a stylus, or any other suitable object or attachment).

Specifically, the touch panel 6051 may detect a touch operation by the user, detect signals resulting from the touch operation, convert the signals into touch point coordinates, send the touch point coordinates to the processor 6010, receive a command sent from the processor 6010, and execute the command. In addition, the touch panel 6051 can be implemented by various types such as a resistive type, a capacitive type, an infrared ray, and a surface acoustic wave. Other input devices 6052 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, power on and off keys, etc.), a trackball, a mouse, a joystick, and the like.

Of course, the touch panel 6051 may cover the display panel 6041, and when the touch panel 6051 detects a touch operation thereon or nearby, the touch operation is transmitted to the processor 6010 to determine the type of the touch event, and then the processor 6010 provides a corresponding visual output on the display panel 6041 according to the type of the touch event. Although in fig. 6, the touch panel 6051 and the display panel 6041 are two separate components to implement the input and output functions of the electronic device 6000, in some embodiments, the touch panel 6051 and the display panel 6041 may be integrated to implement the input and output functions of the electronic device 6000.

The electronic device 6000 may also include one or more sensors, such as pressure sensors, gravitational acceleration sensors, proximity light sensors, and the like. Of course, the electronic device 6000 may also include other components such as a camera, which are not shown in fig. 6 and will not be described in detail since they are not the components used in this embodiment of the present application.

Those skilled in the art will appreciate that fig. 6 is merely an example of an electronic device and is not limiting of electronic devices and may include more or fewer components than those shown, or some components may be combined, or different components.

In an embodiment of the present application, a readable storage medium has a computer program stored thereon, and when the computer program is executed by a processor, the communication device may perform the steps in the above embodiments.

For convenience of description, the above parts are separately described as modules (or units) according to functional division. Of course, the functionality of the various modules (or units) may be implemented in the same one or more pieces of software or hardware when implementing the present application.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims

1. A method of audio conversion, comprising:

2. The method of claim 1, further comprising:

and screening each audio in the audio set to be processed according to the priority of each audio in the audio set to be processed to obtain the target audio set, wherein the target audio set is a set of screened audios.

3. The method of claim 2, wherein the determining that a preset set update condition is reached comprises:

when a set updating instruction sent by a user is determined to be received, judging that the preset set updating condition is reached;

when determining that the audio conversion of each audio in the target audio set is completed, judging that the updating condition of the preset set is reached;

4. The method as claimed in claim 2, wherein the filtering the audios in the audio set to be processed according to the priorities of the audios in the audio set to be processed to obtain the target audio set includes:

and if the total duration of the second audio is lower than a set audio duration threshold, adding the audio into the target audio set.

5. The method according to any one of claims 1 to 4, wherein before the sorting the audios according to the margin durations of the audios in the target audio set and obtaining the audio conversion sorting, further comprising:

the parallel conversion audios are segmented, and a plurality of audio segments of each parallel conversion audio are obtained respectively;

adding a plurality of audio segments of the each parallel converted audio to the target audio set;

6. The method of claim 5, wherein after said separately audio converting each audio in the order of audio conversion for each audio, further comprising:

if the audio frequency fragments of the at least one parallel conversion audio frequency exist in the target audio frequency set, merging the audio frequency conversion results of the audio frequency fragments obtained after the segmentation of each parallel conversion audio frequency respectively to obtain the merged conversion results of each parallel conversion audio frequency respectively.

7. An apparatus for audio conversion, comprising:

8. The apparatus of claim 7, wherein the obtaining unit is further configured to:

9. An electronic device comprising a processor and a memory, the memory storing computer readable instructions that, when executed by the processor, perform the method of any of claims 1-6.

10. A readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-6.