Speech recognition method and device based on coal mine strong noise environment

Abstract

The invention provides a speech recognition method and device based on a coal mine strong noise environment. The speech recognition method based on the coal mine strong noise environment comprises the following steps: collecting sound information of an underground coal mine; performing noise separation on the sound information to generate a clean voice signal; performing enhancement processing on the clean voice signal to generate an enhanced voice signal; extracting voice features from the enhanced voice signal through Fourier transform; and recognizing the voice features, and outputting a recognition result. Coal mine underground voice is collected, clean voice is obtained through noise separation, and then sound quality is improved through enhancement processing. And extracting voice features by using Fourier transform, and finally identifying the features and outputting an accurate result. According to the process, underground complex noise is effectively filtered out, voice definition is enhanced, voice features are accurately extracted and recognized, the accuracy and reliability of coal mine underground voice recognition are remarkably improved, and a solid technical support is provided for safe communication and instruction transmission of coal mine operation.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and device for speech recognition in a strong noise environment in a coal mine. Background Art

[0002] With the development of artificial intelligence technology, speech recognition technology has made great progress and has begun to enter various fields such as home appliances, communications, automobiles, medical care, and industrial production. Speech recognition has made great progress, but most of the research focuses on speech recognition when multiple people speak at the same time without background noise interference, while research on environmental noise alone is relatively lacking. Especially in coal mines, where the environment is complex and the noise is high, it is easily affected by the external environment, resulting in insufficient speech recognition accuracy. Summary of the invention

[0003] The embodiments of the present application provide a method and device for speech recognition in a strong noise environment in a coal mine, thereby at least to a certain extent solving the problem of insufficient speech recognition accuracy.

[0004] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0005] According to one aspect of the present application, a speech recognition method based on a strong noise environment in a coal mine is provided, comprising: collecting sound information underground in the coal mine; performing noise separation on the sound information to generate a clean speech signal; performing enhancement processing on the clean speech signal to generate an enhanced speech signal; extracting speech features from the enhanced speech signal through Fourier transform; identifying the speech features and outputting a recognition result.

[0006] In the present application, based on the aforementioned scheme, the noise separation of the sound information to generate a clean speech signal includes: extracting the corresponding noisy speech signal according to the sound information; filtering based on the noisy speech signal and the estimated noise spectrum to generate a clean speech signal.

[0007] In the present application, based on the aforementioned scheme, the extraction of speech features from the enhanced speech signal through Fourier transform includes: performing Fourier transform on the enhanced speech signal in the time domain to generate a frequency domain signal; filtering the frequency domain signal to obtain energy distribution in different frequency bands; and performing signal transformation on the energy distribution to generate spectral features.

[0008] In the present application, based on the aforementioned scheme, the speech features are recognized and the recognition results are output, including: generating a feature parameter sequence according to the speech features; inputting the feature parameter sequence into a trained speech recognition model, and outputting the recognition results according to the learned mapping relationship.

[0009] In the present application, based on the above-mentioned scheme, the collecting of sound information in the coal mine includes: placing microphones at various locations in the coal mine, and using the microphones to collect the sound information in the coal mine.

[0010] In the present application, based on the aforementioned scheme, after collecting the sound information underground in the coal mine, it also includes: determining the starting point and the ending point of the sound information, removing the silent part, and removing the silent part.

[0011] In the present application, based on the aforementioned solution, it also includes: displaying the recognition result on a display screen.

[0012] According to one aspect of the present application, a speech recognition device based on a strong noise environment in a coal mine is provided, comprising:

[0013] A collection unit, used to collect sound information in coal mines;

[0014] A separation unit, used to separate the sound information from noise to generate a clean speech signal;

[0015] An enhancement unit, configured to perform enhancement processing on the clean speech signal to generate an enhanced speech signal;

[0016] An extraction unit, used for extracting speech features from the enhanced speech signal by Fourier transform;

[0017] The recognition unit is used to recognize the speech feature and output the recognition result.

[0018] In the present application, based on the aforementioned scheme, the noise separation of the sound information to generate a clean speech signal includes: extracting the corresponding noisy speech signal according to the sound information; filtering based on the noisy speech signal and the estimated noise spectrum to generate a clean speech signal.

[0019] In the present application, based on the aforementioned scheme, the extraction of speech features from the enhanced speech signal through Fourier transform includes: performing Fourier transform on the enhanced speech signal in the time domain to generate a frequency domain signal; filtering the frequency domain signal to obtain energy distribution in different frequency bands; and performing signal transformation on the energy distribution to generate spectral features.

[0020] In the present application, based on the aforementioned scheme, the speech features are recognized and the recognition results are output, including: generating a feature parameter sequence according to the speech features; inputting the feature parameter sequence into a trained speech recognition model, and outputting the recognition results according to the learned mapping relationship.

[0021] In the present application, based on the above-mentioned scheme, the collecting of sound information in the coal mine includes: placing microphones at various locations in the coal mine, and using the microphones to collect the sound information in the coal mine.

[0022] In the present application, based on the aforementioned scheme, after collecting the sound information underground in the coal mine, it also includes: determining the starting point and the ending point of the sound information, removing the silent part, and removing the silent part.

[0023] In the present application, based on the aforementioned solution, it also includes: displaying the recognition result on a display screen.

[0024] According to one aspect of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the speech recognition method based on the strong noise environment in a coal mine as described in the above embodiment is implemented.

[0025] According to one aspect of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the speech recognition method based on the strong noise environment in a coal mine as described in the above-mentioned embodiments.

[0026] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the speech recognition method based on a strong noise environment in a coal mine provided in the above-mentioned various optional implementations.

[0027] In the technical solution of the present application, sound information is collected underground in a coal mine; noise separation is performed on the sound information to generate a clean voice signal; enhancement processing is performed on the clean voice signal to generate an enhanced voice signal; voice features are extracted from the enhanced voice signal by Fourier transform; the voice features are identified and the recognition results are output. Sound is collected underground in a coal mine, clean voice is obtained by noise separation, and then enhanced to improve the sound quality. Voice features are extracted using Fourier transform, and finally the features are identified to output accurate results. This process effectively filters out complex noise underground, enhances voice clarity, accurately extracts and identifies voice features, significantly improves the accuracy and reliability of voice recognition underground in coal mines, and provides solid technical support for safe communication and command transmission in coal mine operations.

[0028] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0030] Figure 1 The flowchart of a method for speech recognition in a strong noise environment of a coal mine in one embodiment of the present application is schematically shown.

[0031] Figure 2 The flowchart of extracting speech features in one embodiment of the present application is schematically shown.

[0032] Figure 3 A schematic diagram of a speech recognition device in a strong noise environment of a coal mine in one embodiment of the present application is shown schematically.

[0033] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0034] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more comprehensive and complete and fully convey the concept of the example embodiments to those skilled in the art.

[0035] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0036] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0037] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0038] The implementation details of the technical solution of this application are described in detail below:

[0039] Figure 1 The flowchart of the speech recognition method based on the strong noise environment of the coal mine according to one embodiment of the present application is shown. Figure 1 As shown, the speech recognition method based on the strong noise environment of the coal mine includes at least steps S110 to S150, which are described in detail as follows:

[0040] In step S110, sound information in the coal mine is collected.

[0041] In one embodiment of the present application, collecting sound information underground in a coal mine helps monitor the underground working environment, personnel activities, and equipment operating status.

[0042] In one embodiment of the present application, microphones are deployed at various locations underground in a coal mine, and the microphones are used to collect sound information underground in the coal mine. Microphones with high explosion-proof, waterproof, and dustproof levels are selected to adapt to the harsh environment underground in a coal mine. At the same time, the microphone should have the characteristics of high sensitivity and low noise to accurately capture sound information. The underground environment of a coal mine is complex and there are many safety hazards, such as gas leakage, mechanical failure, and illegal operation of personnel. By deploying microphones to collect sound information, abnormal conditions underground can be monitored in real time, timely warnings can be issued, and mine safety and production efficiency can be improved.

[0043] The deployment locations include the following: microphones are deployed at key locations such as main tunnels, working faces, intersections, etc. to ensure comprehensive coverage of sound information; considering the characteristics of sound propagation, microphones should be installed at a certain height from the ground to avoid interference of ground reflection on sound collection; in noisy areas (such as near mechanical equipment), microphones with noise suppression functions are used or the number of microphones is increased to improve the signal-to-noise ratio. By deploying microphones at various locations underground in coal mines to collect sound information, real-time monitoring and early warning of the underground environment can be achieved. The system helps to improve mine safety, reduce accident risks, and improve production efficiency.

[0044] In one embodiment of the present application, after collecting the sound information in the coal mine, it also includes: determining the starting point and the ending point of the sound information, removing the silent part, and removing the silent part. By removing the silent part, the amount of data for subsequent voice processing can be reduced, thereby improving the efficiency of voice recognition or analysis. The silent part contains background noise or irrelevant information, and removing them can reduce the possibility of misrecognition. In a real-time system, accurately detecting the start and end of voice activity can optimize the utilization of data transmission and storage resources.

[0045] In step S120, the sound information is subjected to noise separation to generate a clean speech signal.

[0046] In one embodiment of the present application, performing noise separation on the sound information to generate a clean speech signal includes:

[0047] Extracting a corresponding noisy speech signal according to the sound information;

[0048] Based on the noisy speech signal and the estimated noise spectrum, filtering is performed to generate a clean speech signal.

[0049] In one embodiment of the present application, when estimating the noise spectrum, during the period when the voice signal is inactive, the sound signal collected is mainly noise. Therefore, the noise spectrum can be estimated by calculating the spectrum of the sound signal during these periods. In actual situations, the noise may not be static, but changes over time. Therefore, an adaptive algorithm can be used to estimate the noise spectrum in real time to more accurately reflect the noise characteristics of the current environment.

[0050] In one embodiment of the present application, a corresponding noisy speech signal is extracted according to the sound information; filtering is performed based on the noisy speech signal and the estimated noise spectrum to generate a clean speech signal S(k,n):

[0051] S(k,n)=max[Y(k,n)-α(k,n)·N(k),0]

[0052] Among them, S(k,n) represents the estimated clean speech signal, Y(k,n) represents the noisy speech signal, α(k,n) represents the adaptive over-subtraction coefficient, N(k) represents the estimated noise spectrum, k represents the frequency, and n represents the time. Through the above steps, the noisy speech signal can be extracted based on the sound information in the coal mine, and a clean speech signal can be generated through filtering, providing high-quality input data for subsequent sound processing and analysis tasks.

[0053] In step S130, the clean speech signal is enhanced to generate an enhanced speech signal.

[0054] In one embodiment of the present application, enhancing the clean speech signal is an important step to further improve the speech quality, intelligibility and hearing. In complex environments such as underground coal mines, due to factors such as noise, echo, and reverberation, even the clean speech signal obtained after preliminary filtering may have problems such as poor sound quality and insufficient clarity. Therefore, it is necessary to enhance the clean speech signal.

[0055] In one embodiment of the present application, the mutation points in the spectrum can be smoothed, high-frequency noise and sawtooth effects can be reduced, and the speech can be made smoother and more natural. The amplitude of the speech signal can also be adjusted to reduce the high amplitude part and increase the low amplitude part, thereby compressing the dynamic range and making the speech more balanced overall.

[0056] Optionally, after the initial filtering, a small amount of noise may still remain. The noise can be further reduced by further noise suppression algorithms, such as spectral subtraction, Wiener filtering, etc.

[0057] Through the above enhancement processing steps, the quality of clean speech signals can be further improved, making them clearer, more natural and easier to understand. This is of great significance for voice communication and speech recognition tasks in complex environments such as coal mines.

[0058] In step S140, speech features are extracted from the enhanced speech signal by Fourier transform.

[0059] like Figure 2 As shown, in one embodiment of the present application, extracting speech features from the enhanced speech signal by Fourier transform includes:

[0060] S210, performing Fourier transform on the enhanced speech signal in the time domain to generate a frequency domain signal;

[0061] S220, filtering the frequency domain signal to obtain energy distribution in different frequency bands;

[0062] S230, performing signal transformation on the energy distribution to generate frequency spectrum features.

[0063] Specifically, in the above process, after spectrum enhancement, the enhanced speech signal is subjected to Fourier transform to obtain its spectrum representation X(k):

[0064]

[0065] Among them, X(k) represents the spectrum representation, x(n) represents the enhanced speech signal in the time domain, N represents the signal length, n represents the signal sampling point, k represents the frequency index, and j is the imaginary unit. The Fourier transform algorithm is applied to convert the time domain signal into a frequency domain signal. The frequency domain signal represents the energy distribution of the speech signal at different frequencies.

[0066] Then, the spectrum signal is filtered through the filter bank to obtain the energy distribution M(k) of different frequency bands:

[0067]

[0068] Among them, H m (k) represents the frequency response of the mth filter, and P represents the total number of filters.

[0069] Finally, the output of the filter group is logarithmically transformed and discrete cosine transformed to obtain the speech feature MC(i):

[0070]

[0071] Among them, MC(i) represents the i-th speech feature coefficient, and K represents the filter dimension.

[0072] Through the above process, the enhanced speech signal is converted from the time domain to the frequency domain, and its energy distribution is analyzed to extract spectral features. These features provide valuable information for subsequent speech processing tasks, which helps to improve the accuracy of speech recognition and the quality of voice communication.

[0073] In step S150, the speech feature is recognized and a recognition result is output.

[0074] In one embodiment of the present application, the speech feature is recognized and the recognition result is output, including:

[0075] Generating a feature parameter sequence according to the speech feature;

[0076] The feature parameter sequence is input into the trained speech recognition model, and the recognition result is output according to the learned mapping relationship.

[0077] In one embodiment of the present application, the feature parameters usually need to be quantized to reduce the complexity of the data and improve the computational efficiency. The quantization step may include normalization, discretization or encoding of the feature parameters. The speech signal is a continuous time series, so the extracted feature parameters also need to be arranged in time order to form a feature parameter sequence.

[0078] Select a suitable speech recognition model and load the trained model parameters. Input the feature parameter sequence into the trained speech recognition model and output the recognition result according to the learned mapping relationship; the recognition result can be a probability distribution, indicating the probability of each word or phoneme appearing.

[0079] Through the above steps, a feature parameter sequence can be generated based on the extracted speech features, and a recognition result can be output using the trained speech recognition model. Then, the recognition result is post-processed to improve the accuracy and reliability of recognition.

[0080] In one embodiment of the present application, the speech feature is recognized, and after the recognition result is output, the recognition result is displayed on a display screen.

[0081] After the speech recognition system successfully recognizes the speech content, it will generate a recognition result in text format. This result may be a word, phrase, sentence, or a series of text information. According to actual needs, the recognition result is formatted. For example, the font size, color, style, or punctuation, line breaks, etc. are adjusted to improve readability and aesthetics.

[0082] Through the above steps, the recognition results generated by the voice recognition system can be clearly and accurately displayed on the display screen, thereby providing users with better usage experience and service quality.

[0083] The above process collects sound information from underground coal mines; performs noise separation on the sound information to generate a clean voice signal; performs enhancement processing on the clean voice signal to generate an enhanced voice signal; extracts voice features from the enhanced voice signal through Fourier transform; identifies the voice features and outputs the recognition result. Collect the sound from underground coal mines, separate the noise to obtain clean voice, and then enhance the voice quality. Use Fourier transform to extract voice features, and finally identify the features to output accurate results. This process effectively filters out complex noise underground, enhances voice clarity, accurately extracts and identifies voice features, significantly improves the accuracy and reliability of voice recognition in underground coal mines, and provides solid technical support for safe communication and command transmission in coal mine operations.

[0084] The following introduces an embodiment of the device of the present application, which can be used to execute the speech recognition method based on the strong noise environment of the coal mine in the above-mentioned embodiment of the present application. It can be understood that the device can be a computer program (including program code) running in a computer device, for example, the device is an application software; the device can be used to execute the corresponding steps in the method provided in the embodiment of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the speech recognition method based on the strong noise environment of the coal mine in the above-mentioned embodiment of the present application.

[0085] Figure 3 A block diagram of a speech recognition device in a strong noise environment of a coal mine according to an embodiment of the present application is shown.

[0086] Reference Figure 3As shown, according to an embodiment of the present application, a speech recognition device based on a strong noise environment in a coal mine includes:

[0087] A collection unit 310 is used to collect sound information in the coal mine;

[0088] A separation unit 320, configured to separate the sound information from noise to generate a clean speech signal;

[0089] The enhancement unit 330 is used to perform enhancement processing on the clean speech signal to generate an enhanced speech signal;

[0090] An extraction unit 340, configured to extract speech features from the enhanced speech signal by Fourier transform;

[0091] The recognition unit 350 is used to recognize the speech feature and output a recognition result.

[0092] In the present application, based on the aforementioned scheme, the noise separation of the sound information to generate a clean speech signal includes: extracting the corresponding noisy speech signal according to the sound information; filtering based on the noisy speech signal and the estimated noise spectrum to generate a clean speech signal.

[0093] In the present application, based on the aforementioned scheme, the extraction of speech features from the enhanced speech signal through Fourier transform includes: performing Fourier transform on the enhanced speech signal in the time domain to generate a frequency domain signal; filtering the frequency domain signal to obtain energy distribution in different frequency bands; and performing signal transformation on the energy distribution to generate spectral features.

[0094] In the present application, based on the aforementioned scheme, the speech features are recognized and the recognition results are output, including: generating a feature parameter sequence according to the speech features; inputting the feature parameter sequence into a trained speech recognition model, and outputting the recognition results according to the learned mapping relationship.

[0095] In the present application, based on the above-mentioned scheme, the collecting of sound information in the coal mine includes: placing microphones at various locations in the coal mine, and using the microphones to collect the sound information in the coal mine.

[0096] In the present application, based on the aforementioned scheme, after collecting the sound information underground in the coal mine, it also includes: determining the starting point and the ending point of the sound information, removing the silent part, and removing the silent part.

[0097] In the present application, based on the aforementioned solution, it also includes: displaying the recognition result on a display screen.

[0098] The above process collects sound information from underground coal mines; performs noise separation on the sound information to generate a clean voice signal; performs enhancement processing on the clean voice signal to generate an enhanced voice signal; extracts voice features from the enhanced voice signal through Fourier transform; identifies the voice features and outputs the recognition result. Collect the sound from underground coal mines, separate the noise to obtain clean voice, and then enhance the voice quality. Use Fourier transform to extract voice features, and finally identify the features to output accurate results. This process effectively filters out complex noise underground, enhances voice clarity, accurately extracts and identifies voice features, significantly improves the accuracy and reliability of voice recognition in underground coal mines, and provides solid technical support for safe communication and command transmission in coal mine operations.

[0099] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown.

[0100] It should be noted that the computer system 400 of the electronic device shown in the figure is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0101] The computer system 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage part 408 to the random access memory (RAM) 403, such as executing the method described in the above embodiment. In the RAM 403, various programs and data required for system operation are also stored. The CPU 401, the ROM 402 and the RAM 403 are connected to each other through the bus 404. The input / output (I / O) interface 405 is also connected to the bus 404.

[0102] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read therefrom is installed into the storage section 408 as needed.

[0103] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 409, and / or installed from a removable medium 411. When the computer program is executed by a central processing unit (CPU) 401, various functions defined in the system of the present application are executed.

[0104] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by an instruction execution system, device or device or used in combination with it. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0105] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0106] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0107] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above-mentioned various optional implementations.

[0108] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the method described in the above embodiment.

[0109] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0110] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0111] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.

[0112] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A speech recognition method based on a strong noise environment in a coal mine, characterized in that: include: Collect sound information in coal mines; Performing noise separation on the sound information to generate a clean speech signal; Performing enhancement processing on the clean speech signal to generate an enhanced speech signal; Extracting speech features from the enhanced speech signal by Fourier transform; The speech feature is recognized and a recognition result is output.

2. The method according to claim 1, characterized in that The sound information is subjected to noise separation to generate a clean speech signal, including: Extracting a corresponding noisy speech signal according to the sound information; Based on the noisy speech signal and the estimated noise spectrum, filtering is performed to generate a clean speech signal.

3. The method according to claim 1, characterized in that Extracting speech features from the enhanced speech signal by Fourier transform includes: Performing Fourier transform on the enhanced speech signal in the time domain to generate a frequency domain signal; Filtering the frequency domain signal to obtain energy distribution in different frequency bands; The energy distribution is subjected to signal transformation to generate a frequency spectrum feature.

4. The method according to claim 1, characterized in that: Recognizing the speech feature and outputting the recognition result includes: Generating a feature parameter sequence according to the speech feature; The feature parameter sequence is input into a trained speech recognition model, and a recognition result is output according to the learned mapping relationship.

5. The method according to claim 1, characterized in that Collect sound information in coal mines, including: Microphones are placed at various locations underground in the coal mine, and are used to collect sound information underground in the coal mine.

6. The method according to claim 1, characterized in that After collecting the sound information in the coal mine, it also includes: Determine the starting and ending points of the sound information and remove the silent parts.

7. The method according to claim 1, characterized in that Also includes: The recognition result is displayed on the display screen.

8. A speech recognition device based on a strong noise environment in a coal mine, characterized in that: include: A collection unit, used to collect sound information in coal mines; A separation unit, used to separate the sound information from noise to generate a clean speech signal; An enhancement unit, configured to perform enhancement processing on the clean speech signal to generate an enhanced speech signal; An extraction unit, configured to extract speech features from the enhanced speech signal by Fourier transform; The recognition unit is used to recognize the speech feature and output the recognition result.

9. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the speech recognition method based on a strong noise environment in a coal mine is implemented as described in any one of claims 1 to 7.

10. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, enables the one or more processors to implement the speech recognition method based on the strong noise environment of the coal mine as described in any one of claims 1 to 7.

Images