JP2009147674A - Voice communication system and voice communication terminal - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a voice communication system by which a crew member can securely inform passengers of the minimum information if an emergency occurs in a transportation means even when a radio communication environment is bad. <P>SOLUTION: The voice communication system comprises: a voice communication server 101; a first voice communication terminal 102; and a second voice communication terminal 103, wherein the voice communication server divides voice data received from the first voice communication terminal into a plurality of voice packets, and transmits the packets to a second voice communication terminal through a communication line. The voice communication system has a voice recognition means 112 for recognizing the voice data received from the first voice communication terminal, and a keyword determination means 113 for determining whether or not a previously registered predetermined keyword is included in the voice data. When the keyword is included in the voice data, the voice communication server adds emergency information related to the keyword to all of the plurality of voice packets, and transmits the packets to the second voice communication terminal. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to wired and wireless voice communication systems that packetize and transmit voice, and in particular, it is possible to make emergency calls and notifications when an emergency occurs in a transportation means such as an airplane. The present invention relates to a voice communication system and a voice communication terminal.

  In a moving means such as an aircraft, when an emergency situation occurs during movement, it is strongly required to transmit necessary information promptly and reliably between crew members and between crew members and passengers. In recent years, packet communication using a wired LAN (registered trademark) LAN or a wireless LAN such as IEEE802.11a / b / g is becoming widespread.

  By the way, when transmitting an audio data signal in digital communication, transmission / reception is performed by converting it into a digital signal by pulse code modulation at a predetermined sampling frequency. In order to faithfully transmit audio, it is possible to set the sampling frequency high. However, the amount of data of the converted digital signal becomes too large, and the influence of compressing communication is great. For this reason, a voice communication method has been proposed in which voice data is recognized, converted into text data, and transmitted to reduce the transmission band. Specifically, an audio data packet transmission apparatus whose configuration is shown in a block diagram in FIG. 9 is known (see, for example, Patent Document 1).

  As shown in FIG. 9, in the voice data packet transmission device 902, voice characteristic component data is stored in advance in the transmission terminal 904, and this is added to the call setting message at the time of call setting, and is sent to the reception terminal 906. Send it. During a call, only the voice character component data is sent from the transmitting terminal 904 to the receiving terminal 906 as packet data, and the receiving terminal 906 performs voice from the characteristic component data and the character component data from the packet data. It becomes possible to synthesize. As a result, the voice character component data can be converted into text data with a small capacity, and the data can be easily compressed, so that the amount of transmission information can be significantly reduced. In addition to voice communication systems and devices that reduce the transmission bandwidth by performing voice recognition processing on voice data and transmitting it as text data, compression that changes the compression rate depending on the transmission status of the communication line There is also a proposal to reduce the transmission capacity by the method.

In addition, in communication that generally transmits and receives information by packetizing signals, including the above-mentioned voice data, a signal loss called packet loss occurs due to troubles such as communication line conditions and various equipment failures, Information may not be transmitted correctly due to noise superimposed on the packet signal. For this reason, a technology that prevents important information from being lost by transmitting signals related to important information to each of a plurality of packets and allowing other packets to be transmitted normally even if packet loss occurs in some signals. Has been proposed (see, for example, Patent Document 2).
JP-A-2-20148 JP 2004-48474 A

  For example, as disclosed in Patent Document 1, a voice data packet transmission device that recognizes voice data, converts it into text data, and transmits it, reduces the amount of data and suppresses adverse effects on the communication environment such as lines. It is possible. However, if the communication environment deteriorates and the packet of text data corresponding to the emergency voice is lost, the emergency information will no longer be transmitted.

  Also, as disclosed in Patent Document 2, in the method of performing communication / transmission by adding the important information signal as it is to a plurality of packets, the amount of communication data may increase more than necessary. When the radio wave conditions in the network become extremely poor, or when traffic increases abnormally even with wired communication, there is a problem that communication is impossible despite the urgency, and a solution has been desired.

  The present invention has been made in order to solve the above-described problems. When an emergency situation occurs, the minimum information is surely transmitted even when the wireless or wired communication environment is bad. It is an object of the present invention to provide a voice communication system and a voice communication terminal that can be used.

  To achieve the above object, a voice communication system of the present invention comprises a voice communication server, a first voice communication terminal, and a second voice communication terminal, and the voice communication server receives from the first voice communication terminal. A voice communication unit that divides the voice data into a plurality of voice packets and transmits the packets to a second voice communication terminal via a communication line, and recognizes voice data received from the first voice communication terminal And keyword determining means for determining whether or not a predetermined keyword registered in advance in the audio data is included. If the audio data includes a keyword, the audio communication server Emergency information related to the keyword is added to the packet and transmitted to the second voice communication terminal. As a result, even in situations where the communication environment is poor and packet loss occurs when an emergency situation occurs, the crew can ensure minimum information via the voice communication server from the first voice communication terminal. To the second voice communication terminal of the crew member or passenger.

  In the voice communication system of the present invention, the voice communication server further includes a communication environment measurement unit that measures a communication environment with the second voice communication terminal, and the voice communication server has a communication environment worse than a predetermined value. Emergency information may be added to all the plurality of voice packets and transmitted to the second voice communication terminal. As a result, the communication environment is measured, and the emergency information related to the keyword is added to the voice packet only when the communication environment is bad. Therefore, when the communication environment is good, an unnecessary processing load is not imposed on the voice communication server. . Furthermore, since the traffic on the communication path is not increased more than necessary, stable communication can be performed.

  In the audio communication system of the present invention, the first audio communication terminal is connected to the audio communication server via a specific radio channel of the radio communication line, and the audio communication server is connected to the second audio communication terminal via a radio channel different from the radio channel. You may communicate with. As a result, a wider-band wireless channel can be used from the first voice communication terminal (wireless terminal) used by the crew to the voice communication server, so that communication is ensured even in a poor communication environment. Is possible. Furthermore, since the first communication terminal is a wireless terminal, an emergency report can be made regardless of the movement position of the crew.

  In the voice communication system according to the present invention, when the voice communication server includes a plurality of types of keywords, the voice communication server sets a plurality of pieces of emergency information related to the keyword having the highest priority according to the preset priority. It may be added to all voice packets. As a result, an increase in traffic due to adding more keywords than necessary can be reduced.

  In the voice communication system of the present invention, the voice communication server further includes storage means for sequentially storing a predetermined number of keywords included in the voice data. When the number of keywords exceeds the predetermined number, The stored keyword is deleted, the most recently recognized keyword is stored in the storage means, and the emergency information related to the keyword stored in the storage means is added to all the voice packets at the end of the voice data Good. Thereby, even when many keywords are included in the voice data, the latest keyword can be transmitted reliably and efficiently.

  In the voice communication system of the present invention, the emergency information added to all the plurality of voice packets may be a keyword. Thus, the voice communication terminal that has received the voice packet can easily reproduce the keyword.

  In the voice communication system of the present invention, the emergency information added to all the voice packets may be an identification code corresponding to the keyword. As a result, since the identification code requires only a few bits of information, an increase in communication channel traffic due to the addition of keywords can be minimized.

  In the voice communication system of the present invention, the emergency information added to all the plurality of voice packets may be identification codes related to a plurality of keywords. Thereby, emergency information can be transmitted to a voice communication terminal more efficiently.

  In the voice communication system of the present invention, the second voice communication terminal includes emergency information extraction means for extracting emergency information from the received voice packet, and voice playback means for playing back voice based on the extracted emergency information. If the voice packet is received and the packet loss is larger than a predetermined value, the voice can be reproduced and output from the extracted emergency information. This makes it possible to make efficient emergency notifications by determining whether normal audio data is to be played or whether emergency information such as keywords is to be played repeatedly according to the packet loss situation at the time of reception. It becomes.

  The voice communication system of the present invention includes a voice communication server, a first voice communication terminal, and a second voice communication terminal. The first voice communication terminal divides voice data into a plurality of voice packets. A voice communication system for transmitting via a communication line to a second voice communication terminal via a voice communication server, wherein the first voice communication terminal includes voice recognition means for recognizing voice data, and voice data in advance. Keyword determination means for determining whether or not the registered predetermined keyword is included, and the first voice communication terminal adds the emergency information related to the keyword to all of the plurality of voice packets and sets the second It transmits to the voice communication terminal of this. Thereby, it is possible for a crew member who is traveling with the first voice communication terminal to quickly report emergency information to other crew members and passengers when an emergency occurs.

  The voice communication terminal of the present invention is a voice communication system in which the voice communication terminal divides voice data into a plurality of voice packets and transmits the voice data to other voice communication terminals via a communication line via the voice communication server. The voice recognition means for recognizing the voice data and the keyword determination means for judging whether or not a predetermined keyword registered in advance in the voice data is included, and all the voice packets are related to the keyword. It is characterized in that emergency information is added and transmitted to another voice communication terminal.

  The voice communication terminal according to the present invention further includes a communication environment measuring means for measuring a communication environment with the voice communication server, and adds emergency information to all the plurality of voice packets when the communication environment is worse than a predetermined value. Then, it may be transmitted to another voice communication terminal.

  According to the present invention, there is provided a voice communication system and a voice communication terminal capable of reliably transmitting minimum information even when a wireless or wired communication environment is bad when an emergency occurs. Can be provided.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

(Embodiment 1)
FIG. 1 is a block diagram schematically showing a voice communication system according to the present embodiment, FIG. 2 is a block diagram showing a schematic configuration of the voice communication system according to the present embodiment, and FIG. 3 is a voice communication system according to the present embodiment. FIG. 4 is a flowchart illustrating the overall operation procedure of the voice communication system according to the present embodiment, and FIG. 5 is a diagram illustrating packetization of the voice communication system according to the present embodiment. FIG. 6 is a flowchart for explaining the concept, and FIG. 6 is a flowchart showing the operation procedure of the voice communication system in the present embodiment during normal and emergency. In FIG. 1 and FIG. 2, the same components are denoted by the same reference numerals in order to avoid duplication.

  First, the configuration of the voice communication system according to Embodiment 1 of the present invention will be described with reference to FIG. 1, FIG. 2, and FIG.

  In the voice communication system according to the present embodiment, crew members talk to each other via a landline telephone or a mobile radio terminal being carried in a cabin of a transportation means represented by an airplane, or between a crew member and a passenger. It is configured to be able to do.

  As shown in FIG. 1, the voice communication system 100 includes a terminal 1 (master unit) 102 that is a first voice communication terminal capable of voice communication with a server 101 that is a voice communication server via a wireless communication line 105, and a second one. Terminal 2 (slave unit) 103 as a voice communication terminal, and a fixed telephone 104 as a first voice communication terminal capable of voice communication via the server 101 and a wired communication line 106. Calls and reports are made using the fixed telephone 104 and the terminal 1 (master unit) 102 by the crew, and the passenger using the terminal 2 (slave unit) 103 provided in the passenger seat. Hereinafter, the terminal 1 may be referred to as a parent device 102 and the terminal 2 may be referred to as a child device 103. Via the server 101, the parent device 102 and the child device 103 communicate with each other through different channels A and B through the wireless communication line 105.

  As shown in the upper part of FIG. 2, the server 101 to which the fixed telephone 104 is connected by the wired communication line 106 includes a packet receiving unit 110, a voice decoding unit 111, a voice recognition unit 112, a keyword (abbreviated as “KW” in the drawing). Determination unit 113, keyword dictionary unit 114, speech encoding unit 115, keyword encoding unit 116, speech packet generation unit 117, communication control unit 121, communication environment determination unit 122, packet reception unit 123, packet transmission unit 124, and A wireless antenna 125 is provided. Further, the parent device 102 and the child device 103 include a transmission unit 300 including a voice input unit 301, a voice encoding unit 302, a voice packet generation unit 303, and a packet transmission unit 304, a packet reception unit 401, and a keyword extraction unit 402. A receiving unit 400 including a keyword decoding unit 403, a speech decoding unit 404, and a speech output unit 405, a communication control unit 501, a built-in microphone 503, a built-in speaker 504, and a wireless antenna 502. The role and function of each component of the server 101 and each terminal will be described in the description of the operation of the voice communication system in the present embodiment.

  Next, the operation of the voice communication system in the present embodiment will be described below. The voice communication system according to the present embodiment has three types of operation modes, that is, a keyword registration mode at the time of initial setting, a normal call / notification operation mode when the wireless communication environment is good, and an emergency when the wireless communication environment is not good. It is configured to operate in the call / report operation mode. An outline of the operation flow in each operation mode is shown in FIG.

  First, the keyword registration mode at the time of initial setting will be described. In the initial setting, related keywords necessary for emergency calling / reporting are registered in the keyword dictionary unit 114 of the server 101. This keyword may be registered in advance in a ROM or the like, or may be registered by an actual crew member's voice using an external microphone (not shown). Examples of the keyword include “fire”, “emergency”, “seat belt wearing”, “oxygen mask wearing”, and the like.

  Next, the normal call / notification operation mode when the wireless communication environment serving as the second operation mode is favorable will be described. The communication environment determining unit 122 determines the communication environment of the radio wave received by the communication control unit 121 via the wireless antenna 125 of the server 101 via the wireless communication line 105. When it is determined that the wireless communication environment is good, the voice communication system of the present invention operates in the normal call / operation mode. In the normal call / operation mode, the crew member of the transportation means uses the fixed telephone 104 connected to the server 101 in the passenger room or the parent device 102 that is being carried by the crew member, and the other child device 102 that is being carried by the crew member or the child device in the passenger seat. Call / report to 103.

  First, a case will be described in which a fixed telephone 104 connected to the server 101 makes a call / report to the handset 103. In FIG. 2, when the crew member utters and inputs to the fixed telephone 104, the voice data is encoded and packetized and input to the packet receiver 110 of the server 101. Data is extracted from the received voice packet, and is decoded into voice data by the voice decoding unit 111. The voice data is sent to the keyword determination unit 113 after the voice recognition unit 112 recognizes the voice information. The keyword determination unit 113 determines whether or not the keyword is included in the received voice data in comparison with the emergency keyword registered in the keyword dictionary unit 114 in advance. The voice data and the keyword are encoded by the voice encoding unit 115 and the keyword encoding unit 116, respectively. After that, the packet is generated by the voice packet generation unit 117, but if the wireless communication environment is good, the keyword is ignored and only the voice data is packetized. The packetized audio data is sequentially transmitted to the packet transmission unit 124 and the communication control unit 121, and is wirelessly transmitted from the server 101 to the slave unit 103 via the wireless antenna 125. Voice packet data received by the wireless antenna 502 of the slave unit 103 is sent to the packet receiving unit 401 via the communication control unit 501, decoded by the voice decoding unit 404, amplified by the voice output unit 405, and then amplified by the slave unit 103. The signal is output from the built-in speaker 504, and a call / report is sent from the crew member to another crew member or passenger.

  On the other hand, a call from the passenger seat to the crew is performed by communication from the slave unit 103 to the fixed telephone 104 or the master unit 102 via the server 101. When a passenger inputs an utterance to the built-in microphone 503 of the child device 103, the voice input unit 301 converts the voice into an analog electric signal, and then the voice encoding unit 302 encodes it. Thereafter, the encoded voice data is packetized by the voice packet generation unit 303, and the packetized voice data is sent to the packet transmission unit 304 and the communication control unit 501, and is transmitted from the slave unit 103 via the wireless antenna 502. Wireless transmission is performed toward the server 101. Then, it is transmitted to the fixed telephone or the wireless master device via the server 101.

  Further, in a normal mode in which the wireless communication environment is good, when calling / reporting to the slave unit 103 using the master unit 102 instead of the fixed phone 104, the call / report from the crew member to the passenger is transmitted to the master unit 102 → Calls / reports from the passenger 101 to the crew can be performed in the route order of the server 101 → the slave unit 103 in the route order of the slave unit 103 → the server 101 → the master unit 102. The processing procedure of the operation in each component is omitted because there are many portions overlapping the above-described contents.

  Next, the emergency call / notification operation mode when the communication environment determination unit 122 of the server 101 determines that the wireless communication environment is not good, that is, the third operation mode will be described. In the emergency call / operation mode, wireless voice communication between the master unit 102 and the server 101 or the slave unit 103 and the server 101 becomes difficult. Therefore, the crew member of the transportation means uses the fixed telephone 104 connected to the server 101 in the cabin. Then, a call / report is made to the child machine 103 in the passenger seat.

  In FIG. 2, the process from when the crew member speaks to the fixed telephone 104 connected to the server 101 to when the spoken voice is input to the server 101 and input to the voice packet generation unit 117 is the second process described above. It is the same as the operation mode. In this mode, when a keyword is included in the voice data, the voice packet generation unit 117 adds the keyword encoded by the keyword encoding unit 116 to the voice data encoded by the voice encoding unit 115. Packetized. In addition, when voice data is divided into a plurality of packets, this keyword is added to all packets. This packetization process will be described in detail later.

  The packetized keyword-added voice data is sequentially transmitted to the packet transmission unit 124 and the communication control unit 121, and is wirelessly transmitted from the server 101 to the slave unit 103 via the wireless antenna 125. The keyword-added voice data packet received by the wireless antenna 502 of the handset 103 is sent to the packet receiving unit 401 via the communication control unit 501, and only the keyword is extracted by the keyword extracting unit 402 and sent to the keyword decoding unit 403. The other voice packet data is sent to the voice decoding unit 404, and a keyword or voice data is selected according to the packet reception state in the packet receiving unit 401, amplified by the voice output unit 405, and built-in speaker of the slave unit 103. The emergency call / report from the crew to passengers is made.

  In the emergency call / notification mode, the crew member can use the master unit 102 to connect with other crew members through a fixed phone or the passenger and the slave unit in addition to the fixed phone 104 connected to the server 101 by a wired communication line. An emergency call / report can also be made via 103. At this time, the voice data including the input keyword is transmitted from the base unit 102 to the server 101 by wireless voice communication by the same operation procedure as described above. Since the subsequent processing is the same as the emergency call / report processing using the fixed telephone 104 described above, description thereof is omitted to avoid duplication. However, at this time, the wireless voice communication with the base unit 102 via the server 101 uses a different band from the band of the wireless communication line 105 used for the wireless communication between the server 101 and the handset 103. It is desirable to perform wireless voice communication. Even if the server 101 and the slave unit (terminal 2) 103 cannot receive well by using another wireless communication line with a wide enough bandwidth exclusively for the crew, the master unit (terminal 1) 102 and the server 101 During this period, stable communication can be performed, and emergency information can be reliably transmitted from the parent device 102 to the server 101.

  The operation and process flow of the voice communication system according to the present embodiment will be described with reference to FIGS. 4, 5, and 6. The overall operation and process flow will be described with reference to FIG.

  In FIG. 4, when the voice communication system 100 is operated, it is first determined whether or not to initialize the system by executing keyword registration / update processing (step S10). When it is necessary to initialize, a process for initializing the voice communication system 100 is executed (step S11). When there is no need for initialization, the communication environment determination unit 122 provided in the server 101 of the voice communication system 100 uses the wireless communication line 105 between the server 101, the parent device 102, and the child device 103 used in the voice communication system 100. An environmental quality determination is performed (step S12). If it is determined that the wireless communication environment is good, normal call notification processing is performed (step S13), and if it is determined that the wireless communication environment is not good, the call and notification in the emergency call notification processing mode are executed. (Step S14). The details of the procedure of each of the normal call notification processing and the emergency call notification processing will be described later. After executing the normal call notification process and the emergency call notification process, it is determined whether or not the voice communication system 100 is to be continuously operated (step S15). When the voice communication system 100 is to be continuously operated, the process returns to step S12. The processes from step S12 to step S15 described above are repeated. When the continuous operation is not performed, the operation of the voice communication system 100 is stopped. The above is the outline of the overall operation and processing flow of the voice communication system in the present embodiment.

  Next, a method for packetizing voice information from the crew will be described with reference to FIG. 5, (a) is an analog voice signal waveform of voice uttered by a crew member, (b) is encoded voice data, (c) is packetized voice data, (d) is keyword-added voice packet data, (e ) Shows the data structure of each voice packet.

  An analog voice signal 701 including a keyword voice signal 702 uttered by a crew member is encoded into voice data 703, and the voice data 703 is divided into a plurality of packet data. In the present embodiment, as an example, the packet is divided into three packets, and the keyword voice signal 702 is included as the keyword 704 in the first voice packet data of the voice data 703. This voice data is subjected to voice recognition processing by the voice recognition unit 112, and only the keyword 704 is extracted by the keyword determination unit 113 and added to the head portion of all packet data. Finally, a header (H) including packet management information is added to the beginning of all packet data, and a CRC for error detection is added to the end, thereby forming a voice packet. As described above, since the keyword is added to all the voice data packets of the crew, even if the wireless environment is bad and packet loss occurs, only the keyword can be transmitted to the passenger's wireless terminal without fail. For example, even if the first and second packets are lost among the three packets in (d), the keyword can be restored if the third packet can be received.

  By the way, when voice data uttered by a crew member is packetized, separation of voice data becomes a problem. As this separation, for example, each time a crew member sets a certain period of time by detecting the absence of silence for a certain period of time, a predetermined time is set manually in advance. Or a method such as dividing by a call switching.

  FIG. 4 shows an outline of the overall operation and processing flow of the voice communication system 100. Details of the procedures of the normal call / notification process in step S13 and the emergency call / notification process in step S14 are shown in FIG. This will be described with reference to FIG.

  The crew member inputs voice to the fixed telephone 104 connected to the master unit 102 or the server 101 via a wired communication line, and starts processing of the voice communication system 100 (step S21). The server 101 receives the voice (step S22), executes voice recognition processing (step S23), and determines whether or not the voice data includes a keyword (step S24). If the keyword is not included, the voice data is packetized as it is (step S26), the packet data is transmitted from the server 101 to the terminal 1 (step S27), and the voice packet data is received by the slave unit (step S28). The voice is converted and output from the handset speaker (step S29). On the other hand, if the voice data includes a keyword, the communication environment determination unit 122 provided in the server 101 causes the wireless communication line 105 between the server 101, the parent device 102, and the child device 103 to be used in the voice communication system 100. Environmental quality is determined (step S25: equivalent to step S12 in FIG. 4). If it is determined that the wireless communication environment is good, the process proceeds to step S26, and the normal call notification process shown in step S13 in FIG. 4 is performed.

  Next, if it is determined in step S25 that the wireless communication environment is not good, the emergency call notification process shown in step S14 in FIG. 4 is performed. That is, a keyword is added to all voice packet data (step S30), the packet data is transmitted from the server 101 to the terminal 2 (slave unit) 103 (step S31), and the slave unit 103 receives the voice packet data (step S31). Step S32). In step S33, it is determined whether the received packet loss is large. If the received packet loss is smaller than a predetermined value, the voice packet data is converted into voice as usual and output from the handset speaker (step S35). On the other hand, if the received packet loss is larger than the predetermined value, the keyword is extracted by the slave unit, converted into voice, and repeatedly output from the speaker. Thereby, even when the wireless communication environment is bad, the keyword can be reliably transmitted to the passenger.

  In the above operation flow, the wireless communication environment determination process is performed after the voice recognition process. However, the present invention is not limited to this, and the order may be changed. That is, the wireless communication environment may be first determined, and the voice recognition process may be performed only when the wireless communication environment is not satisfactory. By doing so, it is possible to reduce the processing load on the server 101 when the wireless communication environment is good.

(Embodiment 2)
Next, a second embodiment of the present invention will be described. The difference between the first embodiment and the second embodiment is that the first embodiment first confirms the communication radio environment and adds a keyword to the voice data only when the environment is not good. In the second embodiment, A keyword is added to all voice data packets regardless of the communication environment. And the subunit | mobile_unit which received audio | voice data determines whether a keyword is output repeatedly, seeing the condition of packet loss. With such a configuration, it is possible to reliably transmit emergency information to the passenger even when the wireless environment changes suddenly or when the wireless environment is biased depending on the position of the passenger.

  FIG. 7 is a flowchart showing the operation of the voice communication system 100 in the present embodiment. The same processes as those in the first embodiment are denoted by the same reference numerals, and description thereof is omitted. As shown in FIG. 7, in the voice communication system 100 according to the present embodiment, the process for determining whether or not the wireless communication environment in the server 101 of the operation flow in the first embodiment is good is omitted. That is, the server 101 always adds keywords to all voice packet data regardless of whether the wireless communication environment is good or not.

  As described above, in the voice communication system according to the present embodiment, when packetizing voice input voice data, keywords are determined from voice recognized voice data, and keywords are added to all voice packets. Then, it is transmitted to the slave unit by wireless communication. As a result, even if packet loss occurs when the wireless communication environment is not good, the slave unit can extract keywords from several keyword-added voice packets that can be received and play the keyword voice. Emergency calls and reports can be made without losing information.

(Embodiment 3)
Next, the call system according to the third embodiment in which the parent unit of the voice communication terminal has functions such as voice recognition, keyword determination, keyword encoding, and keyword addition provided in the server 1 in the first and second embodiments will be described. To do.

  FIG. 8 is a block configuration diagram of base unit 202 of the voice communication terminal according to the present embodiment. 8, components having the same functions as those of base unit 102 in FIG. That is, the transmission unit of the base unit 202 includes a voice input unit 301, a voice recognition unit 310, a keyword determination unit 311, a keyword dictionary unit 312, a keyword encoding unit 313, a voice encoding unit 302, a voice packet generation unit 314, and packet transmission. Unit 304 and communication environment determination unit 315. Since the operation of the transmission unit of base unit 202 is the same as the operation at the time of transmission of server 101 in the second embodiment, description thereof will be omitted.

  In the present embodiment as well, as in the first embodiment, whether to add a keyword to a voice packet may be determined based on the communication state determined by the communication environment determination unit 315. A keyword may be added regardless of the communication state as in the second embodiment. In this way, the communication terminal side has the function of recognizing a keyword and transmitting the recognized keyword on a voice packet, so that when a crew member finds an emergency while moving, he / she goes to a fixed line. Since it is not necessary to make a call, it is possible to quickly respond to an emergency.

  As described above, according to the voice communication system and the voice communication terminal of the present invention, when an emergency such as a fire, a sudden illness, or an accident occurs while a moving body such as an aircraft is moving, it is wireless or wired. Even if the communication environment is poor, it is possible to reliably convey the minimum information between the crew members or between the crew members and the passengers, and it is possible to respond quickly.

  In the description of the above embodiment, when a keyword is recognized in an emergency, the keyword itself is added to all voice packets and transmitted. However, a specific identification code corresponding to the keyword is added. May be. Since the identification code requires only a very small amount of information such as several bits, an increase in traffic on the communication path due to the addition of keywords can be minimized. The correspondence between the keyword and the identification code is not necessarily one-to-one, and the related keyword may be associated with one identification code. For example, if a plurality of keywords such as “fire”, “smoke”, “hot”, etc. corresponding to a fire are associated with one identification code, additional information can be obtained even when a plurality of related keywords are included in the call. There is no unnecessary increase. When a keyword is sent with an identification code, the receiving side may prepare a conversion table for converting the identification code into a keyword or related emergency information and output it from the voice output unit.

  In the description of the above embodiment, the keyword is always output repeatedly when the packet loss is larger than the predetermined value on the handset 103 side. However, for example, the keyword was originally included in the headers of all packets. Information that can identify a packet of voice data may be added, and the keyword may be repeatedly output only when the packet is lost. By doing so, information other than the keyword can be transmitted to the passenger in an emergency, so that the passenger can grasp the situation in more detail.

  In the description of the above embodiment, the case where one keyword is included in the utterance from the crew member has been described, but two or more keywords may be included. In this case, processing for determining the importance of each keyword may be further added so that only the most important one is added to all packets. Furthermore, the keyword added to the voice packet is not limited to one type but may be plural. In this case, a memory area that primarily stores a predetermined number of recognized keywords may be set, and old keywords or less important keywords may be deleted when the memory area is full. By doing so, an increase in traffic due to adding more keywords than necessary can be reduced. Needless to say, what is stored in the memory area may be the above-described recognition code instead of the keyword.

  In the above embodiment, the keyword determination unit determines whether or not the keyword is included only by comparing the content with the keyword registered in the keyword dictionary unit in advance. May be added. By doing so, keywords may be registered in advance with the voice of the crew, and utterances other than those of the crew may be ignored. By doing in this way, even if a passenger etc. utters a keyword accidentally, it can be prevented from reacting and unnecessary confusion can be avoided.

  In the above embodiment, it has been described that a keyword is added to all voice packets. However, the keyword is not always added to all packets, but the ratio of packets to which keywords are added is changed depending on the state of the wireless communication environment. May be. Thereby, an efficient voice emergency call becomes possible.

  Furthermore, in the above-described embodiment, the server 101, the parent devices 102 and 202, and the child device 103 are described as being connected via a wireless communication line, but may be connected via a wired communication line. In a wired communication line, packet loss occurs depending on the traffic condition of the line and the surrounding noise environment. In this case as well, emergency information can be transmitted quickly and reliably.

  The voice communication system of the present invention is not limited to a transportation means such as an airplane, but is a voice communication system between the front of an accommodation facility such as a hotel or an inn and a guest room, or between a manager's room and an individual residence in an apartment house. Etc.

1 is a configuration diagram schematically showing a voice communication system according to a first embodiment of the present invention. 1 is a block diagram showing an outline of the configuration of a voice communication system according to Embodiment 1 of the present invention. The figure explaining the operation | movement in each operation mode of the component of the audio | voice communication system in Embodiment 1 of this invention. The flowchart which shows the whole operation | movement and processing procedure of the audio | voice communication system in Embodiment 1 of this invention. FIG. 4 is a diagram for explaining the concept of packetization of the voice communication system in the first embodiment of the present invention The flowchart which shows the operation | movement procedure in the normal time and emergency of the audio | voice communication system in Embodiment 1 of this invention. The flowchart which shows the operation | movement procedure in the normal time and emergency of the voice communication system in Embodiment 2 of this invention. The block block diagram of the main | base station of the voice communication terminal in Embodiment 3 of this invention The block diagram which shows the outline of the structure of the conventional voice communication system

Explanation of symbols

100 voice communication system 101 server (voice communication server)
102, 202 Terminal 1 (base unit: first voice communication terminal)
103 terminal 2 (slave unit: second voice communication terminal)
104 landline telephone (first voice communication terminal)
DESCRIPTION OF SYMBOLS 105 Wireless communication line 106 Wired communication line 110,123,401 Packet receiving part 111,404 Voice decoding part 112,310 Voice recognition part 113,311 Keyword determination part 114,312 Keyword dictionary part 115,302 Voice encoding part 116,313 Keyword encoding unit 117,303 Voice packet generation unit 121,501 Communication control unit 122,315 Communication environment determination unit 124,304 Packet transmission unit 125,502 Wireless antenna 300 Transmission unit 400 Reception unit 402 Keyword extraction unit 403 Keyword decoding unit 405 Audio output unit 503 Built-in microphone 504 Built-in speaker 902 Audio data packet transmission device 904 Transmitting terminal 906 Receiving terminal

Claims (12)

A voice communication server, a first voice communication terminal, and a second voice communication terminal;
The voice communication server is a voice communication system for dividing voice data received from the first voice communication terminal into a plurality of voice packets and transmitting the voice data to the second voice communication terminal via a communication line,
Voice recognition means for recognizing voice data received from the first voice communication terminal;
Keyword determination means for determining whether or not a predetermined keyword registered in advance in the audio data is included;
When the keyword is included in the voice data, the voice communication server adds emergency information related to the keyword to all of the plurality of voice packets and transmits the emergency information to the second voice communication terminal. A voice communication system. The voice communication server further comprises a communication environment measuring means for measuring a communication environment with the second voice communication terminal,
The voice communication server adds the emergency information to all of the plurality of voice packets and transmits the emergency information to the second voice communication terminal when the communication environment is worse than a predetermined value. Voice communication system. The first voice communication terminal is connected to the voice communication server via a specific radio channel of a radio communication line, and the voice communication server communicates with the second voice communication terminal via a radio channel different from the radio channel. The voice communication system according to claim 1 or 2, characterized by the above. When a plurality of types of keywords are included in the voice data, the voice communication server adds emergency information related to the highest priority keyword to all of the plurality of voice packets according to a preset priority order. The voice communication system according to any one of claims 1 to 3. The voice communication server further includes storage means for sequentially storing a predetermined number of keywords included in the voice data, and deletes the most recently stored keyword when the number of keywords exceeds the predetermined number. The most recently recognized keyword is stored in the storage means, and emergency information related to the keyword stored in the storage means is added to all of the plurality of voice packets at the end of the voice data. The voice communication system according to any one of claims 1 to 3. The voice communication system according to any one of claims 1 to 5, wherein the emergency information added to all the plurality of voice packets is a keyword. 6. The voice communication system according to claim 1, wherein the emergency information added to all of the plurality of voice packets is an identification code corresponding to a keyword. 6. The voice communication system according to claim 1, wherein emergency information added to all of the plurality of voice packets is an identification code related to a plurality of keywords. The second voice communication terminal includes emergency information extraction means for extracting the emergency information from the received voice packet, and voice playback means for playing back voice based on the extracted emergency information, and the voice packet The voice communication system according to any one of claims 1 to 8, wherein when the packet loss is larger than a predetermined value, the voice is reproduced and output from the extracted emergency information. . A voice communication server, a first voice communication terminal, and a second voice communication terminal;
The first voice communication terminal is a voice communication system that divides voice data into a plurality of voice packets and transmits the voice data to the second voice communication terminal via the communication line via the voice communication server,
The first voice communication terminal is
Voice recognition means for recognizing the voice data;
Keyword determination means for determining whether or not a predetermined keyword registered in advance in the audio data is included;
The first voice communication terminal adds emergency information related to the keyword to all of the plurality of voice packets and transmits the emergency information to the second voice communication terminal. In a voice communication system in which a voice communication terminal divides voice data into a plurality of voice packets and transmits the voice data to another voice communication terminal via a communication line via a voice communication server.
Voice recognition means for recognizing the voice data;
Keyword determination means for determining whether or not a predetermined keyword registered in advance in the audio data is included;
A voice communication terminal, wherein emergency information related to the keyword is added to all of the plurality of voice packets and transmitted to the other voice communication terminal. A communication environment measuring means for measuring a communication environment with the voice communication server;
The voice communication terminal according to claim 11, wherein when the communication environment is worse than a predetermined value, the emergency information is added to all of the plurality of voice packets and transmitted to the other voice communication terminal.

Images