CN112259111A - Raspberry pie-based emergency broadcasting method and system - Google Patents
Raspberry pie-based emergency broadcasting method and system Download PDFInfo
- Publication number
- CN112259111A CN112259111A CN202010986780.7A CN202010986780A CN112259111A CN 112259111 A CN112259111 A CN 112259111A CN 202010986780 A CN202010986780 A CN 202010986780A CN 112259111 A CN112259111 A CN 112259111A
- Authority
- CN
- China
- Prior art keywords
- sound data
- original
- sound
- data
- real
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 235000011034 Rubus glaucus Nutrition 0.000 title claims abstract description 33
- 235000009122 Rubus idaeus Nutrition 0.000 title claims abstract description 33
- 244000235659 Rubus idaeus Species 0.000 title description 4
- 240000007651 Rubus glaucus Species 0.000 claims abstract description 29
- 230000009467 reduction Effects 0.000 claims description 29
- 238000007781 pre-processing Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000009432 framing Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 abstract description 8
- 238000000354 decomposition reaction Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000005259 measurement Methods 0.000 description 3
- 208000032041 Hearing impaired Diseases 0.000 description 1
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 241000287127 Passeridae Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 208000016354 hearing loss disease Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 210000001835 viscera Anatomy 0.000 description 1
- 210000001260 vocal cord Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/42—Data-driven translation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/55—Rule-based translation
- G06F40/56—Natural language generation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04H—BROADCAST COMMUNICATION
- H04H20/00—Arrangements for broadcast or for distribution combined with broadcast
- H04H20/53—Arrangements specially adapted for specific applications, e.g. for traffic information or for mobile receivers
- H04H20/59—Arrangements specially adapted for specific applications, e.g. for traffic information or for mobile receivers for emergency or urgency
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/08—Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
- G10L13/086—Detection of language
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Quality & Reliability (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention relates to the technical field of raspberry groups, and discloses an emergency broadcasting method and system based on a raspberry group. Therefore, the problem that when the language familiar to passengers at an airport is the little language or the language or English unfamiliar to the country can be solved through the method, the broadcast voice can be timely broadcasted by the little language, and meanwhile, the communication between staff and the passengers is facilitated.
Description
Technical Field
The invention relates to the technical field of raspberry groups, in particular to an emergency broadcasting method and system based on a raspberry group.
Background
At present, the raspberry pie is a microcomputer and is designed for learning computer programming education. Although the size of the credit card is only the size of the credit card, the credit card can be called 'sparrow is small and has complete five internal organs', has very functions and is very popular with people.
At present, airport broadcasting languages are basically the native language and english, however, when the language familiar to passengers is the Chinese language or is not familiar to the country, passengers are liable to not understand the broadcasted voice information and miss the flight information, or when passengers need to seek help from broadcasters or other staff, communication and communication cannot be performed due to the lack of the language.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides a raspberry group-based emergency broadcasting method and system which can conveniently and quickly translate the Xiaozhong language and ensure that workers can communicate with passengers in the Xiaozhong language.
The purpose of the invention is realized by the following technical scheme:
an emergency broadcasting method based on raspberry pi comprises the following steps:
s101, receiving original sound data, comparing the original sound data with a preset sound threshold value, and generating preprocessed sound data;
s102, judging whether the preprocessed sound data has noise, if so, generating a noise reduction instruction, and performing noise reduction operation on the preprocessed sound data to generate processed sound data;
s103, analyzing the processed sound data to generate a pre-processing feature tag, and binding the pre-processing feature tag with the processed sound data;
s104, generating an original feature tag according to preset language information, binding the feature tag with the preset language information, and comparing the original feature tag with the preprocessed feature tag to generate real-time language data;
and S105, converting the processed sound data according to the real-time language data to generate real-time broadcast sound data, and sending the real-time broadcast sound data.
In one embodiment, in the step, according to preset language information, generating an original feature tag, binding the feature tag with the preset language information, and comparing the original feature tag with the preprocessed feature tag to generate real-time language data, the method specifically includes the following steps:
and comparing the original feature tag with the preprocessed feature tag according to a preset sound feature similarity value to generate a real-time sound feature similarity value, and if the real-time sound feature similarity value is greater than or equal to the preset sound feature similarity value, generating the real-time language data.
In one embodiment, the preset sound feature similarity value is 90%.
In one embodiment, the step of receiving the original sound data, comparing the original sound data with a preset sound threshold, and generating the preprocessed sound data specifically includes the following steps:
and generating a sound extraction instruction, and extracting the original sound data.
In one embodiment, the preset sound threshold range is 80Hz to 1200 Hz.
In one embodiment, after receiving the original sound data, comparing the original sound data with a preset sound threshold, and generating the pre-processed sound data, the method further includes the following steps:
and generating a fuzzy search instruction aiming at the processed sound data, executing the fuzzy search instruction, and generating the sound data to be confirmed.
In one embodiment, the step of determining whether the preprocessed sound data has noise, and if so, generating a noise reduction instruction, performing a noise reduction operation on the processed sound data, and generating the preprocessed sound data specifically includes the following steps:
performing framing operation on the processed sound data to generate sound data to be processed;
and performing calculation processing on the sound data to be processed to generate the processed sound data.
A raspberry pi based emergency broadcast system, comprising:
the acquisition module is used for receiving original sound data;
the noise reduction module is used for judging whether the original sound data has noise or not, if so, generating a noise reduction instruction, and performing noise reduction operation on the original sound data to generate preprocessed sound data;
the comparison module is used for comparing the original sound data with a preset sound threshold value to generate preprocessed sound data, and is also used for comparing the original characteristic label with the preprocessed characteristic label to generate real-time language data;
the binding module is used for analyzing the processed sound data, generating a preprocessed feature tag, binding the preprocessed feature tag with the processed sound data, generating an original feature tag, and binding the feature tag with the preset language information;
the analysis module is used for converting the processed sound data according to the real-time language data to generate real-time broadcast sound data; and
a sending module, configured to send the real-time broadcast sound data.
In one embodiment, the comparison module is further configured to compare the original feature tag with the preprocessed feature tag according to a preset sound feature similarity value to generate a real-time sound feature similarity value, and generate the real-time language data if the real-time sound feature similarity value is greater than or equal to the preset sound feature similarity value.
In one embodiment, the system further comprises an intercepting module, and the parsing module is configured to generate a sound extraction instruction and perform an extraction operation on the original sound data.
Compared with the prior art, the invention has the following advantages and beneficial effects:
the invention relates to an emergency broadcasting method and system based on a raspberry group, which are characterized in that original sound data of a passenger are obtained, processed sound data are generated through noise reduction processing, the processed sound data are analyzed, a preprocessing characteristic label related to the processed sound data is generated, and the preprocessing characteristic label is compared with an original characteristic label of preset language information in a database, so that the language matched with the original sound data of the passenger is obtained. Therefore, the problem that when the language familiar to passengers at an airport is the little language or the language or English unfamiliar to the country can be solved through the method, the broadcast voice can be timely broadcasted by the little language, and meanwhile, the communication between staff and the passengers is facilitated.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a flowchart illustrating the steps of a Raspberry pie-based emergency broadcast method according to an embodiment of the present invention;
FIG. 2 is a functional diagram of a Raspberry pie-based emergency broadcasting system according to an embodiment of the present invention
Detailed Description
To facilitate an understanding of the invention, the invention will now be described more fully with reference to the accompanying drawings. Preferred embodiments of the present invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like as used herein are for illustrative purposes only and do not represent the only embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
Referring to fig. 1, an emergency broadcasting method based on raspberry pi includes the following steps: s101, receiving original sound data, comparing the original sound data with a preset sound threshold value, and generating preprocessed sound data;
s102, judging whether noise exists in the preprocessed sound data, if so, generating a noise reduction instruction, and performing noise reduction operation on the preprocessed sound data to generate processed sound data;
s103, analyzing the processed sound data to generate a pre-processing feature tag, and binding the pre-processing feature tag with the processed sound data;
s104, generating an original characteristic tag according to preset language information, binding the characteristic tag with the preset language information, and comparing the original characteristic tag with a preprocessed characteristic tag to generate real-time language data;
and S105, converting the processed voice data according to the real-time language data to generate real-time broadcast voice data, and transmitting the real-time broadcast voice data.
For better describing the scheme of the raspberry pi based emergency broadcasting method and better understanding the concept of the raspberry pi based emergency broadcasting method, please refer to fig. 1, for example, step S101, receiving the original sound data, comparing the original sound data with a preset sound threshold, and generating the preprocessed sound data.
Step S102, judging whether noise exists in the preprocessed sound data, if so, generating a noise reduction instruction, and performing noise reduction operation on the preprocessed sound data to generate processed sound data;
specifically, in one embodiment, the preset sound threshold range is 80Hz to 1200 Hz.
More specifically, in an embodiment, the step of receiving the original sound data, comparing the original sound data with a preset sound threshold, and generating the preprocessed sound data specifically includes the following steps:
and generating a sound extraction instruction, and extracting the original sound data.
More specifically, in one embodiment, the step of determining whether noise exists in the pre-processed sound data, if so, generating a noise reduction command, performing a noise reduction operation on the pre-processed sound data, and generating the processed sound data specifically includes the following steps:
performing framing operation on the processed sound data to generate sound data to be processed;
and performing calculation processing on the sound data to be processed to generate processed sound data.
It should be noted that the broadcasting equipment is connected with the raspberry pie through an aux port, an AI translator and a voice database are arranged in the client, the client receives the voice of the help seeker, the AI translator compares and translates the voice of the help seeker and uploads the translated voice to the cloud server, and finally the raspberry pie broadcasts the translated voice through obtaining the cloud server. In combination with the embodiment, the AI translator firstly obtains the original sound data of the help seeker, and performs noise detection on the original sound data, human voice is generated by airflow vocal cords, and the average value cannot be achieved due to the fact that factors such as personal physique and language are greatly different, so that the threshold value of the AI translator can only be 80-1200 Hz. When the AI translator detects that the original sound data is higher than 80Hz or lower than 1200Hz, an extraction instruction is generated to intercept the sound data of 80Hz to 1200 Hz. Meanwhile, a noise reduction instruction is generated, frame processing is carried out on the preprocessed voice data, wherein IFFT can be adopted to calculate short-time Fourier transform, then a minimum tracking method or a time recursive average algorithm is utilized to estimate noise, voice data to be processed is generated, furthermore, calculation operation is carried out on the voice data to be processed to obtain a posterior signal-to-noise ratio, a prior signal-to-noise ratio is estimated by a maximum likelihood method according to the posterior signal-to-noise ratio, finally a gain function is calculated, and the gain function is multiplied with an input signal spectrum with noise to obtain a noise-removed voice signal. The above methods are all existing calculation methods.
Step S103, analyzing the processed sound data to generate a pre-processing feature tag, and binding the pre-processing feature tag with the processed sound data.
And step S104, generating an original characteristic label according to the preset language information, binding the characteristic label with the preset language information, and comparing the original characteristic label with the preprocessed characteristic label to generate real-time language data.
It should be noted that, the AI translator generates a plurality of preprocessed feature tags for the features of the processed sound data and binds the preprocessed feature tags to the processed sound data, and at the same time, the AI translator generates a plurality of original feature tags for the preset language information and binds the original feature tags to the preset language information. To better explain the above process, for example, if there is a lingering sound in the processed sound data, it may be roughly determined as russian, french, thai or spanish, and if there is a consonant, the search range may be locked to the chinese Tibetan language system; if vowel harmony occurs, the retrieval can be performed in the Altai language system, and therefore the translation practice of the AI translator can be accelerated accurately and quickly by using the method.
And step S105, converting the processed sound data according to the real-time language data to generate real-time broadcast sound data, and sending the real-time broadcast sound data.
It should be noted that the AI translator uploads the real-time language data to the cloud server, and meanwhile, the AI translator converts the processed sound data into real-time broadcast sound data according to the real-time language data, and the broadcasting device broadcasts the real-time broadcast sound data.
Further, in an embodiment, the generating of the original feature tag according to the preset language information in the step, binding the feature tag with the preset language information, and comparing the original feature tag with the preprocessed feature tag to generate the real-time language data specifically includes the following steps:
and comparing the original characteristic label with the preprocessed characteristic label according to a preset sound characteristic similarity value to generate a real-time sound characteristic similarity value, and if the real-time sound characteristic similarity value is greater than or equal to the preset sound characteristic similarity value, generating real-time language data.
Specifically, in one embodiment, the sound characteristic similarity value is preset to 90%.
It should be noted that, when the similarity value of the real-time sound features is greater than or equal to 90%, it is determined that the processed sound data is the same as a certain language in the preset language information in the speech database.
Further, in an embodiment, after the step of receiving the original sound data, comparing the original sound data with a preset sound threshold, and generating the preprocessed sound data, the method further includes the following steps:
and generating a fuzzy search instruction aiming at the processed sound data, executing the fuzzy search instruction, and generating the sound data to be confirmed.
It should be noted that the AI translator has another function of performing a fuzzy search on the processed sound data, that is, roughly searching out a plurality of languages according to the processed sound data, so as to allow the staff and the help-seeking staff to select.
According to the raspberry group-based emergency broadcasting method, the original sound data of a passenger is obtained, the processed sound data is generated through noise reduction processing, the processed sound data is analyzed, a preprocessing characteristic label related to the processed sound data is generated, and the preprocessing characteristic label is compared with the original characteristic label of the preset language information in the database, so that the language matched with the original sound data of the passenger is obtained. Therefore, the problem that when the language familiar to passengers at an airport is the little language or the language or English unfamiliar to the country can be solved through the method, the broadcast voice can be timely broadcasted by the little language, and meanwhile, the communication between staff and the passengers is facilitated.
Referring to fig. 2, a raspberry pi-based emergency broadcasting system 10 includes: the system comprises an acquisition module 100, a comparison module 200, a noise reduction module 300, a binding module 400, an analysis module 500 and a sending module 600.
Referring to fig. 2, the collecting module 100 is used for receiving original sound data; the comparison module 200 is configured to compare the original sound data with a preset sound threshold to generate preprocessed sound data, and the comparison module 200 is further configured to compare the original feature tag with the preprocessed feature tag to generate real-time language data; the noise reduction module 300 is configured to determine whether the original sound data has noise, and if so, generate a noise reduction instruction, perform noise reduction operation on the original sound data, and generate preprocessed sound data; the binding module 400 is configured to perform parsing operation on the processed sound data, generate a preprocessed feature tag, bind the preprocessed feature tag with the processed sound data, and the binding module 400 is further configured to generate an original feature tag, and bind the feature tag with preset language information; the analysis module 500 is configured to perform a conversion operation on the processed sound data according to the real-time language data to generate real-time broadcast sound data; the transmitting module 600 is used for transmitting real-time broadcast sound data.
Further, in an embodiment, the comparing module 200 is further configured to compare the original feature tag with the preprocessed feature tag according to a preset sound feature similarity value to generate a real-time sound feature similarity value, and generate real-time language data if the real-time sound feature similarity value is greater than or equal to the preset sound feature similarity value.
Further, in an embodiment, the raspberry pi-based emergency broadcasting system 10 further includes an intercepting module, and the intercepting module is configured to generate a sound extracting instruction and perform an extracting operation on the original sound data.
The emergency broadcasting system 10 based on the raspberry group generates processed sound data by obtaining original sound data of a passenger and performing noise reduction processing, analyzes the processed sound data, generates a pre-processing feature tag related to the processed sound data, compares the pre-processing feature tag with an original feature tag of preset language information in a database, and obtains a language matched with the original sound data of the passenger. Therefore, the problem that when the language familiar to passengers at an airport is the little language or the language or English unfamiliar to the country can be solved through the method, the broadcast voice can be timely broadcasted by the little language, and meanwhile, the communication between staff and the passengers is facilitated.
Referring to fig. 1, further, when the speaking speed of the passenger is faster or the standard of the language spoken by the passenger is different from the official standard, for example, step S102 specifically includes: s102a, generating a sound cutting instruction according to the processed sound data, executing the sound cutting instruction and generating a plurality of segmented sound data; s102b, generating a character decomposition command for each piece of voice data; s102c, generating a plurality of sound characteristic identifications, and respectively binding the sound characteristic identifications with the segmented sound data in a one-to-one correspondence manner; s102d, comparing the sound feature identifications with the original feature labels one by one, and generating sound data to be played. It should be noted that, when the speaking speed of the passenger is fast or the standard of the language spoken by the passenger is different from the official standard, the AI translator generates a corresponding voice cutting instruction for the processed voice data, performs segmentation processing on the whole processed voice data to generate a plurality of voice segments, then performs parsing operation on each voice segment through a character decomposition instruction to generate a plurality of voice feature identifiers, and finally compares the plurality of voice feature identifiers with the original feature tags one by one to confirm the language of the passenger. Therefore, the spoken language of the passenger with the fast speaking speed can be quickly translated through the method, so that communication is convenient.
Further, when the passengers in the airport have hearing impairment, and the staff in the field is unfamiliar with sign language, for example, after step S105, the method further comprises the following steps: s106, generating a distance measurement request, responding to the distance measurement request, generating a real-time distance value, comparing the real-time distance value with a preset distance threshold value, and generating a recording instruction; s107, generating real-time video data, and generating a character decomposition instruction to analyze the real-time video data; s108, comparing the real-time video data with preset sign language information in a cloud server to generate a plurality of initial sign language data; s109, comparing the real-time video data with a plurality of primary sign language data one by one to generate secondary sign language data; and S110, generating voice information according to the secondary sign language data and sending the voice information. It should be noted that, the AI translator is provided with a camera module inside, and when the passenger is a hearing impaired person, the staff can press a button to start recording the sign language of the passenger. Firstly, the camera module can carry out distance measurement operation, judge whether a passenger is in the range of a preset distance threshold value, and if not, turn on a light to remind; further, when the passenger is within the range of the preset distance threshold value, the camera module starts recording, generates a character decomposition instruction, analyzes the real-time video data, uploads the real-time video data to the cloud server, primarily compares the real-time video data with preset sign language information, and generates primary sign language data which is similar to sign language actions in the real-time video data; and further analyzing the real-time video data and the primary sign language data to obtain secondary sign language data with higher similarity, and generating corresponding voice information to play according to the meaning expressed by the secondary sign language data so as to facilitate the staff to understand the sign language of the passenger. Therefore, the mode can ensure that when the staff encounters a passenger with hearing failure, the sign language meaning represented by the passenger can be understood in time, so that the trouble of the passenger can be relieved as soon as possible. Meanwhile, the AI translator is more functional and diversified, and can be applied to more environments.
Compared with the prior art, the invention has the following advantages:
according to the raspberry group-based emergency broadcasting method and system, the original sound data of the passenger is obtained, the processed sound data is generated through noise reduction processing, the processed sound data is analyzed, the preprocessed feature tag related to the processed sound data is generated, and the preprocessed feature tag is compared with the original feature tag of the preset language information in the database, so that the language matched with the original sound data of the passenger is obtained. Therefore, the problem that when the language familiar to passengers at an airport is the little language or the language or English unfamiliar to the country can be solved through the method, the broadcast voice can be timely broadcasted by the little language, and meanwhile, the communication between staff and the passengers is facilitated.
The above embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An emergency broadcasting method based on a raspberry group is characterized by comprising the following steps:
receiving original sound data, comparing the original sound data with a preset sound threshold value, and generating preprocessed sound data;
judging whether the preprocessed sound data has noise, if so, generating a noise reduction instruction, and performing noise reduction operation on the preprocessed sound data to generate processed sound data;
analyzing the processed sound data to generate a pre-processing feature tag, and binding the pre-processing feature tag with the processed sound data;
generating an original characteristic tag according to preset language information, binding the characteristic tag with the preset language information, and comparing the original characteristic tag with the preprocessed characteristic tag to generate real-time language data;
and according to the real-time language data, converting the processed sound data to generate real-time broadcast sound data, and sending the real-time broadcast sound data.
2. The raspberry pi-based emergency broadcasting method according to claim 1, wherein in the step of generating an original feature tag according to preset language information, binding the feature tag with the preset language information, and comparing the original feature tag with the preprocessed feature tag to generate real-time language data, the method specifically comprises the following steps:
and comparing the original feature tag with the preprocessed feature tag according to a preset sound feature similarity value to generate a real-time sound feature similarity value, and if the real-time sound feature similarity value is greater than or equal to the preset sound feature similarity value, generating the real-time language data.
3. The raspberry pi based emergency broadcast method of claim 2, wherein said preset acoustic feature similarity value is 90%.
4. The raspberry pi-based emergency broadcasting method according to claim 1, wherein the step of receiving original sound data, comparing the original sound data with a preset sound threshold, and generating preprocessed sound data specifically comprises the following steps:
and generating a sound extraction instruction, and extracting the original sound data.
5. The raspberry pi based emergency broadcast method of claim 1, wherein the preset sound threshold range is 80Hz to 1200 Hz.
6. The raspberry pi based emergency broadcasting method of claim 1, wherein after receiving original sound data and comparing the original sound data with a preset sound threshold to generate pre-processed sound data, the method further comprises the following steps:
and generating a fuzzy search instruction aiming at the processed sound data, executing the fuzzy search instruction, and generating the sound data to be confirmed.
7. The raspberry pi based emergency broadcasting method of claim 1, wherein the step of determining whether the pre-processed sound data has noise, if yes, generating a noise reduction command, performing a noise reduction operation on the pre-processed sound data, and generating the processed sound data specifically comprises the following steps:
performing framing operation on the processed sound data to generate sound data to be processed;
and performing calculation processing on the sound data to be processed to generate the processed sound data.
8. An emergency broadcast system based on a raspberry pi, comprising:
the acquisition module is used for receiving original sound data;
the noise reduction module is used for judging whether the original sound data has noise or not, if so, generating a noise reduction instruction, and performing noise reduction operation on the original sound data to generate preprocessed sound data;
the comparison module is used for comparing the original sound data with a preset sound threshold value to generate preprocessed sound data, and is also used for comparing the original characteristic label with the preprocessed characteristic label to generate real-time language data;
the binding module is used for analyzing the processed sound data, generating a preprocessed feature tag, binding the preprocessed feature tag with the processed sound data, generating an original feature tag, and binding the feature tag with the preset language information;
the analysis module is used for converting the processed sound data according to the real-time language data to generate real-time broadcast sound data; and
a sending module, configured to send the real-time broadcast sound data.
9. The raspberry pi based emergency broadcast system of claim 8, wherein the comparison module is further configured to compare the original feature tag with the preprocessed feature tag according to a preset sound feature similarity value to generate a real-time sound feature similarity value, and if the real-time sound feature similarity value is greater than or equal to the preset sound feature similarity value, generate the real-time language data.
10. The raspberry pi based emergency broadcast system of claim 8, further comprising an intercepting module, wherein the parsing module is configured to generate a sound extraction command to perform an extraction operation on the original sound data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010986780.7A CN112259111A (en) | 2020-09-18 | 2020-09-18 | Raspberry pie-based emergency broadcasting method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010986780.7A CN112259111A (en) | 2020-09-18 | 2020-09-18 | Raspberry pie-based emergency broadcasting method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112259111A true CN112259111A (en) | 2021-01-22 |
Family
ID=74233028
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010986780.7A Pending CN112259111A (en) | 2020-09-18 | 2020-09-18 | Raspberry pie-based emergency broadcasting method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112259111A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102324995A (en) * | 2011-04-20 | 2012-01-18 | 铁道部运输局 | Speech broadcasting method and system |
| KR20120063582A (en) * | 2010-12-08 | 2012-06-18 | 엘지전자 주식회사 | System for setting language of broadcasting receiver and language setting apparatus and method thereof |
| CN106209285A (en) * | 2016-07-21 | 2016-12-07 | 北京合智创展科技有限责任公司 | Mobile set reduction public broadcast and information issuing system and method |
| CN106856091A (en) * | 2016-12-21 | 2017-06-16 | 北京智能管家科技有限公司 | The automatic broadcasting method and system of a kind of multi-language text |
| CN110970018A (en) * | 2018-09-28 | 2020-04-07 | 珠海格力电器股份有限公司 | Speech recognition method and device |
| CN210986436U (en) * | 2019-07-04 | 2020-07-10 | 合肥炬芯智能科技有限公司 | Meeting place broadcasting and receiving system based on Bluetooth broadcasting and transmitting equipment thereof |
-
2020
- 2020-09-18 CN CN202010986780.7A patent/CN112259111A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120063582A (en) * | 2010-12-08 | 2012-06-18 | 엘지전자 주식회사 | System for setting language of broadcasting receiver and language setting apparatus and method thereof |
| CN102324995A (en) * | 2011-04-20 | 2012-01-18 | 铁道部运输局 | Speech broadcasting method and system |
| CN106209285A (en) * | 2016-07-21 | 2016-12-07 | 北京合智创展科技有限责任公司 | Mobile set reduction public broadcast and information issuing system and method |
| CN106856091A (en) * | 2016-12-21 | 2017-06-16 | 北京智能管家科技有限公司 | The automatic broadcasting method and system of a kind of multi-language text |
| CN110970018A (en) * | 2018-09-28 | 2020-04-07 | 珠海格力电器股份有限公司 | Speech recognition method and device |
| CN210986436U (en) * | 2019-07-04 | 2020-07-10 | 合肥炬芯智能科技有限公司 | Meeting place broadcasting and receiving system based on Bluetooth broadcasting and transmitting equipment thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108428446B (en) | Speech recognition method and device | |
| US9230547B2 (en) | Metadata extraction of non-transcribed video and audio streams | |
| Alghowinem et al. | Cross-cultural depression recognition from vocal biomarkers. | |
| US6434520B1 (en) | System and method for indexing and querying audio archives | |
| US8775174B2 (en) | Method for indexing multimedia information | |
| KR20170034227A (en) | Apparatus and method for speech recognition, apparatus and method for learning transformation parameter | |
| US20220115002A1 (en) | Speech recognition method, speech recognition device, and electronic equipment | |
| CN112153397B (en) | Video processing method, device, server and storage medium | |
| JP2015212731A (en) | Acoustic event recognition device and program | |
| KR102192678B1 (en) | Apparatus and method for normalizing input data of acoustic model, speech recognition apparatus | |
| CN114996506A (en) | Corpus generation method and device, electronic equipment and computer-readable storage medium | |
| US20190103110A1 (en) | Information processing device, information processing method, and program | |
| CN113129895B (en) | Voice detection processing system | |
| CN114239610A (en) | Multi-language speech recognition and translation method and related system | |
| Birla | A robust unsupervised pattern discovery and clustering of speech signals | |
| CN115331670B (en) | Off-line voice remote controller for household appliances | |
| CN112259111A (en) | Raspberry pie-based emergency broadcasting method and system | |
| CN111048068B (en) | Voice wake-up method, device and system and electronic equipment | |
| Georgiladakis et al. | Root Cause Analysis of Miscommunication Hotspots in Spoken Dialogue Systems. | |
| CN113782005B (en) | Speech recognition method and device, storage medium and electronic equipment | |
| KR102429365B1 (en) | System and method for analyzing emotion of speech | |
| JP6344849B2 (en) | Video classifier learning device and program | |
| Kalantari et al. | Cross database training of audio-visual hidden Markov models for phone recognition | |
| Zubi et al. | Arabic Dialects System using Hidden Markov Models (HMMs) | |
| CN111276146A (en) | Teaching training system based on voice recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |