CN104766605A - Time synchronizing system and method for haulage motor recording device and LKJ - Google Patents
Time synchronizing system and method for haulage motor recording device and LKJ Download PDFInfo
- Publication number
- CN104766605A CN104766605A CN201510194350.0A CN201510194350A CN104766605A CN 104766605 A CN104766605 A CN 104766605A CN 201510194350 A CN201510194350 A CN 201510194350A CN 104766605 A CN104766605 A CN 104766605A
- Authority
- CN
- China
- Prior art keywords
- voice message
- voice
- signal
- message signal
- moment
- 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.)
- Granted
Links
Landscapes
- Electric Clocks (AREA)
Abstract
The invention relates to a time synchronizing system and method for a haulage motor recording device and an LKJ. The time synchronizing system comprises the steps that a voice signal input by the haulage motor recording device is received, and a voice prompt signal emitted by the LKJ is collected from the voice signal; endpoint detection and feature extraction are carried out on the input voice signal and the voice prompt signal; features of the voice prompt signal are trained, features of the input voice signal and a training module are matched and recognized, the voice prompt signal of the input voice signal is recognized, and a moment of the voice prompt signal in a recording record is recognized; finally, the moment of the voice prompt signal in the detected recording record is synchronized with a moment of the voice prompt signal in an LKJ operation record document, and then the time synchronization between the haulage motor recording device and the LKJ is achieved. The synchronization between the two devices is achieved in a voice signal treatment mode, the timing time and difficulty is greatly reduced on the basis of not adding the cost of a recording device.
Description
Technical field
The present invention relates to the clock synchronization system between a kind of locomotive recording device and LKJ supervising device and method, belong to voice process technology field.
Background technology
In order to strengthen trainman's standardized work consciousness, guarantee that motorcycle safety travels, each trainman can be equipped with locomotive recording device, calling respond, station-locomotive joint control and other voice handling situations in omnidistance record locomotive operational process.LKJ is train operation monitoring and recording device, and be domestic train overspeeding protection equipment, it can record train operating conditions, signalling arrangement situation and steward exactly and handle situation, and adopts two-node cluster hot backup redundancy of effort mode, serviceability more reliable; The screen display of device shows the information such as forward box situation, ruuning situation in modes such as figure, curve, words.
And LKJ is for while train speed control, the various kinds of vehicles running state information that acquisition and recording is relevant with safe train operation, and provide related voice prompting.According to the recorded message of recording device and LKJ log sheet, locomotive work personnel can judge that trainman is with or without operating against regulations.But in a practical situation, the time of locomotive recording device and the Time Inconsistency of LKJ, cause recorded message time and LKJ log sheet Time Inconsistency, and record length is generally several hours, locomotive work personnel were adjusted by manual the time of recording device, lost time especially.
And synchronous for what realize between two devices in prior art, or when adopting artificial school, or by means of GPS.For during artificial school, not only need a large amount of manpowers, and efficiency comparison is low, also may because there is error when human factor causes pair; For the mode by means of GPS, although it is synchronous to realize between two devices quickly and easily, synchronously greatly can be increased the cost of recording device by the mode increasing hardware.
Summary of the invention
The object of this invention is to provide the clock synchronization system between a kind of locomotive recording device and LKJ supervising device and method, when to adopt artificial school between current locomotive recording device and LKJ supervising device to solve, the time is long, the problem of inefficiency.
The present invention solves the problems of the technologies described above the clock synchronization system additionally provided between a kind of locomotive recording device and LKJ supervising device, this clock synchronization system comprises voice input module, voice message signal acquisition module, voice signal processing module, sound identification module and time synchronized module
An output terminal of described voice input module is directly connected with the input end of voice signal processing module, another output terminal of voice input module is connected with the input end of voice signal processing module by voice message signal acquisition module, for carrying out feature extraction respectively to the voice message signal in the voice signal in voice input module and voice message signal acquisition module, the output terminal of voice signal processing module is connected with the input end of sound identification module, for according to when in the feature identification input speech signal extracted, the voice message signal that comprises and this voice message signal are in sound recordings, the output terminal of sound identification module is connected with the input end of time synchronized module, moment for the voice message signal identified according to sound identification module carries out time synchronized to locomotive recording device and LKJ supervising device.
Described synchronization module is compared in the moment of the voice message signal identified with corresponding voice signal places all in LKJ supervising device log sheet, determine the moment that the mistiming is minimum, using this moment as in sound recordings device moment at voice message signal place of selecting, and correct the time in recording device with the determined mistiming, realize the time synchronized between recording device and LKJ supervising device.
Described voice signal processing module comprises end-point detection submodule and feature extraction submodule, described end-point detection submodule is for detecting starting point and the terminal of voice signal and voice message signal, and described feature extraction submodule is for extracting the feature of the voice signal after end-point detection submodule detects and voice message signal.
The voice message signal that the LKJ supervising device of described voice message signal acquisition module collection sends can be one, or multiple different voice message signals, also can be multiple not same voice cues in the same time.
For the voice message signal that voice message signal acquisition module gathers, if a voice message signal, described time synchronized module finds out correspondence in LKJ supervising device log sheet and moment immediate voice message signal, if multiple voice message signal, described time synchronized module is by calculating the mistiming in above-mentioned multiple voice message signal moment, find out closest with the voice message signal moment respectively in LKJ supervising device log sheet, and multiple voice message signals that the mistiming is equal with the mistiming of above-mentioned calculating, is replaced the moment of voice message signal corresponding in sound recordings the moment of the voice message signal in LKJ log sheet respectively, by the mistiming of the corresponding voice message signal of sound recordings and LKJ supervising device log sheet, revise the time in recording device, make the time of recording device and the time synchronized of LKJ supervising device.
Present invention also offers the method for synchronizing time between a kind of locomotive recording device and LKJ supervising device, this synchronous method comprises the following steps:
1) receive the voice signal of locomotive recording device input, and gather the voice message signal that wherein LKJ supervising device sends;
2) respectively feature extraction is carried out to the voice signal in locomotive recording device and voice message signal;
3) feature of the voice signal in the locomotive recording device extracted is mated with the feature of voice message signal, identify voice message signal in input speech signal and this voice message signal in locomotive recording device sound recordings when;
4) finally the moment at corresponding with LKJ supervising device log sheet for the voice message signal place moment in the sound recordings detected voice message signal place is carried out synchronously, to realize the time synchronized of locomotive recording device and LKJ.
Described step 4) in be synchronously that the moment of the voice message signal identified with corresponding voice signal places all in LKJ supervising device log sheet is compared, determine the moment that the mistiming is minimum, using this moment as in sound recordings device moment at voice indicator signal place of selecting, and correct the time in recording device with the determined mistiming, realize the time synchronized between locomotive recording device and LKJ supervising device.
Described step 2) in characteristic extraction procedure comprise end-point detection subprocess and feature extraction subprocess, described end-point detection subprocess is for detecting starting point and the terminal of voice signal and voice message signal, and described feature extraction subprocess is for extracting the feature of the voice signal after end-point detection submodule detects and voice message signal.
Described step 1) in gather the voice message signal that LKJ supervising device sends can be one, or multiple different voice message signal also can be multiple not same voice cues in the same time.
For step 1) in the voice message signal that gathers when being two or more, described step 4) by calculating the mistiming in above-mentioned two or more voice message signal moment, find out with the voice message signal moment closest in LKJ supervising device log sheet, and two or more voice message signals that the mistiming is equal with the mistiming of above-mentioned calculating, is replaced the moment of voice message signal corresponding in sound recordings the moment of the voice message signal in LKJ log sheet respectively, by the mistiming in the moment of the corresponding voice message signal of sound recordings and LKJ supervising device log sheet, revise the time in recording device, make the time of recording device and the time synchronized of LKJ supervising device.
The invention has the beneficial effects as follows: first the present invention gathers the voice message signal that LKJ supervising device sends from the voice signal receiving the input of locomotive recording device; Then end-point detection and feature extraction are carried out to the voice signal inputted and voice message signal; Train the feature of voice message signal, feature and the training pattern of input speech signal carry out mating and identifying, identify voice message signal in input speech signal and this voice message signal in sound-track engraving apparatus record when; Finally the voice message signal place moment in the sound recordings detected is carried out synchronous with the moment at this voice message signal place in LKJ log sheet, thus realize the time synchronized of locomotive recording device and LKJ.It is synchronous that the present invention realizes between two devices by the mode of Speech processing, the time when basis of cost not increasing recording device greatly reduces school and difficulty.
Accompanying drawing explanation
Fig. 1 is the structural representation of the clock synchronization system between locomotive recording device of the present invention and LKJ supervising device;
Fig. 2 is the process flow diagram of the method for synchronizing time between locomotive recording device of the present invention and LKJ supervising device.
Embodiment
Below in conjunction with accompanying drawing, the specific embodiment of the present invention is further described.
The embodiment of the clock synchronization system between a kind of locomotive recording device of the present invention and LKJ supervising device
Synchro system of the present invention is used for carrying out synchronously to the time between locomotive recording device and LKJ supervising device, concrete structure as shown in Figure 1, comprise voice input module, voice message signal acquisition module, voice signal processing module, sound identification module and time synchronized module, an output terminal of voice input module is directly connected with the input end of voice signal processing module, another output terminal of voice input module is connected with the input end of voice signal processing module by voice message signal acquisition module, for carrying out end-point detection and feature extraction to the voice message signal in the voice signal in voice input module and voice message signal acquisition module, the output terminal of speech processing module is connected with the input end of sound identification module, when for identifying that the voice message signal and this voice message signal that comprise in input speech signal are in sound recordings, the output terminal of sound identification module is connected with the input end of time synchronized module, moment for the voice message signal identified according to sound identification module carries out time synchronized to locomotive recording device and LKJ supervising device.Wherein the specific implementation process of modules is as follows:
Voice input module is for receiving the voice signal of locomotive recording device input, here voice signal comprises calling respond, station-locomotive joint control and other voice handling situations in locomotive operation process, also include the voice message signal that LKJ supervising device sends, the locomotive recording device in the present embodiment can adopt recording pen.
The voice message signal that voice message signal acquisition module sends for LKJ in the voice signal that gathers voice input module and receive.Voice message signal in the present embodiment is " green light passes through " voice signal that LKJ sends, also can be " reddish yellow lamp ", " two amber light " etc., as long as the voice message that LKJ sends, and the voice signal recorded of recording device is just passable, " green light passes through " voice signal sent using LKJ supervising device is here as voice message signal.
Voice signal processing module comprises end-point detection submodule and feature extraction submodule, wherein end-point detection submodule is for detecting starting point and the terminal of voice signal and voice message signal, and the modes such as short-time energy, short-time average zero-crossing rate, cepstrum feature, entropy, complicacy (KC complicacy and C0 complicacy) can be adopted to realize.This enforcement adopts short-time energy and short-time average zero-crossing rate, the detection method of short-time energy and short-time average zero-crossing rate is also referred to as double-threshold comparing method, it is on the basis of short-time energy detection method, add short-time average zero-crossing rate, energy and zero-crossing rate is utilized to detect as feature, when signal to noise ratio (S/N ratio) is not very low, the hypothesis of noise energy is greater than according to the energy of voice signal, by the energy of comparator input signal and the size of speech energy threshold value, can be distinguished voice segments and non-speech segment.Feature extraction submodule is for extracting the feature of the voice signal after above-mentioned end-point detection and voice message signal, MFCC (mel cepstrum coefficients), LPCC (linear prediction residue error) can be adopted to realize, that select in this enforcement is MFCC, utilize MFCC extraction voice messaging feature to belong to the technology of comparative maturity, no longer describe in detail here.
Sound identification module is used for carrying out machine learning training to the feature of the voice message signal that signal processing module obtains, the feature of the characteristic sum voice message signal of above-mentioned input speech signal is carried out mating and identifying, thus the voice message signal comprised in identification input speech signal, and when determining that this voice message signal is in sound recordings.
Time synchronized module is used for the moment of the voice message signal identified according to sound identification module, and the moment at the voice signal place corresponding with LKJ log sheet carries out synchronously.First detect in the present embodiment that the moment at the voice message signal place that the moment at voice message signal place in sound recordings is corresponding to LKJ log sheet compares, then finding out by calculating the moment that in sound recordings and LKJ log sheet, corresponding voice message signal time difference is minimum, finally utilizing the minimum time found poor and corresponding moment to make locomotive recording device and LKJ time synchronized.
The voice message that the two or more that the voice message signal that voice message signal acquisition module gathers also can send for LKJ supervising device is different, now time synchronized module is by calculating the mistiming in these two (or multiple) voice message signal moment, find out with these two (or multiple) voice message signal moment closest in LKJ log sheet, and two (or multiple) voice message signals that the mistiming is equal with the mistiming of above-mentioned calculating, is replaced the moment of voice message signal corresponding in sound recordings the moment of the voice message signal in LKJ log sheet respectively, simultaneously by the mistiming in two moment of the corresponding voice message signal of sound recordings and LKJ log sheet, revise the time in recording device, make the time of recording device and the time synchronized of LKJ supervising device.
The embodiment of the method for synchronizing time between a kind of locomotive recording device of the present invention and LKJ supervising device
As shown in Figure 2, the method for synchronizing time in the present embodiment carries out simultaneously match by speech recognition technology to the locomotive equipment time, from the voice signal receiving the input of locomotive recording device, first gather the voice message signal that LKJ supervising device sends; Then end-point detection and feature extraction are carried out to the voice signal inputted and voice message signal; Train the feature of voice message signal, feature and the training pattern of input speech signal carry out mating and identifying, identify voice message signal in input speech signal and this voice message signal in sound recordings when; Finally the voice message signal place moment in the sound recordings detected is carried out synchronous with the moment at this voice message signal place in LKJ log sheet, thus realize the time synchronized of locomotive recording device and LKJ.The detailed process of the method is as follows:
1. receive the voice signal of locomotive recording device input, locomotive recording device in the present embodiment can adopt recording pen, by calling respond, station-locomotive joint control and other voice handling situations in recording pen whole process record locomotive operational process, meanwhile, recording pen also records the voice message signal that LKJ supervising device sends.
2. from the voice signal of input, gather the voice message signal that LKJ supervising device sends.Voice message signal in the present embodiment is " green light passes through " voice signal that LKJ sends, and also can be " reddish yellow lamp ", " two amber light " etc., as long as the voice message that LKJ sends, and the voice signal that recording device is recorded is just passable." green light passes through " voice signal that this enforcement sends using LKJ supervising device is as voice message signal.
3. pair voice signal inputted and voice message signal carry out end-point detection and feature extraction.
End-point detection can adopt the modes such as short-time energy, short-time average zero-crossing rate, cepstrum feature, entropy, complicacy (KC complicacy and C0 complicacy) to realize.Short-time energy and short-time average zero-crossing rate are selected in this enforcement, the detection method of short-time energy and short-time average zero-crossing rate is also referred to as double-threshold comparing method, it is on the basis of short-time energy detection method, add short-time average zero-crossing rate, energy and zero-crossing rate is utilized to detect as feature, when signal to noise ratio (S/N ratio) is not very low, the hypothesis of noise energy is greater than according to the energy of voice signal, by the energy of comparator input signal and the size of speech energy threshold value, can be distinguished voice segments and non-speech segment.Feature extraction can adopt MFCC (mel cepstrum coefficients), LPCC (linear prediction residue error) to realize, that select in this enforcement is MFCC, utilize MFCC extraction voice messaging feature to belong to the technology of comparative maturity, no longer describe in detail here.
By detecting starting point and the terminal of each voice segments in " green light passes through " voice signal and input speech signal in the present embodiment, extract the phonetic feature of voice segments in " green light passes through " voice signal after end-point detection and input signal.
4. the feature of pair voice message signal carries out machine learning training, and feature and the training pattern of input speech signal carry out mating and identifying, identify the voice message signal in input speech signal, and when determining that this voice message signal is in sound recordings.In this enforcement, machine learning training is carried out to " green light by " phonic signal character extracted, feature and the training pattern of input speech signal carry out mating and identifying, identify the voice signal of all " green light passes through " in input speech signal, and determine the moment at each " green light passes through " voice signal place.
5., according to voice identification result, the voice message signal place moment in the sound recordings detected is carried out synchronous with the moment at this voice message signal place in LKJ log sheet.
The moment that the present embodiment to select arbitrarily in input speech signal all in moment at " green light a by " voice signal place and LKJ log sheet " green light by " voice signal place compares, find out minimum moment mistiming, using the moment at " green light passes through " voice signal place selected in sound recordings this moment, simultaneously by the mistiming in two moment of the corresponding voice signal of sound recordings and LKJ log sheet, correct the time in recording device, make the time synchronized of recording device and LKJ supervising device.
The voice message that the two or more that the voice message signal gathered also can send for LKJ supervising device is different, now by calculating the mistiming in these two (or multiple) voice message signal moment, find out with these two (or multiple) voice message signal moment closest in LKJ log sheet, and two (or multiple) voice message signals that the mistiming is equal with the mistiming of above-mentioned calculating, is replaced the moment of voice message signal corresponding in sound recordings the moment of the voice message signal in LKJ log sheet respectively, simultaneously by the mistiming in two moment of the corresponding voice message signal of sound recordings and LKJ log sheet, revise the time in recording device, make the time of recording device and the time synchronized of LKJ supervising device.
Compared to existing craft to method when locomotive recording device and LKJ supervising device school, utilize the clock synchronization system between locomotive recording device of the present invention and LKJ supervising device and method, only need by software simulating locomotive recording device and the automatic synchronization of LKJ time, the time when basis of cost not increasing recording device greatly reduces school and difficulty.
Claims (10)
1. the clock synchronization system between locomotive recording device and LKJ supervising device, is characterized in that, this clock synchronization system comprises voice input module, voice message signal acquisition module, voice signal processing module, sound identification module and time synchronized module,
An output terminal of described voice input module is directly connected with the input end of voice signal processing module, another output terminal of voice input module is connected with the input end of voice signal processing module by voice message signal acquisition module, for carrying out feature extraction respectively to the voice message signal in the voice signal in voice input module and voice message signal acquisition module, the output terminal of voice signal processing module is connected with the input end of sound identification module, for according to when in the feature identification input speech signal extracted, the voice message signal that comprises and this voice message signal are in sound recordings, the output terminal of sound identification module is connected with the input end of time synchronized module, moment for the voice message signal identified according to sound identification module carries out time synchronized to locomotive recording device and LKJ supervising device.
2. the clock synchronization system between locomotive recording device according to claim 1 and LKJ supervising device, it is characterized in that, described synchronization module is compared in the moment of the voice message signal identified with corresponding voice signal places all in LKJ supervising device log sheet, determine the moment that the mistiming is minimum, using this moment as in sound recordings device moment at voice message signal place of selecting, and correct the time in recording device with the determined mistiming, realize the time synchronized between recording device and LKJ supervising device.
3. the clock synchronization system between locomotive recording device according to claim 2 and LKJ supervising device, it is characterized in that, described voice signal processing module comprises end-point detection submodule and feature extraction submodule, described end-point detection submodule is for detecting starting point and the terminal of voice signal and voice message signal, and described feature extraction submodule is for extracting the feature of the voice signal after end-point detection submodule detects and voice message signal.
4. the clock synchronization system between locomotive recording device according to claim 3 and LKJ supervising device, it is characterized in that, the voice message signal that the LKJ supervising device of described voice message signal acquisition module collection sends can be one, or multiple different voice message signals also can be multiple not same voice cues in the same time.
5. the clock synchronization system between locomotive recording device according to claim 4 and LKJ supervising device, it is characterized in that, for the voice message signal that voice message signal acquisition module gathers, if a voice message signal, described time synchronized module finds out correspondence in LKJ supervising device log sheet and moment immediate voice message signal, if multiple voice message signal, described time synchronized module is by calculating the mistiming in above-mentioned multiple voice message signal moment, find out closest with the voice message signal moment respectively in LKJ supervising device log sheet, and multiple voice message signals that the mistiming is equal with the mistiming of above-mentioned calculating, is replaced the moment of voice message signal corresponding in sound recordings the moment of the voice message signal in LKJ log sheet respectively, by the mistiming of the corresponding voice message signal of sound recordings and LKJ supervising device log sheet, revise the time in recording device, make the time of recording device and the time synchronized of LKJ supervising device.
6. the method for synchronizing time between locomotive recording device and LKJ supervising device, is characterized in that, this synchronous method comprises the following steps:
1) receive the voice signal of locomotive recording device input, and gather the voice message signal that wherein LKJ supervising device sends;
2) respectively feature extraction is carried out to the voice signal in locomotive recording device and voice message signal;
3) feature of the voice signal in the locomotive recording device extracted is mated with the feature of voice message signal, identify voice message signal in input speech signal and this voice message signal in locomotive recording device sound recordings when;
4) finally the moment at corresponding with LKJ supervising device log sheet for the voice message signal place moment in the sound recordings detected voice message signal place is carried out synchronously, to realize the time synchronized of locomotive recording device and LKJ.
7. the method for synchronizing time between locomotive recording device according to claim 6 and LKJ supervising device, it is characterized in that, described step 4) in be synchronously that the moment of the voice message signal identified with corresponding voice signal places all in LKJ supervising device log sheet is compared, determine the moment that the mistiming is minimum, using this moment as in sound recordings device moment at voice indicator signal place of selecting, and correct the time in recording device with the determined mistiming, realize the time synchronized between locomotive recording device and LKJ supervising device.
8. the method for synchronizing time between locomotive recording device according to claim 7 and LKJ supervising device, it is characterized in that, described step 2) in characteristic extraction procedure comprise end-point detection subprocess and feature extraction subprocess, described end-point detection subprocess is for detecting starting point and the terminal of voice signal and voice message signal, and described feature extraction subprocess is for extracting the feature of the voice signal after end-point detection submodule detects and voice message signal.
9. the method for synchronizing time between locomotive recording device according to claim 8 and LKJ supervising device, it is characterized in that, described step 1) in gather the voice message signal that LKJ supervising device sends can be one, or multiple different voice message signals also can be multiple not same voice cues in the same time.
10. the method for synchronizing time between locomotive recording device according to claim 9 and LKJ supervising device, it is characterized in that, for step 1) in the voice message signal that gathers when being two or more, described step 4) by calculating the mistiming in above-mentioned two or more voice message signal moment, find out with the voice message signal moment closest in LKJ supervising device log sheet, and two or more voice message signals that the mistiming is equal with the mistiming of above-mentioned calculating, is replaced the moment of voice message signal corresponding in sound recordings the moment of the voice message signal in LKJ log sheet respectively, by the mistiming in the moment of the corresponding voice message signal of sound recordings and LKJ supervising device log sheet, revise the time in recording device, make the time of recording device and the time synchronized of LKJ supervising device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510194350.0A CN104766605B (en) | 2015-04-23 | 2015-04-23 | Clock synchronization system and method between a kind of locomotive recording device and LKJ supervising devices |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510194350.0A CN104766605B (en) | 2015-04-23 | 2015-04-23 | Clock synchronization system and method between a kind of locomotive recording device and LKJ supervising devices |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104766605A true CN104766605A (en) | 2015-07-08 |
CN104766605B CN104766605B (en) | 2018-03-27 |
Family
ID=53648389
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510194350.0A Active CN104766605B (en) | 2015-04-23 | 2015-04-23 | Clock synchronization system and method between a kind of locomotive recording device and LKJ supervising devices |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104766605B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105262976A (en) * | 2015-09-22 | 2016-01-20 | 武汉钢铁(集团)公司 | Method for controlling third-party recording and broadcasting source and multipoint controller (MCU) |
CN105741855A (en) * | 2016-02-03 | 2016-07-06 | 郑州畅想高科股份有限公司 | Steward calling and responding detection method based on audio analysis |
CN105843884A (en) * | 2016-03-21 | 2016-08-10 | 西安银石科技发展有限责任公司 | LKJ and audio-video synchronization based intelligent retrieval analysis method |
CN106601241A (en) * | 2016-12-26 | 2017-04-26 | 河南思维信息技术有限公司 | Automatic time correcting method for recording file |
CN106649745A (en) * | 2016-12-26 | 2017-05-10 | 河南思维信息技术有限公司 | Locomotive application comprehensive analysis method |
CN106657852A (en) * | 2016-12-21 | 2017-05-10 | 智威富(北京)科技有限公司 | Time synchronization method, device and system |
CN106813702A (en) * | 2015-12-02 | 2017-06-09 | 北京铁路信号有限公司 | A kind of test device and system of communications records device |
CN109545027A (en) * | 2018-12-24 | 2019-03-29 | 郑州畅想高科股份有限公司 | A kind of practical traning platform, crew's simulation training method and device |
CN113763988A (en) * | 2020-06-01 | 2021-12-07 | 中车株洲电力机车研究所有限公司 | Time synchronization method and system for locomotive cab monitoring information and LKJ monitoring information |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007047291A (en) * | 2005-08-08 | 2007-02-22 | Matsushita Electric Ind Co Ltd | Voice interpretation system and voice interpretation method |
CN200959133Y (en) * | 2006-06-23 | 2007-10-10 | 北京华韬致诚科技有限责任公司 | Apparatus for phonetic record and telecommunication of locomotive |
CN101186216A (en) * | 2006-11-17 | 2008-05-28 | 兰州交通大学 | Switching locomotive operation safety monitoring apparatus |
CN104123932A (en) * | 2014-07-29 | 2014-10-29 | 科大讯飞股份有限公司 | Voice conversion system and method |
-
2015
- 2015-04-23 CN CN201510194350.0A patent/CN104766605B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007047291A (en) * | 2005-08-08 | 2007-02-22 | Matsushita Electric Ind Co Ltd | Voice interpretation system and voice interpretation method |
CN200959133Y (en) * | 2006-06-23 | 2007-10-10 | 北京华韬致诚科技有限责任公司 | Apparatus for phonetic record and telecommunication of locomotive |
CN101186216A (en) * | 2006-11-17 | 2008-05-28 | 兰州交通大学 | Switching locomotive operation safety monitoring apparatus |
CN104123932A (en) * | 2014-07-29 | 2014-10-29 | 科大讯飞股份有限公司 | Voice conversion system and method |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105262976A (en) * | 2015-09-22 | 2016-01-20 | 武汉钢铁(集团)公司 | Method for controlling third-party recording and broadcasting source and multipoint controller (MCU) |
CN106813702A (en) * | 2015-12-02 | 2017-06-09 | 北京铁路信号有限公司 | A kind of test device and system of communications records device |
CN106813702B (en) * | 2015-12-02 | 2019-08-13 | 北京铁路信号有限公司 | A kind of test device and system of communications records device |
CN105741855A (en) * | 2016-02-03 | 2016-07-06 | 郑州畅想高科股份有限公司 | Steward calling and responding detection method based on audio analysis |
CN105843884A (en) * | 2016-03-21 | 2016-08-10 | 西安银石科技发展有限责任公司 | LKJ and audio-video synchronization based intelligent retrieval analysis method |
CN105843884B (en) * | 2016-03-21 | 2019-05-24 | 西安银石科技发展有限责任公司 | One kind being based on LKJ and its audio-visual synchronization intelligent retrieval analysis method |
CN106657852A (en) * | 2016-12-21 | 2017-05-10 | 智威富(北京)科技有限公司 | Time synchronization method, device and system |
WO2018113193A1 (en) * | 2016-12-21 | 2018-06-28 | 智威富(北京)科技有限公司 | Time synchronization method, device and system |
CN106601241A (en) * | 2016-12-26 | 2017-04-26 | 河南思维信息技术有限公司 | Automatic time correcting method for recording file |
CN106649745A (en) * | 2016-12-26 | 2017-05-10 | 河南思维信息技术有限公司 | Locomotive application comprehensive analysis method |
CN109545027A (en) * | 2018-12-24 | 2019-03-29 | 郑州畅想高科股份有限公司 | A kind of practical traning platform, crew's simulation training method and device |
CN113763988A (en) * | 2020-06-01 | 2021-12-07 | 中车株洲电力机车研究所有限公司 | Time synchronization method and system for locomotive cab monitoring information and LKJ monitoring information |
Also Published As
Publication number | Publication date |
---|---|
CN104766605B (en) | 2018-03-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104766605A (en) | Time synchronizing system and method for haulage motor recording device and LKJ | |
CN104914468B (en) | A kind of mine microquake signal P ripples initial time combines pick-up method | |
CN108428448A (en) | A kind of sound end detecting method and audio recognition method | |
CN110634493A (en) | Transformer state identification method, system and medium based on voiceprint image characteristics | |
CN105225493B (en) | A kind of vehicle identification method, device and auditing system | |
US20160322064A1 (en) | Method and apparatus for signal extraction of audio signal | |
CN101819770A (en) | System and method for detecting audio event | |
EP4270215A3 (en) | A system and a method for speech analysis | |
CN105609105A (en) | Speech recognition system and speech recognition method | |
CN113255556A (en) | Multi-mode voice endpoint detection method and device, vehicle-mounted terminal and storage medium | |
CN104834910A (en) | Locomotive attendant anti-cheating alcohol detection device and locomotive attendant anti-cheating alcohol detection method | |
CN105741855B (en) | Attendant call response detection method based on audio analysis | |
CN112929141B (en) | Unmanned aerial vehicle detection and recognition method and system based on graph signaling signal matching | |
CN103407464A (en) | Electronic locomotive brake building equipment based on video image recognition | |
CN108389281A (en) | A kind of unmanned plane cruising inspection system with voice record function | |
WO2020262841A3 (en) | Method for detecting integrity index of apparatus through control output signal | |
CN102355318A (en) | Method and device for recognizing clock reference type | |
CN106328165A (en) | Robot autologous sound source elimination system | |
CN104331680B (en) | Flowing water lamp-based beacon system for rapidly identifying | |
CN208848375U (en) | A kind of road test information acquisition system | |
EP3540601A3 (en) | Detection of wiring faults in serial bus connected components | |
CN104599497A (en) | Codebook model based vehicle overload monitoring method | |
CN117291222B (en) | Downhole drill rod counting method, monitoring equipment and storage medium | |
CN205864580U (en) | A kind of intelligent sound capturing system | |
CN107885174A (en) | A kind of workpiece neglected loading monitoring system and its detection method based on pressure sensitive |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
EXSB | Decision made by sipo to initiate substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |