CN114639390A - Voice noise analysis method and system - Google Patents

Abstract

The invention provides a voice noise analysis method and a system, wherein the method comprises the following steps: acquiring voice data to be analyzed; extracting a noise audio segment only containing noise from voice data to be analyzed; determining the noise intensity grade corresponding to each noise audio frequency segment based on the noise intensity index of each noise audio frequency segment and the preset noise intensity classification grade; and determining a noise level evaluation result of the voice data to be analyzed according to the distribution condition of the noise intensity level corresponding to each noise audio clip. The noise level evaluation method based on the noise level of the voice data to be analyzed has the advantages that the noise intensity indexes of the noise audio frequency segments only containing noise are calculated to carry out independent analysis, then the noise level evaluation result of the whole voice data to be analyzed is determined according to the distribution condition of the noise intensity levels of all the noise audio frequency segments, the influence of normal voice is avoided, objective evaluation of the noise level of the voice data to be analyzed is achieved, reference audio is not needed, the application range is wider, and the noise conditions under various scenes can be accurately reflected.

Description

A method and system for analyzing speech noise

technical field

The invention relates to the technical field of speech signal processing, in particular to a speech noise analysis method and system.

Background technique

With the rapid development of the mobile Internet, the application of communication software is becoming more and more extensive. For example, more and more teachers provide online teaching guidance to students through instant communication software, instead of the traditional face-to-face teaching method. However, when using communication software, noise will seriously affect the audio quality of communication. In places with high requirements for noise, for example, when students listen to the audio courses recorded by teachers online through communication software, the audio noise in the audio courses should be kept as low as possible. small to improve teaching effectiveness. However, due to the huge amount of online teaching audio, the traditional way of analyzing the noise of each classroom by manual labor is huge and the analysis results are highly subjective.

In the prior art, the index evaluation methods (such as signal-to-noise ratio, segmental signal-to-noise ratio, etc.) for objectively evaluating the noise situation need to have exactly the same reference as the strictly time-aligned speech content when measuring the noise situation of a piece of audio. Audio, and for teaching scenarios or other situations where reference audio cannot be obtained, existing noise evaluation methods will not be able to perform noise evaluation. Therefore, how to achieve an objective evaluation of speech noise without reference audio is an urgent problem to be solved. .

SUMMARY OF THE INVENTION

In view of this, the embodiments of the present invention provide a speech noise analysis method and system to overcome the problem in the prior art that it is difficult to achieve objective evaluation of speech noise in the absence of reference audio.

An embodiment of the present invention provides a speech noise analysis method, including:

Obtain the voice data to be analyzed;

extracting noise audio segments that only contain noise from the speech data to be analyzed;

Determine the noise intensity level corresponding to each of the noise audio segments based on the noise intensity index of each noise audio segment and the preset noise intensity classification level;

Determine the noise level evaluation result of the speech data to be analyzed according to the distribution of the noise intensity levels corresponding to each of the noise audio segments.

Optionally, extracting a noise audio segment that only contains noise from the to-be-analyzed speech data includes:

Dividing the to-be-analyzed speech data into multiple audio segments based on the total duration of the to-be-analyzed speech data and a preset extraction duration period;

Convert each audio clip to an amplitude spectrum;

Input the amplitude spectrum corresponding to each audio clip into the preset noise classification model, and obtain the probability that each audio clip contains only noise;

Filters noisy audio clips containing only noise from audio clips based on a preset probability threshold.

Optionally, determining the noise intensity level corresponding to each of the noise audio clips based on the noise intensity index of each noise audio clip and a preset noise intensity classification level, including:

Calculate the noise intensity index corresponding to each noise audio segment separately;

Obtaining noise intensity index ranges corresponding to different noise intensity levels in the preset noise intensity classification levels;

According to the noise intensity index corresponding to the current noise audio clip, determine the current noise intensity index range corresponding to the current noise audio clip;

The noise intensity level corresponding to the current noise intensity index range is determined as the noise intensity level of the current noise audio segment.

Optionally, determining the noise level of the to-be-analyzed speech data according to the distribution of noise intensity levels corresponding to each of the noise audio segments includes:

obtaining the proportions of different noise intensity levels in each of the noise audio clips;

Determine the noise level evaluation result of the speech data to be analyzed according to the proportion of different noise intensity levels and the preset proportion evaluation index.

Optionally, the noise intensity levels include: high-intensity noise levels, medium-intensity noise levels, and low-intensity noise levels.

Optionally, determining the noise level evaluation result of the speech data to be analyzed according to the ratio of different noise intensity levels and a preset ratio evaluation index, including:

Obtain the proportion of high-intensity noise levels;

According to the relationship between the proportion of the high-intensity noise level and the preset proportion range of the high-intensity noise level in the preset proportion evaluation index, the noise level evaluation result of the speech data to be analyzed is determined.

Optionally, the noise level evaluation result includes: low noise level, moderate noise level and high noise level, wherein,

When the proportion of the high-intensity noise level is less than the minimum value of the preset proportion of the high-intensity noise level in the preset proportion evaluation index, it is determined that the noise level evaluation result is that the noise level is low;

When the proportion of the high-intensity noise level is within the preset proportion of the high-intensity noise level in the preset proportion evaluation index, judging that the noise level evaluation result is a moderate noise level;

When the proportion of the high-intensity noise level is greater than the maximum value of the preset high-intensity noise level proportion range in the preset proportion evaluation index, it is determined that the noise level evaluation result is a high noise level.

The embodiment of the present invention also provides a speech noise analysis system, including:

an acquisition module for acquiring the voice data to be analyzed;

a first processing module for extracting noise audio segments that only contain noise from the to-be-analyzed speech data;

The second processing module is configured to determine the noise intensity level corresponding to each of the noise audio segments based on the noise intensity index of each noise audio segment and the preset noise intensity classification level;

The third processing module is configured to determine the noise level evaluation result of the to-be-analyzed speech data according to the distribution of the noise intensity levels corresponding to each of the noise audio segments.

An embodiment of the present invention further provides an electronic device, including: a memory and a processor, the memory and the processor are connected in communication with each other, the memory stores computer instructions, and the processor executes the computer instructions, thereby executing the speech noise analysis method provided by the embodiments of the present invention.

Embodiments of the present invention further provide a computer-readable storage medium, where the computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to execute the speech noise analysis method provided by the embodiments of the present invention.

The technical scheme of the present invention has the following advantages:

Embodiments of the present invention provide a speech noise analysis method and system, by acquiring speech data to be analyzed; extracting noise audio segments containing only noise from the speech data to be analyzed; based on the noise intensity index and prediction of each noise audio segment The noise intensity level is set to determine the noise intensity level corresponding to each noise audio segment; the noise level evaluation result of the speech data to be analyzed is determined according to the distribution of the noise intensity level corresponding to each noise audio segment. Therefore, the noise intensity level of each noise audio segment is separately analyzed by calculating the noise intensity index of the noise audio segment containing only noise, and then the noise level of the entire speech data to be analyzed is determined according to the distribution of the noise intensity levels of all noise audio segments. The evaluation result avoids the influence of normal speech in the speech data to be analyzed, realizes an objective evaluation of the noise level of the speech data to be analyzed, and does not require reference audio, has a wider application range, and can accurately reflect the noise in various scenarios.

Description of drawings

In order to illustrate the specific embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the specific embodiments or the prior art. Obviously, the accompanying drawings in the following description The drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

1 is a flowchart of a method for analyzing speech noise in an embodiment of the present invention;

2 is a schematic diagram of the process of inputting the amplitude spectrum corresponding to each audio clip into a preset noise classification model to obtain a probability corresponding to each audio clip that only contains noise according to an embodiment of the present invention;

3 is a schematic structural diagram of a speech noise analysis system in an embodiment of the present invention;

FIG. 4 is a schematic structural diagram of an electronic device in an embodiment of the present invention.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments These are some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present invention.

The technical features involved in the different embodiments of the present invention described below can be combined with each other as long as there is no conflict with each other.

With the rapid development of the mobile Internet, online education has gradually replaced traditional education methods. At present, more and more teachers use instant messaging software to provide teaching guidance to students, which makes it more convenient to analyze the classroom situation intelligently. Noise is a factor that affects the quality of students' classroom learning, so it is necessary to detect noise to create a quiet environment for students to ensure the learning effect. However, at present, a large number of online teaching audio and video are produced every day. The manual analysis of the noise in each classroom requires a huge workload and the analysis results are highly subjective. Therefore, the objective and intelligent analysis of audio noise is particularly necessary.

At present, the indicators (such as signal-to-noise ratio, segmental signal-to-noise ratio, etc.) for objectively evaluating the noise situation have great limitations in application, that is, when measuring the noise situation of a teaching audio, it is necessary to have a speech that is strictly time-aligned with it. Reference audio with the exact same content, which is extremely difficult to obtain in teaching scenarios. Therefore, how to realize the noise evaluation in the non-reference situation needs to be solved urgently.

An embodiment of the present invention provides a voice noise analysis method, which can be applied to noise analysis of an online teaching platform. As shown in FIG. 1 , the voice noise analysis method mainly includes the following steps:

Step S101: Acquire the speech data to be analyzed. Specifically, the voice data to be analyzed is audio data containing noise, such as: teaching audio recorded on an online teaching platform or corresponding audio data extracted from a teaching video containing voice data. The acquisition method of the voice data to be analyzed may be directly downloading the audio data or extracting from a preset voice database to be analyzed, etc., and the present invention is not limited to this.

Step S102 : extracting noise audio segments that only contain noise from the speech data to be analyzed. Specifically, since the speech data to be analyzed that contains noise contains both normal speech and noise, in order to avoid evaluating the noise, it is necessary to refer to the audio, that is, the normal speech. Visually measure the size of the noise by extracting noise intensity indicators such as the volume or energy of the audio.

Step S103: Determine the noise intensity level corresponding to each noise audio segment based on the noise intensity index of each noise audio segment and the preset noise intensity classification level. Specifically, there is a large difference in the noise energy or sound volume of different noise audio clips, and each noise audio clip can be compared more intuitively by classifying each noise audio clip, which is convenient for subsequent analysis of the entire to-be-analyzed Noise level assessment of speech data,

Step S104: Determine the noise level evaluation result of the speech data to be analyzed according to the distribution of the noise intensity levels corresponding to each noise audio segment. Specifically, since there are many noise audio segments in a complete speech data to be analyzed, in order to improve the accuracy of noise evaluation of the entire speech data to be analyzed, the noise level evaluation is obtained by considering the distribution of noise intensity levels of all noise audio segments As a result, an objective noise assessment of the speech data to be analyzed is achieved.

Through the above steps S101 to S104, the speech noise analysis method provided by the embodiment of the present invention separately analyzes the noise intensity level of each noise audio segment by calculating the noise intensity index of the noise audio segment containing only noise, and then according to all noise The distribution of the noise intensity level of the audio segment determines the noise level evaluation result of the entire speech data to be analyzed, avoids the influence of normal speech in the speech data to be analyzed, and realizes the objective evaluation of the noise level of the speech data to be analyzed, and does not need to refer to audio, It has a wider range of applications and can accurately reflect the noise in various scenarios.

Specifically, in an embodiment, the above-mentioned step S102 specifically includes the following steps:

Step S201: Divide the speech data to be analyzed into a plurality of audio segments based on the total duration of the speech data to be analyzed and a preset extraction duration period. Specifically, the speech data to be analyzed is divided into several audio clips of equal length with relatively small duration according to the time axis of the total duration. The preset extraction duration period can be flexibly set according to the total duration and the accuracy requirements of noise analysis, for example, 1s , 3s, etc., the present invention is not limited to this.

Step S202: Convert each audio segment into an amplitude spectrum. Specifically, each audio segment is converted into an amplitude spectrum by performing framing, Fourier transform, and amplitude normalization operations on each audio segment.

Step S203: Input the amplitude spectrum corresponding to each audio segment into a preset noise classification model to obtain a probability corresponding to each audio segment that only contains noise. The preset noise classification model is a classification model established in advance. The input of the classification model is an audio clip, and the output is the probability that the audio clip contains only noise. After training the classification model with a large number of known audio clips owned.

In the embodiment of the present invention, as shown in Figure 2, the classification model uses mobilenet-v2 as the backbone network, and further obtains several deep features of the audio, and then aggregates these deep features to obtain the dense features of the audio and finally sends them to the classifier for processing. Classification. Among them, the backbone network mobilenet-v2 uses depthwise separable convolution instead of traditional convolution, and the reasoning speed is faster. It has been widely used in the industry and will not be introduced in depth here; in the feature aggregation stage, a more effective feature aggregation method NetVLAD Pooling is used. . Assuming that the deep features obtained by the backbone network are {x ₁ ,x ₂ ,…,x _T }, the intermediate output of NetVLAD Pooling is a K×D matrix V, where K represents the predefined number of clusters, and D represents the center of each cluster , then each row of matrix V is obtained by the following formula:

Among them, {w _k }, {b _k }, {c _k } are training parameters, which are trained together with the classification model. The matrix V is L2 regularized and spliced together is the feature of NetVLAD Pooling aggregation, and then sent to the fully connected layer for binary classification. The entire classification model is trained with a binary cross-entropy loss function as the target.

Step S204: Screen the noise audio clips containing only noise from the audio clips based on a preset probability threshold. Specifically, the probability of the audio segment obtained in the above step S203 is compared with the preset probability threshold, and if the probability value exceeds the threshold, it means that the audio segment only contains noise, otherwise the audio also contains non-noise such as human voice, and then All audio clips judged to contain only noise, namely noise audio clips, are retained, and other audio clips are discarded.

Specifically, in an embodiment, the above-mentioned step S103 specifically includes the following steps:

Step S301: Calculate the noise intensity index corresponding to each noise audio segment respectively. Specifically, the noise intensity index may be an index that can reflect the magnitude of the noise, such as noise energy or volume. In the embodiment of the present invention, the noise energy index is used, that is, the energy of the noise audio segment is calculated. Assuming that the noise audio segment is represented by a={a ₁ ,a ₂ ,...,a _N }, and N is the number of sample points contained in the audio, the energy of the audio is calculated as:

Among them, energy represents the energy of the audio, t represents the duration of the audio, N is the number of sample points contained in the audio, and a ₁ , a ₂ , ..., a _N represents the energy value of each sample point of the audio.

Step S302: Acquire the noise intensity index ranges corresponding to different noise intensity levels in the preset noise intensity classification levels. Specifically, in the embodiment of the present invention, the preset noise intensity classification levels include low-intensity noise levels, medium-intensity noise levels, and high-intensity noise levels as an example, and the division basis is the range of noise intensity indicators. Two high and low energy thresholds T _l and T _h are preset, and the energy less than the low threshold is low-intensity noise, the energy between the low threshold and the high threshold is medium-intensity noise, and the energy greater than the high threshold is classified as high-intensity noise.

Step S303: Determine the current noise intensity index range corresponding to the current noise audio segment according to the noise intensity index corresponding to the current noise audio segment. According to the relationship between the noise energy value calculated in the above step S301 and the two energy thresholds T _l and _Th in the above step S302 , the current noise intensity index range to which it belongs is determined.

Step S304: Determine the noise intensity level corresponding to the current noise intensity index range as the noise intensity level of the current noise audio segment. Specifically, assuming that the energy value corresponding to the current noise audio clip is A, and T _l <A<T _h , then the current noise intensity index range to which the noise audio clip belongs corresponds to the medium-intensity noise level, then the noise audio clip’s The noise level is determined as a medium-intensity noise level.

Specifically, in an embodiment, the above-mentioned step S104 specifically includes the following steps:

Step S401: Obtain the proportions of different noise intensity levels in each noise audio segment. Specifically, by calculating the proportion of the noise audio segments belonging to the low-intensity noise level in the total number of noise audio segments among the noise audio segments in the entire to-be-analyzed speech data, and the proportion and high-intensity corresponding to the noise audio segments of the medium-intensity noise level The scale corresponding to the noise level of the noisy audio segment.

Step S402: Determine the noise level evaluation result of the speech data to be analyzed according to the proportion of different noise intensity levels and the preset proportion evaluation index. Specifically, the preset ratio evaluation index can be set according to actual needs, for example, the noise intensity level with the largest proportion is used as the noise level evaluation result of the speech data to be analyzed, or it can also be set for the ratio of different noise intensity levels The weighted proportions are compared, and the noise intensity level with the largest proportion after weighting is used as the noise level evaluation result of the speech data to be analyzed, etc. The present invention is not limited to this.

In the embodiment of the present invention, in the case of paying more attention to the high-intensity noise affecting students' learning, in order to improve the sensitivity of the noise level evaluation result to the high-intensity noise, the high-intensity noise is obtained by synthesizing the noise level results of each noise audio segment The proportion of noise level, according to the relationship between the proportion of high-intensity noise level and the preset proportion of high-intensity noise level in the preset proportion evaluation index, to determine the noise level evaluation result of the speech data to be analyzed. When the proportion of high-intensity noise levels is less than the minimum value of the preset proportion of high-intensity noise levels in the preset proportion evaluation index, it is judged that the noise level evaluation result is low noise level; When the proportion of the preset high-intensity noise level in the proportion evaluation index is within the proportion of the preset high-intensity noise level, it is judged that the noise level evaluation result is a moderate noise level; when the proportion of the high-intensity noise level is greater than the preset high-intensity noise level in the preset proportion evaluation index When the ratio is the maximum value of the range, it is judged that the noise level evaluation result is high noise level. In practical applications, the preset high-intensity noise level ratio range can also be determined by setting two high and low thresholds _TL and _TH . If it is less than _TL , it means that the overall noise level of the speech data to be analyzed is low, and between T Between _L and _TH indicates that the overall noise level of the speech data to be analyzed is moderate, and greater than _TH indicates that the overall noise level of the speech data to be analyzed is high.

By performing the above steps, the speech noise analysis method provided by the embodiment of the present invention obtains the speech data to be analyzed; extracts noise audio segments containing only noise from the speech data to be analyzed; based on the noise intensity index of each noise audio segment and The noise intensity level is preset, and the noise intensity level corresponding to each noise audio segment is determined; according to the distribution of the noise intensity level corresponding to each noise audio segment, the noise level evaluation result of the speech data to be analyzed is determined. Therefore, the noise intensity level of each noise audio segment is separately analyzed by calculating the noise intensity index of the noise audio segment containing only noise, and then the noise level of the entire speech data to be analyzed is determined according to the distribution of the noise intensity levels of all noise audio segments. The evaluation result avoids the influence of normal speech in the speech data to be analyzed, realizes an objective evaluation of the noise level of the speech data to be analyzed, and does not require reference audio, has a wider application range, and can accurately reflect the noise in various scenarios.

An embodiment of the present invention also provides a speech noise analysis system, as shown in FIG. 3 , the speech noise analysis system includes:

The acquiring module 101 is used for acquiring the speech data to be analyzed. For details, please refer to the relevant description of step S101 in the above method embodiments, which will not be repeated here.

The noise extraction module 102 is configured to extract a noise audio segment containing only noise from the speech data to be analyzed. For details, refer to the relevant description of step S102 in the above method embodiments, which will not be repeated here.

The noise estimation module 103 is configured to determine the noise intensity level corresponding to each noise audio segment based on the noise intensity index of each noise audio segment and the preset noise intensity classification level. For details, please refer to the relevant description of step S103 in the above method embodiments, which will not be repeated here.

The noise statistics module 104 is configured to determine the noise level evaluation result of the speech data to be analyzed according to the distribution of the noise intensity levels corresponding to each noise audio segment. For details, refer to the relevant description of step S104 in the above method embodiments, and details are not repeated here.

Through the cooperation of the above components, the speech noise analysis system provided by the embodiment of the present invention obtains the speech data to be analyzed; extracts noise audio segments containing only noise from the speech data to be analyzed; The noise intensity index and the preset noise intensity classification level are used to determine the noise intensity level corresponding to each noise audio segment; the noise level evaluation result of the speech data to be analyzed is determined according to the distribution of the noise intensity level corresponding to each noise audio segment. Therefore, the noise intensity level of each noise audio segment is separately analyzed by calculating the noise intensity index of the noise audio segment containing only noise, and then the noise level of the entire speech data to be analyzed is determined according to the distribution of the noise intensity levels of all noise audio segments. The evaluation result avoids the influence of normal speech in the speech data to be analyzed, realizes an objective evaluation of the noise level of the speech data to be analyzed, and does not require reference audio, has a wider application range, and can accurately reflect the noise in various scenarios.

An electronic device is also provided according to an embodiment of the present invention. As shown in FIG. 4 , the electronic device may include a processor 901 and a memory 902, wherein the processor 901 and the memory 902 may be connected by a bus or in other ways. Connecting via a bus is an example.

The processor 901 may be a central processing unit (Central Processing Unit, CPU). The processor 901 may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or Other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components and other chips, or a combination of the above types of chips.

As a non-transitory computer-readable storage medium, the memory 902 can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as program instructions/modules corresponding to the methods in the method embodiments of the present invention. The processor 901 executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions and modules stored in the memory 902, ie, implements the methods in the above method embodiments.

The memory 902 may include a storage program area and a storage data area, wherein the storage program area may store an operating system and an application program required by at least one function; the storage data area may store data created by the processor 901 and the like. Additionally, memory 902 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 902 may optionally include memory located remotely from processor 901, which may be connected to processor 901 via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

One or more modules are stored in the memory 902, and when executed by the processor 901, perform the methods in the above method embodiments.

The specific details of the above electronic device can be understood by referring to the corresponding related descriptions and effects in the above method embodiments, and details are not repeated here.

Those skilled in the art can understand that the realization of all or part of the processes in the methods of the above embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and the program can be executed when the program is executed. , may include the flow of the above-mentioned method embodiments. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk drive (Hard Disk Drive). , abbreviation: HDD) or solid-state hard disk (Solid-StateDrive, SSD), etc.; the storage medium may also include a combination of the above-mentioned types of memories.

Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, various modifications and variations can be made by those skilled in the art without departing from the spirit and scope of the present invention, such modifications and variations falling within the scope of the appended claims within the limited range.

Claims (10)

1. A method for speech noise analysis, comprising:

acquiring voice data to be analyzed;

extracting a noise audio segment only containing noise from the voice data to be analyzed;

determining the noise intensity grade corresponding to each noise audio frequency segment based on the noise intensity index of each noise audio frequency segment and the preset noise intensity classification grade;

and determining a noise level evaluation result of the voice data to be analyzed according to the distribution condition of the noise intensity level corresponding to each noise audio segment.

2. The method according to claim 1, wherein the extracting noise audio segments containing only noise from the speech data to be analyzed comprises:

dividing the voice data to be analyzed into a plurality of audio segments based on the total time length of the voice data to be analyzed and a preset extraction time length period;

converting each audio clip into a magnitude spectrum;

inputting the amplitude spectrum corresponding to each audio clip into a preset noise classification model to obtain the probability of only containing noise corresponding to each audio clip;

and screening the noise audio clips only containing the noise from the audio clips based on a preset probability threshold.

3. The method of claim 1, wherein determining the noise intensity level corresponding to each noise audio segment based on the noise intensity indicator of each noise audio segment and a preset noise intensity classification level comprises:

respectively calculating the noise intensity index corresponding to each noise audio frequency segment;

acquiring noise intensity index ranges corresponding to different noise intensity levels in the preset noise intensity classification levels;

determining a current noise intensity index range corresponding to a current noise audio frequency segment according to a noise intensity index corresponding to the current noise audio frequency segment;

and determining the noise intensity level corresponding to the current noise intensity index range as the noise intensity level of the current noise audio frequency segment.

4. The method according to claim 3, wherein the determining the noise level of the speech data to be analyzed according to the distribution of the noise intensity level corresponding to each of the noise audio segments comprises:

obtaining the ratio of different noise intensity levels in each noise audio segment;

and determining a noise level evaluation result of the voice data to be analyzed according to the ratios of different noise intensity levels and preset ratio evaluation indexes.

5. The method of claim 4, wherein the noise strength level comprises: high intensity noise level, medium intensity noise level, and low intensity noise level.

6. The method according to claim 5, wherein the determining the noise level evaluation result of the speech data to be analyzed according to the ratios of different noise intensity levels and the preset ratio evaluation index comprises:

acquiring the ratio of the high-intensity noise level;

and determining a noise level evaluation result of the voice data to be analyzed according to the relation between the ratio of the high-intensity noise level and the ratio range of the preset high-intensity noise level in the preset ratio evaluation index.

7. The method of claim 6, wherein the noise level assessment result comprises: low, moderate and high noise levels, wherein,

when the ratio of the high-intensity noise level is smaller than the minimum value of the ratio range of the preset high-intensity noise level in the preset ratio evaluation index, judging that the noise level evaluation result is low in noise level;

when the proportion of the high-intensity noise level is within the preset proportion range of the high-intensity noise level in the preset proportion evaluation index, judging that the noise level evaluation result is that the noise level is moderate;

and when the ratio of the high-intensity noise level is larger than the maximum value of the ratio range of the preset high-intensity noise level in the preset ratio evaluation index, judging that the noise level evaluation result is that the noise level is high.

8. A speech noise analysis system, comprising:

the acquisition module is used for acquiring voice data to be analyzed;

the noise extraction module is used for extracting a noise audio segment only containing noise from the voice data to be analyzed;

the noise estimation module is used for determining the noise intensity grade corresponding to each noise audio frequency segment based on the noise intensity index of each noise audio frequency segment and the preset noise intensity classification grade;

and the noise statistical module is used for determining a noise level evaluation result of the voice data to be analyzed according to the distribution condition of the noise intensity level corresponding to each noise audio frequency segment.

9. An electronic device, comprising:

a memory and a processor communicatively coupled to each other, the memory having stored therein computer instructions, the processor executing the computer instructions to perform the method of any of claims 1-7.

10. A computer-readable storage medium having stored thereon computer instructions for causing a computer to thereby perform the method of any one of claims 1-7.

Images