WO2024205155A1 - 음성 처리 장치와 이의 작동 방법 및 음성 처리 장치를 포함하는 차량 제어 시스템 - Google Patents
음성 처리 장치와 이의 작동 방법 및 음성 처리 장치를 포함하는 차량 제어 시스템 Download PDFInfo
- Publication number
- WO2024205155A1 WO2024205155A1 PCT/KR2024/003664 KR2024003664W WO2024205155A1 WO 2024205155 A1 WO2024205155 A1 WO 2024205155A1 KR 2024003664 W KR2024003664 W KR 2024003664W WO 2024205155 A1 WO2024205155 A1 WO 2024205155A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- passenger
- sound source
- vehicle
- voice
- source location
- 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.)
- Ceased
Links
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
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
-
- 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
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS
- H04R1/00—Details of transducers, loudspeakers or microphones
- H04R1/08—Mouthpieces; Microphones; Attachments therefor
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS
- H04R1/00—Details of transducers, loudspeakers or microphones
- H04R1/20—Arrangements for obtaining desired frequency or directional characteristics
- H04R1/32—Arrangements for obtaining desired frequency or directional characteristics for obtaining desired directional characteristic only
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS
- H04R1/00—Details of transducers, loudspeakers or microphones
- H04R1/20—Arrangements for obtaining desired frequency or directional characteristics
- H04R1/32—Arrangements for obtaining desired frequency or directional characteristics for obtaining desired directional characteristic only
- H04R1/323—Arrangements for obtaining desired frequency or directional characteristics for obtaining desired directional characteristic only for loudspeakers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS
- H04R3/00—Circuits for transducers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS
- H04R3/00—Circuits for transducers
- H04R3/005—Circuits for transducers for combining the signals of two or more microphones
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/12—Messaging; Mailboxes; Announcements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/90—Services for handling of emergency or hazardous situations, e.g. earthquake and tsunami warning systems [ETWS]
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W2040/089—Driver voice
Definitions
- the present invention relates to a voice processing device, an operating method thereof, and a vehicle control system including the voice processing device, and more specifically, to a voice processing device capable of outputting information corresponding to the occurrence of an emergency situation for a vehicle, an operating method thereof, and a vehicle control system including such a voice processing device.
- the e-call service system is a vehicle ICT-based service system that automatically transmits accident location and accident information to emergency rescue agencies and requests emergency rescue in the event of a vehicle collision or serious accident, enabling rapid rescue of people.
- the e-Call service system in cooperation with the satellite positioning system and the telecommunications company, transmits specific information such as the location of the accident, the type of vehicle, the direction of travel, and the number of seat belts used at the time of the accident to the nearest Public-Safety Answering Point (PSAP).
- PSAP Public-Safety Answering Point
- the PSAP interprets the information received and transmits the accident-related information to the rescue agency nearest to the accident site. Through this rapid contact system, the accident is quickly responded to and lifesaving is carried out.
- the present invention has been proposed in consideration of the above-mentioned conventional circumstances, and its purpose is to provide a voice processing device capable of outputting a conversation with a passenger when an emergency situation such as a vehicle collision occurs, a method of operating the same, and a vehicle control system including the voice processing device.
- a voice processing device installed in a vehicle, comprising: a microphone configured to generate a voice signal associated with the voice of a passenger in response to the voice of the passenger in the vehicle; a speaker configured to output a voice to the passenger in the vehicle; a memory; and a processor configured to load commands stored in the memory and perform one or more operations according to the execution of the commands; wherein, when the processor receives a collision occurrence signal from a vehicle controller configured to control an operation of the vehicle, the processor outputs a conversation attempt message to the passenger through the speaker, processes a response voice signal of the passenger in response to the conversation attempt message received from the microphone, generates sound source location information indicating a sound source location of the response voice signal, groups the response voice signal according to the sound source location information, and outputs the grouped response voice signal.
- the above memory stores a plurality of candidate conversation attempt messages
- the processor can output a first candidate conversation attempt message from among the plurality of candidate conversation attempt messages, and output a second candidate conversation attempt message subsequent to the first candidate conversation attempt message based on a response related to a response voice signal of the passenger to the first candidate conversation attempt message.
- the above memory stores a plurality of candidate conversation attempt messages
- the processor transmits the sound source location information to the vehicle controller, receives injury estimation information indicating the degree and part of injury of a passenger at the sound source location estimated based on the sound source location information and the sensing information of a sensor from the vehicle controller, and can output a candidate conversation attempt message corresponding to the injury estimation information among the plurality of candidate conversation attempt messages.
- the processor may analyze a response voice signal at the sound source location to determine a height and a tone of the response voice signal, determine whether the passenger at the sound source location is a child passenger based on the determined height and tone, and if determined to be a child passenger, output identification information indicating that the passenger at the sound source location is a child passenger.
- the above memory stores a plurality of candidate conversation attempt messages, and the processor can output a candidate conversation attempt message corresponding to the child passenger from among the plurality of candidate conversation attempt messages.
- the above processor can output the grouped response voice signal to an emergency rescue request device installed in the vehicle.
- the above processor can output the grouped response voice signal to the control server and output sound source location information corresponding to the grouped response voice signal to the emergency rescue request device installed in the vehicle.
- the above processor can receive vehicle location information from the vehicle controller, and output vehicle location information at the time of receiving the collision occurrence signal together with the grouped response voice signal.
- a method for operating a voice processing device is a method for operating a voice processing device installed in a vehicle, comprising: a step of outputting a conversation attempt message as a voice to a passenger of the vehicle when a collision occurrence signal is received from a vehicle controller configured to control an operation of the vehicle; a step of processing a response voice signal of the passenger to the conversation attempt message to generate sound source location information indicating a sound source location of the response voice signal; a step of grouping the response voice signals according to the sound source location information; and a step of outputting the grouped response voice signals.
- a vehicle control system includes: a vehicle controller configured to control the operation of a vehicle; and a voice processing device configured to output a conversation attempt message to a passenger of the vehicle when a collision occurrence signal is received from the vehicle controller, process a response voice signal of the passenger to the conversation attempt message to generate sound source location information indicating a sound source location of the response voice signal, group the response voice signals according to the sound source location information, and output the grouped response voice signals.
- the conversation content with passengers in the vehicle, information on the location of sound sources, and information on the location of the vehicle can be sent to the control server, so that the control server can more accurately determine the details of the accident (e.g., the degree of injury of the passenger, the injured area, etc.).
- a rescuer who is not at the scene of an accident can more accurately determine the situation inside a vehicle at the time of the accident, so that a rescue plan for handling the accident can be appropriately established and accident handling and emergency patient transport can be quickly carried out.
- FIG. 1 is a configuration diagram of a system including a vehicle employing a voice processing device according to an embodiment of the present invention and a control server networked with the vehicle.
- FIG. 2 is a drawing for explaining the operation of a voice processing device according to an embodiment of the present invention.
- Figure 3 is a diagram illustrating data transmitted from a vehicle to a control server when an accident occurs.
- Figure 4 is an internal configuration diagram of the voice processing device illustrated in Figure 1.
- Figure 5 is a flowchart for explaining the operation of a voice processing device according to an embodiment of the present invention.
- FIG. 1 is a configuration diagram of a system including a vehicle employing a voice processing device according to an embodiment of the present invention and a control server networked with the vehicle
- FIG. 2 is a diagram explaining the operation of a voice processing device according to an embodiment of the present invention
- FIG. 3 is a diagram exemplifying data transmitted from a vehicle to a control server when an accident occurs.
- a vehicle (10) may be defined as a means of transportation or transport that runs on roads, seaways, rails, and waterways, such as an automobile, train, motorcycle, ship, or aircraft.
- the vehicle (10) may be a concept that includes all of an internal combustion engine vehicle having an engine as a power source, a hybrid vehicle having an engine and an electric motor as power sources, and an electric vehicle having an electric motor as a power source.
- a vehicle (10) may be equipped with a sensor (20), a vehicle controller (30), a voice processing device (40), and an emergency rescue request device (50). Although not shown in the drawing, a steering device, a driving device, etc. may also be installed in the vehicle (10).
- the sensor (20) may include a plurality of sensors and may detect the status of the vehicle (10) to generate vehicle status information.
- the vehicle status information may include information about the current location of the vehicle (10), whether a collision has occurred, etc. If necessary, the vehicle status information may further include information about the vehicle speed of the vehicle (10), surrounding obstacles, etc.
- the sensor (20) can send vehicle status information to the vehicle controller (30).
- the vehicle status information can be an analog signal or a digital signal depending on the characteristics of the sensor.
- the vehicle controller (30) can include an AD converter (not shown) that converts the vehicle status information, which is an analog signal, into a digital signal if the received vehicle status information is an analog signal, and a digital input buffer (not shown) that buffers the vehicle status information, which is a digital signal, if the received vehicle status information is a digital signal.
- the sensor (20) may include a GPS sensor capable of sensing the current location of the vehicle (10) in real time, a collision sensor capable of detecting a collision between the vehicle (10) and another object (e.g., another vehicle, an obstacle, etc.), an obstacle sensor capable of detecting an obstacle around the vehicle (10), a vehicle speed sensor capable of detecting the vehicle speed of the vehicle (10), an impact sensor, an acceleration sensor, etc.
- a GPS sensor capable of sensing the current location of the vehicle (10) in real time
- a collision sensor capable of detecting a collision between the vehicle (10) and another object (e.g., another vehicle, an obstacle, etc.
- an obstacle sensor capable of detecting an obstacle around the vehicle (10
- a vehicle speed sensor capable of detecting the vehicle speed of the vehicle (10
- an impact sensor e.g., an acceleration sensor, etc.
- the senor (20) can detect internal/external information of the vehicle (10). Accordingly, additionally, the sensor (20) can sense temperature and humidity, longitudinal/lateral acceleration, etc., inside/outside the vehicle (10).
- the vehicle controller (30) may be configured to control the operation of the vehicle (10).
- the vehicle controller (30) can receive vehicle status information from the sensor (20) and can receive vehicle information through the OBD-II port of the vehicle (10).
- vehicle information may mean information about the status or abnormality of parts mounted or installed in the vehicle (10).
- the vehicle controller (30) When a vehicle collision occurs, the vehicle controller (30) receives vehicle status information (particularly, a collision occurrence signal) from the sensor (20). Accordingly, the vehicle controller (30) can send the received vehicle status information (particularly, a collision occurrence signal) to the voice processing device (40).
- the vehicle controller (30) may be configured to include, for example, an ECU (Electronic Control Unit).
- ECU Electronic Control Unit
- the vehicle controller (30) may receive sound source location information from the voice processing device (40) and receive various types of sensing information at the time of a vehicle collision from the sensor (20).
- the sound source location information may mean sound source location information indicating the sound source location of a passenger's response voice signal to a conversation attempt message.
- the various types of sensing information at the time of a vehicle collision may include, for example, vehicle speed, longitudinal/lateral acceleration values, impact values, etc.
- the vehicle controller (30) may estimate the degree and location of injury of the passenger at the corresponding sound source location based on the received sound source location information and the sensing information of the sensor.
- the vehicle controller (30) may store in advance information on the degree and location of injury of the passenger at each sound source location (i.e., boarding location) according to various collision conditions. Accordingly, when the vehicle controller (30) receives the sound source location information and the sensing information at the time of the vehicle collision, it can estimate by reading the information on the degree and location of injury of the passenger at the sound source location corresponding to the received sound source location information and the sensing information of the sensor. The vehicle controller (30) can transmit the injury estimation information indicating the estimated degree and location of injury of the passenger at the corresponding sound source location to the voice processing device (40). Accordingly, the voice processing device (40) can output a candidate conversation attempt message corresponding to the injury estimation information among the plurality of pre-stored candidate conversation attempt messages. In this way, the voice processing device (40) can obtain an answer (answer) about the degree and location of injury of the passenger more quickly and accurately.
- the vehicle controller (30) can estimate the degree of injury and the injured part of the passenger by the boarding position (i.e., the sound source position) based on various sensing information from the sensor (20) at the time of the vehicle collision.
- the various sensing information from the sensor (20) at the time of the vehicle collision can include, for example, vehicle speed, longitudinal/lateral acceleration values, impact values, etc.
- the vehicle controller (30) stores in advance information on the degree of injury and the injured part of the passenger by the sound source position (i.e., the boarding position) according to various collision conditions.
- the vehicle controller (30) when the vehicle controller (30) receives the sensing information at the time of the vehicle collision, it can estimate by reading the information on the degree of injury and the injured part of the passenger at the sound source position corresponding to the sensing information of the received sensor. Thereafter, the vehicle controller (30) receives the sound source position information of the passenger and the passenger's identity information (information indicating whether the passenger is an adult or a child) from the voice processing device (40).
- a child can mean a child from 1 year old to 6 years old.
- the vehicle controller (30) can predict the degree of injury and the injured area of the passenger for each sound source location (i.e., boarding location) based on the received information (i.e., sound source location information and identity information, or sound source location information and identity information and sensing information of the sensor (20)).
- the estimation of the degree of injury and the injured area of the passenger for each boarding location is simply based on the case where the passenger is an adult, and may be somewhat inaccurate if the passenger is a child.
- the prediction of the degree of injury and the injured area of the passenger for each boarding location is based on the consideration of both adult and child passengers, and predicts the degree of injury and the injured area of the passenger depending on whether the passenger is an adult or a child.
- the vehicle controller (30) can transmit injury prediction information indicating the predicted degree of injury and the injured area of the passenger for each sound source location (i.e., boarding location) to the voice processing device (40).
- the voice processing device (40) can receive injury prediction information and output a conversation attempt message corresponding to the injury prediction information as a voice.
- the voice processing device (40) can output a conversation attempt message corresponding to injury prediction information for a child passenger as a voice, answers (answers) regarding the degree and location of injury can be obtained more quickly and accurately for not only adult passengers but also child passengers.
- the voice processing device (40) can generate a voice signal associated with the voice of each passenger in the vehicle (10) in response to the voice of each passenger.
- the voice signal is a signal associated with voices spoken during a specific period of time, and may be a signal representing the voice of each of a plurality of passengers.
- the voice processing device (40) can recognize the voices of passengers separately for each passenger. When multiple passengers speak simultaneously, the voice includes the voices of all passengers who spoke. In order to accurately process the voices of each passenger, it is necessary to separate the voices of each passenger from the voices that include the voices of all passengers.
- a voice processing device (40) can extract (or generate) a separated voice signal associated with each of the voices of the passengers from the voice signal by determining the sound source location of each of the voices of the passengers from the voice signal associated with the voices of multiple passengers and performing sound source separation based on the sound source location.
- the voice processing device (40) can generate a separated voice signal associated with the voice of each sound source location based on the sound source location of the voices (i.e., which may be the boarding location of the passengers).
- the voice processing device (40) can classify components of the voice signal by sound source location and generate a separated voice signal associated with the voice spoken at each sound source location using the classified components corresponding to each sound source location.
- the voice processing device (40) can generate a first separated voice signal associated with the voice of the first passenger spoken at the first sound source location based on the voice signal.
- the first separated voice signal may have the highest correlation with the voice of the first passenger among the voices of the passengers. In other words, the proportion of the voice component of the first passenger among the voice components included in the first separated voice signal may be the highest.
- the voice processing device (40) may determine the sound source location of each voice of the passengers by using the time delay (or phase delay) between the voice signals associated with the voices of the passengers in the vehicle (10), and generate a separate voice signal corresponding only to the sound source at the specific location. For example, the voice processing device (40) may generate a separate voice signal associated with a voice spoken at a specific location (or direction). Accordingly, the voice processing device (40) may generate a separate voice signal associated with the voice of each passenger. Through the operation to generate such a separate voice signal, the voice processing device (40) may sufficiently generate a response voice signal of the passenger at a specific sound source location for a conversation attempt message and sound source location information indicating the sound source location of the response voice signal.
- the first passenger (SPK1) may be located in a front row left area (FL) of the vehicle (10)
- the second passenger (SPK2) may be located in a front row right area (FR) of the vehicle (10)
- the third passenger (SPK3) may be located in a rear left area (BL) of the vehicle (10)
- the fourth passenger (SPK4) may be located in a rear right area (BR) of the vehicle (10), but embodiments of the present invention are not limited thereto.
- the speakers (S1 to S4) may output voices corresponding to voice signals.
- the voice processing device (40) can generate a voice signal associated with the voice of the first to fourth passengers (SPK1 to SPK4) in response to each of the voices of the first to fourth passengers (SPK1 to SPK4).
- the voice signal is a signal associated with voices uttered during a specific time, and may be a signal representing the voices of a plurality of passengers.
- the voice processing device (40) determines the sound source location of each voice of the first to fourth passengers (SPK1 to SPK4) by using the time delay (or phase delay) between the voice signals associated with the voices of the first to fourth passengers (SPK1 to SPK4), and extracts (or generates) a separate voice signal corresponding only to the sound source of the specific location. As illustrated in FIG.
- the voice processing device (40) can generate a voice signal in response to the voices “AAA”, “BBB”, “CCC” and “DDD” and use the generated voice signal to generate a separate voice signal associated with the voice of each passenger (SPK1 to SPK4).
- the voice processing device (40) can match and store a first separated voice signal associated with the voice “AAA” of the first passenger (SPK1) and first sound source location information indicating the sound source location of the voice “AAA” (i.e., the boarding location of the first passenger (SPK1)) to the left front row (FL) by separating the voice signal according to the location of the sound source.
- the voice processing device (40) can match and store a second separated voice signal associated with the voice “BBB” of the second passenger (SPK2) and second sound source location information indicating the sound source location of the voice “BBB” (i.e., the boarding location of the second passenger (SPK2)) to the right front row (FR).
- the voice processing device (40) can match and store the third separate voice signal associated with the voice “CCC” of the third passenger (SPK3) and the third sound source location information indicating the rear left (BL) which is the sound source location of the voice “CCC” (i.e., the boarding location of the third passenger (SPK3)).
- the voice processing device (40) can match and store the fourth separate voice signal associated with the voice “DDD” of the fourth passenger (SPK4) and the fourth sound source location information indicating the rear right (BR) which is the sound source location of the voice “DDD” (i.e., the boarding location of the fourth passenger (SPK4)).
- the voice processing device (40) may output a predetermined conversation attempt message to the passenger.
- the voice processing device (40) may store a plurality of candidate conversation attempt messages in advance.
- the plurality of candidate conversation attempt messages may be connected in a hierarchical query structure. Accordingly, when the voice processing device (40) receives a collision occurrence signal from the vehicle controller (30), it may output a first candidate conversation attempt message among the plurality of candidate conversation attempt messages in order to have a conversation with a passenger in the vehicle (10).
- the first candidate conversation attempt message may be a message that is initially designated in advance or may be a randomly selected message.
- the voice processing device (40) may output a second candidate conversation attempt message following the first candidate conversation attempt message as a voice based on a reaction related to a passenger's response voice signal to the first candidate conversation attempt message.
- the response related to the response voice signal may include whether or not the passenger responds, the time required to respond, the size (strength) of the response, and the content of the response (e.g., positive or negative response). That is, the second candidate conversation attempt message following the first candidate conversation attempt message is not unconditionally determined, but the second candidate conversation attempt message is selected and voiced based on the passenger's response (e.g., response) to the first candidate conversation attempt message (e.g., question).
- the voice processing device (40) may output the conversation attempt message as a voice considering the degree of injury of the passenger and the location of the injury.
- the voice processing device (40) may store a plurality of candidate conversation attempt messages in advance. The plurality of candidate conversation attempt messages may be connected in a hierarchical query structure. The voice processing device (40) transmits the sound source location information to the vehicle controller (30).
- the sound source location information may be generated by processing the passenger's response voice signal to a certain number of conversation attempt messages after the vehicle collision.
- the sound source location information may be generated in advance by determining the sound source location of each of the passenger's voices from the voice signals associated with the passenger's voices received from the microphone (41) before the vehicle collision.
- the vehicle controller (30) estimates the degree and location of injury of a passenger at the corresponding sound source location based on the sound source location information and the sensing information of the sensor (20).
- the vehicle controller (30) generates injury estimation information indicating the degree and location of injury of a passenger at the estimated sound source location and sends the information to the voice processing device (40).
- the voice processing device (40) receives the injury estimation information and can output a candidate conversation attempt message corresponding to the injury estimation information among a plurality of candidate conversation attempt messages.
- the sensing information of the sensor (20) above can include, for example, vehicle speed, longitudinal/lateral acceleration values, impact values, etc., and thus can be helpful in estimating the degree and location of injury of a passenger at the corresponding sound source location.
- the vehicle controller (30) can receive the sound source location information of the passenger and the passenger's identity information (information indicating whether the passenger is an adult or a child; the identity information will be described later) from the voice processing device (40), and can receive various sensing information at the time of the vehicle collision from the sensor (20).
- the vehicle controller (30) can predict the injury degree and the injured area of the passenger according to the sound source location (i.e., the boarding position) based on the received information.
- the vehicle controller (30) can have a table in which the information on the injury degree and the injured area of the passenger is matched according to the sound source location information, the identity information, and the contents of the sensing information of the sensor.
- the vehicle controller (30) can easily predict the injury degree and the injured area of the passenger according to the sound source location by utilizing this table. In this case, since the vehicle controller (30) uses the passenger's identity information more than the above-described estimation method, the injury degree and the injured area of the passenger according to the sound source location can be predicted more accurately.
- the vehicle controller (30) can transmit injury prediction information indicating the predicted injury degree and injury site for each passenger by sound source location (i.e., boarding location) to the voice processing device (40). Accordingly, the voice processing device (40) can receive the injury prediction information and output a candidate conversation attempt message corresponding to the injury prediction information among a plurality of candidate conversation attempt messages by sound source location.
- the vehicle controller (30) can generate injury prediction information appropriate therefor and send it to the voice processing device (40), so that the voice processing device (40) can output a conversation attempt message corresponding to the injury prediction information for the child passenger. Accordingly, it is possible to make appropriate inquiries (questions) considering the injury degree and injury site even for the child passenger.
- the voice processing device (40) may receive a passenger's response voice signal to a conversation attempt message, process the received response voice signal, and generate sound source location information indicating a sound source location of the response voice signal. Since the voice processing device (40) may classify components of a passenger's voice signal by sound source location, it is believed that the sound source location information indicating a sound source location can be sufficiently generated. The sound source location information may be used to output the above-described conversation attempt message as a voice, or may be used when grouping the passenger's response voice signal.
- the voice processing device (40) may group the response voice signals of each passenger according to the sound source location information. For example, the voice processing device (40) may generate a first group of response voice signals composed only of the response voice signals of the first passenger (SPK1) at the first sound source location, and the response voice signals of the first group may be arranged in time series.
- SPK1 response voice signals of the first passenger
- the voice processing device (40) may send the grouped response voice signals and the sound source location information corresponding to the grouped response voice signals to the emergency rescue request device (50). Then, the emergency rescue request device (50) may send the grouped response voice signals and the sound source location information corresponding to the grouped response voice signals to the control server (70). Of course, if necessary, the voice processing device (40) may directly send the grouped response voice signals to the control server (70), and the sound source location information corresponding to the grouped response voice signals may be sent to the control server (70) via the emergency rescue request device (50).
- the above grouped response voice signals may be a collection of answers (answers) to certain questions (questions), and the response voice signals of the first group as an example above may be composed only of the response voice signals of the first passenger (SPK1) at the first sound source location.
- the control server (70) can more accurately determine the situation (degree of injury, injured area, etc.) of the passenger (i.e., the first passenger (SPK1)) at the corresponding sound source location within the vehicle through the response voice signals of the first group.
- the voice processing device (40) can group the response voice signals of the corresponding passengers by sound source location for a preset amount of time when receiving a collision occurrence signal. According to an embodiment, the voice processing device (40) can store the grouped response voice signals in an internal memory and then output the grouped response voice signals stored in the internal memory.
- the voice processing device (40) may analyze a response voice signal by sound source location to determine the height and tone of the corresponding response voice signal, and may determine whether the passenger at the sound source location is a child passenger based on the determined height and tone. If the voice processing device (40) determines that the passenger is a child passenger, the voice processing device (40) may output identification information indicating that the passenger at the sound source location is a child passenger. Of course, if the voice processing device (40) determines that the passenger at the sound source location is an adult passenger, the voice processing device (40) may output identification information indicating that the passenger is an adult passenger.
- the identification information indicating that the passenger is a child may be transmitted to the control server (70) together with the grouped response voice signal.
- the voice processing device (40) may send the grouped response voice signal, the sound source location information corresponding to the grouped response voice signal, and the identification information indicating that the passenger is a child to the control server (70) via the emergency rescue request device (50).
- the voice processing device (40) may directly send the grouped response voice signal to the control server (70), and the sound source location information corresponding to the grouped response voice signal and the identification information indicating that the passenger is a child may be sent to the control server (70) via the emergency rescue request device (50).
- the voice processing device (40) may include a communication unit (not shown) configured to exchange data (i.e., the grouped response voice signal) with the control server (70) using radio waves of various frequencies in order to directly send the grouped response voice signal to the control server (70).
- the communication unit (not shown) in the voice processing device (40) can exchange data with the control server (70) according to at least one of short-range wireless communication, medium-range wireless communication, and long-range wireless communication.
- control server (70) By transmitting the identification information indicating that the passenger is a child to the control server (70) in this way, the control server (70) can know that there are children as well as adults among the passengers through the identification information. As a result, the control server (70) can issue a more accurate response order for the rescue of children as well as adults.
- the voice processing device (40) can receive the vehicle's location information in real time from the vehicle controller (30). Accordingly, the voice processing device (40) can output the vehicle's location information at the time of receiving the collision occurrence signal when outputting the grouped response voice signal and the sound source location information.
- the voice processing device (40) may receive the vehicle location information at the time of the vehicle collision from the vehicle controller (30) instead of receiving the vehicle location information in real time from the vehicle controller (30). For example, when the vehicle controller (30) receives a collision occurrence signal from the sensor (20), it may receive the vehicle location information at that time together and transmit the collision occurrence signal and the vehicle location information at the time of the vehicle collision to the voice processing device (40).
- the emergency rescue request device (50) can be configured to receive a grouped response voice signal and transmit the received grouped response voice signal to the control server (70).
- the emergency rescue request device (50) can transmit the current location information of the vehicle (10) and the sound source location information of the passengers together with the grouped response voice signal to the control server (70).
- the emergency rescue request device (50) may include a communication unit (not shown) configured to exchange data with the control server (70) using radio waves of various frequencies.
- the communication unit in the emergency rescue request device (50) may exchange data with the control server (70) according to at least one of short-range wireless communication, medium-range wireless communication, and long-range wireless communication.
- the microphone (41) may include a plurality of microphones arranged to form an array, and each of the plurality of microphones may generate a voice signal in response to a voice.
- the voice signals generated from each of the plurality of microphones may have a phase difference (or time delay) from each other.
- the voice processing device (40) includes a microphone (41).
- the memory (42) may store an identifier corresponding to each sound source location (i.e., a passenger's boarding location) within the vehicle (10).
- the identifier may be data for distinguishing the sound source location. Since each of the sound source locations corresponds to each passenger, each passenger may be distinguished using the identifier corresponding to the sound source location. For example, a first identifier indicating a first sound source location may indicate a first passenger. From this perspective, the identifier corresponding to each sound source location within the vehicle (10) may also function as a passenger identifier for identifying each passenger.
- the memory (42) may store grouped response voice signals and sound source location information related to the sound source locations of each of the passengers.
- the location information of the vehicle (10) at the time of receiving the collision occurrence signal may also be stored.
- the communication unit (43) is configured to exchange data with the vehicle controller (30) and/or the emergency rescue request device (50).
- the processor (44) can control the overall operation of the voice processing device (40).
- the processor (44) can include a processor having an operation processing function.
- the processor (44) can include, but is not limited to, a CPU (central processing unit), an MCU (micro controller unit), a GPU (graphics processing unit), a DSP (digital signal processor), an ADC (analog to digital converter), or a DAC (digital to analog converter).
- the operation of the voice processing device (40) described in this specification can be understood as the operation of the processor (44).
- the processor (44) can process voice signals generated by the microphone (41). For example, the processor (44) can convert an analog type voice signal generated by the microphone (41) into a digital type voice signal and process the converted digital type voice signal. In this case, since the type of the signal (analog or digital) is changed, in the description of embodiments of the present invention, the digital type voice signal and the analog type voice signal are described interchangeably.
- the processor (44) may process a voice signal generated by the microphone (41) to extract (or generate) a voice signal associated with each of the passengers' voices. According to embodiments, the processor (44) may generate a separate voice signal associated with the voice of the passenger located at each sound source location. The separate voice signal may be in the form of voice data or text data.
- the processor (44) can determine the sound source locations of the passengers' voices by using the time delay (or phase delay) between the separate voice signals. For example, the processor (44) can determine the relative locations of the sound sources (i.e., the relative locations of the passengers).
- the processor (44) can classify components of a voice signal by sound source location and generate a separate voice signal associated with a voice spoken at each sound source location using the classified components corresponding to each sound source location. For example, the processor (44) can generate a first separate voice signal associated with the voice of the first passenger based on the sound source location of the voices.
- the processor (44) may match and store sound source location information indicating the determined sound source location with the separated voice signal.
- the processor (44) may match and store in the memory (42) the first separated voice signal associated with the voice of the first passenger and the first sound source location information indicating the sound source location of the voice of the first passenger. That is, since the location of the sound source corresponds directly to the boarding location of each passenger, the sound source location information may function as passenger boarding location information for identifying the boarding location of each passenger.
- the processor (44) when the processor (44) receives a collision occurrence signal from the vehicle controller (30), it may output a predetermined conversation attempt message to the passenger.
- the processor (44) may output a first candidate conversation attempt message among a plurality of candidate conversation attempt messages to have a conversation with a passenger in the vehicle (10).
- the plurality of candidate conversation attempt messages are connected in a hierarchical query structure and are stored in advance in the memory (42).
- the processor (44) may output a second candidate conversation attempt message subsequent to the first candidate conversation attempt message based on a reaction related to a passenger's response voice signal to the first candidate conversation attempt message (e.g., whether the passenger responds, the time required to respond, the size (strength) of the response, a positive or negative response, etc.).
- the processor (44) may process the passenger's response voice signal to the conversation attempt message received from the microphone (41) to generate sound source location information indicating the sound source location of the response voice signal, and transmit the generated sound source location information to the vehicle controller (30).
- the sound source location information may be generated by processing the passenger's response voice signal to the conversation attempt message some time after the vehicle collision occurs.
- the sound source location information generated in advance may be used by determining the sound source location of each of the passengers' voices from the voice signals associated with the passengers' voices received from the microphone (41) before the vehicle collision occurs.
- the vehicle controller (30) estimates the degree and location of the passenger's injury at the corresponding sound source location based on the sound source location information and the sensing information of the sensor (20).
- the vehicle controller (30) generates injury estimation information indicating the degree and location of the passenger's injury at the corresponding estimated sound source location and sends it to the processor (44). Thereafter, the processor (44) can receive the injury estimation information and output a candidate conversation attempt message corresponding to the injury estimation information among the plurality of candidate conversation attempt messages.
- the sensing information of the sensor (20) above can include, for example, vehicle speed, longitudinal/lateral acceleration values, impact values, etc., and thus can be helpful in estimating the degree and location of injury of a passenger at the sound source location. It is assumed that the plurality of candidate conversation attempt messages are stored in advance in the memory (42).
- the processor (44) may receive passenger injury prediction information for each sound source location (i.e., boarding location) generated based on the sound source location information of the passenger, the passenger identification information, and the sensing information of the sensor (20) at the time of the vehicle collision from the vehicle controller (30). Accordingly, the processor (44) may output candidate conversation attempt messages corresponding to the injury prediction information among a plurality of candidate conversation attempt messages by sound source location.
- the processor (44) can group the response voice signals of each passenger according to the sound source location information generated after receiving the collision occurrence signal. For example, the processor (44) can generate a first group of response voice signals composed only of the response voice signals of the first passenger (SPK1) at the first sound source location, and the response voice signals of the first group can be arranged in time series.
- SPK1 response voice signals of the first passenger
- the processor (44) when the processor (44) receives a collision occurrence signal, it groups the response voice signals of the passengers by sound source location for a predetermined amount of time. According to an embodiment, the processor (44) may store the grouped response voice signals in the memory (42) and then output the grouped response voice signals stored in the memory (42).
- the processor (44) can send the grouped response voice signal and the sound source location information corresponding to the grouped response voice signal to the emergency rescue request device (50).
- the processor (44) can directly send the grouped response voice signal to the control server (70), and the sound source location information corresponding to the grouped response voice signal can be sent to the control server (70) through the emergency rescue request device (50). Since the sound source location of a passenger can correspond to the boarding location of the passenger, the above sound source location information can be referred to as the passenger's boarding location information.
- the processor (44) may analyze the response voice signal by sound source location to determine the height and tone of the corresponding response voice signal, and determine whether the passenger at the corresponding sound source location is a child passenger based on the determined height and tone. If the processor (44) determines that the passenger is a child passenger, the processor (44) may output identification information indicating that the passenger at the corresponding sound source location is a child passenger. Of course, if the processor (44) determines that the passenger at the corresponding sound source location is an adult passenger, the processor (44) may output identification information indicating that the passenger is an adult passenger.
- the processor (44) may transmit the identification information indicating the child passenger to the control server (70) together with the grouped response voice signal. For example, the processor (44) may send the grouped response voice signal, the sound source location information corresponding to the grouped response voice signal, and the identification information indicating the child passenger to the control server (70) through the emergency rescue request device (50). Of course, if necessary, the processor (44) may directly send the grouped response voice signal to the control server (70), and may also send the sound source location information corresponding to the grouped response voice signal and the identification information indicating the child passenger to the control server (70) through the emergency rescue request device (50).
- control server (70) When identification information indicating a child passenger is transmitted to the control server (70), the control server (70) can know that there is a child passenger among the passengers, and thus can issue a more accurate response order for the rescue of children as well as adults.
- the processor (44) can output a candidate conversation attempt message corresponding to the child passenger from among a plurality of candidate conversation attempt messages stored in the internal memory for the child passenger. That is, in order to ask the child passenger more accurately about the types and locations of injuries, it is desirable to output a conversation attempt message suitable for the child passenger (i.e., a candidate conversation attempt message).
- the processor (44) can receive the vehicle location information at the time of the vehicle collision (i.e., at the time of receiving the collision occurrence signal) from the vehicle controller (30). Accordingly, the processor (44) can output the vehicle location information at the time of receiving the collision occurrence signal together when outputting the grouped response voice signal and the sound source location information.
- processor (44) or voice processing device (40) described in this specification may be implemented in the form of a program executable by a computing device.
- the processor (44) may execute an application stored in the memory (42) and perform operations corresponding to instructions that instruct specific operations according to the execution of the application.
- the speaker (45) can vibrate under the control of the processor (44), and a sound can be generated according to the vibration. According to embodiments, the speaker (45) can reproduce a sound associated with a sound signal by forming a vibration corresponding to the sound signal.
- the speaker (45) may include a plurality of speakers (S1 to S4; see FIG. 2).
- the speakers (S1 to S4) may generate vibrations based on a voice signal, and a voice may be reproduced according to the vibration of the speakers (S1 to S4).
- the speakers (S1 to S4) may be arranged at respective positions of the passengers (SPK1 to SPK4).
- each of the speakers (S1 to S4) may be a speaker arranged at a headrest of a seat where the passengers (SPK1 to SPK4) are located, but embodiments of the present invention are not limited thereto.
- the voice processing device (40) includes a speaker (45) and outputs a conversation attempt message as a voice using the speaker (45).
- the speaker (45) may be configured externally and separately from the voice processing device (40). That is, the voice processing device (40) may output a conversation attempt message as a voice using the speaker (45) included internally, or may output a conversation attempt message as a voice using speakers (S1 to S4) configured separately as illustrated in FIG. 2.
- Figure 5 is a flowchart for explaining the operation of a voice processing device according to an embodiment of the present invention.
- the vehicle (10) is driving (S10).
- the voice processing device (40) When the voice processing device (40) receives a collision occurrence signal from the vehicle controller (30) while the vehicle is driving ("Yes" at S20), the voice processing device (40) outputs a predetermined conversation attempt message to the passenger (S30). At this time, the conversation attempt message can be output through speakers (S1 to S4; see FIG. 2) placed at each passenger's boarding position.
- passengers in the vehicle (10) can respond to the conversation attempt message with their own voices.
- the microphone (41) of the voice processing device (40) receives the passenger's response voice signal to the conversation attempt message (S40).
- the voice processing device (40) processes the received passenger's response voice signal to generate sound source location information indicating the sound source location of the response voice signal (S50). For example, the voice processing device (40) can classify the components of the voice signal by sound source location. By adopting this method, the voice processing device (40) can sufficiently generate sound source location information from the passenger's response voice signal.
- the voice processing device (40) groups the response voice signals of each sound source location (i.e., the voice signals associated with the voices in response to the conversation attempt message of the corresponding passengers at each boarding location) using the sound source location information (S60). Assume that there are four passengers (SPK1 to SPK4) in the vehicle (10) and that four of the passengers (SPK1 to SPK4) are slightly injured.
- the voice processing device (40) may generate a first group of response voice signals composed only of the response voice signals of the first passenger (SPK1), a second group of response voice signals composed only of the response voice signals of the second passenger (SPK2), a third group of response voice signals composed only of the response voice signals of the third passenger (SPK3), and a fourth group of response voice signals composed only of the response voice signals of the fourth passenger (SPK4).
- the voice processing device (40) outputs the grouped response voice signals (S70).
- the voice processing device (40) can send the grouped response voice signals, the sound source location information corresponding to the grouped response voice signals, and the location information of the vehicle at the time of receiving the collision occurrence signal to the emergency rescue request device (50).
- the emergency rescue request device (50) can send the grouped response voice signals, the sound source location information corresponding to the grouped response voice signals, and the location information of the vehicle at the time of receiving the collision occurrence signal to the control server (70).
- the voice processing device (40) can directly send the grouped response voice signals to the control server (70), and the sound source location information corresponding to the grouped response voice signals and the location information of the vehicle at the time of receiving the collision occurrence signal can be sent to the control server (70) via the emergency rescue request device (50).
- control server (70) can more accurately determine the number of passengers inside the vehicle at the time of the vehicle accident, the status of the passengers (degree of injury, injured area), etc. based on the individually grouped response voice signals, the individually grouped sound source location information corresponding to the individually grouped response voice signals, and the location information of the vehicle at the time of receiving the collision occurrence signal. Accordingly, the control server (70) can instruct a quicker and more accurate response to the occurrence of the vehicle accident.
- the operating method of the voice processing device of the present invention described above can be implemented as a computer-readable code on a computer-readable recording medium.
- the computer-readable recording medium includes all kinds of recording devices that store data that can be read by a computer system. Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
- the computer-readable recording medium can be distributed to computer systems connected to a network, so that the computer-readable code can be stored and executed in a distributed manner.
- functional programs, codes, and code segments for implementing the above method can be easily inferred by programmers in the technical field to which the present invention belongs.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Acoustics & Sound (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Computer Networks & Wireless Communication (AREA)
- Otolaryngology (AREA)
- Mechanical Engineering (AREA)
- Transportation (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Environmental & Geological Engineering (AREA)
- Public Health (AREA)
- Automation & Control Theory (AREA)
- General Health & Medical Sciences (AREA)
- Alarm Systems (AREA)
- Fittings On The Vehicle Exterior For Carrying Loads, And Devices For Holding Or Mounting Articles (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
Description
Claims (15)
- 차량에 설치된 음성 처리 장치로서,차량내 탑승객의 음성에 응답하여 탑승객의 음성과 연관된 음성 신호를 생성하도록 구성되는 마이크;상기 차량내 탑승객에게로 음성을 출력하도록 구성되는 스피커;메모리; 및상기 메모리에 저장된 명령어들을 로드하고, 상기 명령어들의 실행에 따라 하나 이상의 동작을 수행하도록 구성되는 프로세서;를 포함하고,상기 프로세서는,상기 차량의 동작을 제어하도록 구성되는 차량 컨트롤러로부터 충돌 발생 신호를 수신하면 상기 탑승객에게 대화 시도 메시지를 상기 스피커를 통해 음성출력하고,상기 마이크로부터 수신되는 상기 대화 시도 메시지에 대한 상기 탑승객의 응답 음성 신호를 처리하여 상기 응답 음성 신호의 음원 위치를 나타내는 음원 위치 정보를 생성하고,상기 음원 위치 정보에 따라 상기 응답 음성 신호를 그룹핑하고,상기 그룹핑된 응답 음성 신호를 출력하는,음성 처리 장치.
- 제 1항에 있어서,상기 메모리는 복수의 후보 대화 시도 메시지를 저장하고,상기 프로세서는,상기 복수의 후보 대화 시도 메시지 중에서 제 1 후보 대화 시도 메시지를 음성출력하고, 상기 제 1 후보 대화 시도 메시지에 대한 상기 탑승객의 응답 음성 신호와 관련된 반응에 근거하여 상기 제 1 후보 대화 시도 메시지에 후속하는 제 2 후보 대화 시도 메시지를 음성출력하는,음성 처리 장치.
- 제 1항에 있어서,상기 메모리는 복수의 후보 대화 시도 메시지를 저장하고,상기 프로세서는,상기 음원 위치 정보를 상기 차량 컨트롤러에게로 전송하고,상기 차량 컨트롤러에서 상기 음원 위치 정보 및 센서의 센싱 정보를 근거로 추정된 상기 음원 위치의 탑승객의 부상의 정도 및 부위를 나타내는 부상 추정 정보를 수신하고,상기 복수의 후보 대화 시도 메시지 중에서 상기 부상 추정 정보에 대응하는 후보 대화 시도 메시지를 음성출력하는,음성 처리 장치.
- 제 1항에 있어서,상기 프로세서는,상기 음원 위치의 응답 음성 신호를 분석하여 해당 응답 음성 신호의 높이 및 음색을 결정하고,상기 결정된 높이 및 음색에 따라 상기 음원 위치의 탑승객이 소아 탑승객인지를 판단하고,상기 소아 탑승객으로 판단되면 상기 음원 위치의 탑승객이 소아 탑승객임을 나타내는 신원 정보를 출력하는,음성 처리 장치.
- 제 4항에 있어서,상기 메모리는 복수의 후보 대화 시도 메시지를 저장하고,상기 프로세서는,상기 복수의 후보 대화 시도 메시지 중에서 상기 소아 탑승객에 대응하는 후보 대화 시도 메시지를 음성출력하는,음성 처리 장치.
- 제 1항에 있어서,상기 프로세서는,상기 그룹핑된 응답 음성 신호를 상기 차량에 설치된 긴급 구조 요청 장치에게로 출력하는,음성 처리 장치.
- 제 1항에 있어서,상기 프로세서는,상기 그룹핑된 응답 음성 신호를 관제 서버에게로 출력하고, 상기 그룹핑된 응답 음성 신호에 대응하는 음원 위치 정보를 상기 차량에 설치된 긴급 구조 요청 장치에게로 출력하는,음성 처리 장치.
- 제 1항에 있어서,상기 프로세서는,상기 차량 컨트롤러로부터 차량의 위치 정보를 수신하고,상기 그룹핑된 응답 음성 신호와 함께 상기 충돌 발생 신호를 수신한 시점의 차량의 위치 정보를 출력하는,음성 처리 장치.
- 차량에 설치된 음성 처리 장치의 작동 방법으로서,상기 차량의 동작을 제어하도록 구성되는 차량 컨트롤러로부터 충돌 발생 신호를 수신하면 상기 차량의 탑승객에게 대화 시도 메시지를 음성출력하는 단계;상기 대화 시도 메시지에 대한 상기 탑승객의 응답 음성 신호를 처리하여 상기 응답 음성 신호의 음원 위치를 나타내는 음원 위치 정보를 생성하는 단계;상기 음원 위치 정보에 따라 상기 응답 음성 신호를 그룹핑하는 단계; 및상기 그룹핑된 응답 음성 신호를 출력하는 단계;를 포함하는,음성 처리 장치의 작동 방법.
- 차량의 동작을 제어하도록 구성되는 차량 컨트롤러; 및상기 차량 컨트롤러로부터 충돌 발생 신호를 수신하면 상기 차량의 탑승객에게 대화 시도 메시지를 음성출력하고, 상기 대화 시도 메시지에 대한 상기 탑승객의 응답 음성 신호를 처리하여 상기 응답 음성 신호의 음원 위치를 나타내는 음원 위치 정보를 생성하고, 상기 음원 위치 정보에 따라 상기 응답 음성 신호를 그룹핑하고, 상기 그룹핑된 응답 음성 신호를 출력하도록 구성되는 음성 처리 장치;를 포함하는,차량 제어 시스템.
- 제 10항에 있어서,상기 음성 처리 장치는 복수의 후보 대화 시도 메시지를 저장하고,상기 음성 처리 장치는,상기 음원 위치 정보를 상기 차량 컨트롤러에게로 전송하고,상기 차량 컨트롤러에서 상기 음원 위치 정보 및 센서의 센싱 정보를 근거로 추정된 상기 음원 위치의 탑승객의 부상의 정도 및 부위를 나타내는 부상 추정 정보를 수신하고,상기 복수의 후보 대화 시도 메시지 중에서 상기 부상 추정 정보에 대응하는 후보 대화 시도 메시지를 음성출력하는,차량 제어 시스템.
- 제 10항에 있어서,상기 음성 처리 장치는,상기 음원 위치의 응답 음성 신호를 분석하여 음색을 결정하고,상기 결정된 음색에 따라 상기 음원 위치의 탑승객이 소아 탑승객인지를 판단하고,상기 소아 탑승객으로 판단되면 상기 음원 위치의 탑승객이 소아 탑승객임을 나타내는 신원 정보를 출력하는,차량 제어 시스템.
- 제 12항에 있어서,상기 차량 컨트롤러는,상기 음원 위치 정보와 상기 신원 정보 및 센서의 센싱 정보를 수신하고,상기 음원 위치 정보와 상기 신원 정보 및 센서의 센싱 정보를 근거로 상기 소아 탑승객에 대한 부상 정도 및 부위를 예측하고,상기 예측에 따른 부상 예측 정보를 상기 음성 처리 장치에게로 출력하는,차량 제어 시스템.
- 제 13항에 있어서,상기 음성 처리 장치는,상기 부상 예측 정보를 수신하고, 상기 소아 탑승객에 대해 상기 부상 예측 정보에 대응하는 대화 시도 메시지를 음성출력하는,차량 제어 시스템.
- 제 10항에 있어서,상기 음성 처리 장치는 복수의 후보 대화 시도 메시지를 저장하고,상기 음성 처리 장치는,상기 복수의 후보 대화 시도 메시지 중에서 제 1 후보 대화 시도 메시지를 음성출력하고,상기 제 1 후보 대화 시도 메시지에 대한 상기 탑승객의 응답 음성 신호와 관련된 반응에 근거하여 상기 제 1 후보 대화 시도 메시지에 후속하는 제 2 후보 대화 시도 메시지를 음성출력하는,차량 제어 시스템.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2025557099A JP2026513301A (ja) | 2023-03-30 | 2024-03-25 | 音声処理装置と、その作動方法及び音声処理装置を含む車両制御システム |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020230041616A KR20240146703A (ko) | 2023-03-30 | 2023-03-30 | 음성 처리 장치와 이의 작동 방법 및 음성 처리 장치를 포함하는 차량 제어 시스템 |
| KR10-2023-0041616 | 2023-03-30 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2024205155A1 true WO2024205155A1 (ko) | 2024-10-03 |
Family
ID=92906271
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/KR2024/003664 Ceased WO2024205155A1 (ko) | 2023-03-30 | 2024-03-25 | 음성 처리 장치와 이의 작동 방법 및 음성 처리 장치를 포함하는 차량 제어 시스템 |
Country Status (3)
| Country | Link |
|---|---|
| JP (1) | JP2026513301A (ko) |
| KR (1) | KR20240146703A (ko) |
| WO (1) | WO2024205155A1 (ko) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015161977A (ja) * | 2014-02-26 | 2015-09-07 | 株式会社デンソー | 車両用緊急対応装置及び車両事故通報システム |
| KR20190093094A (ko) * | 2018-01-31 | 2019-08-08 | 주식회사 비즈모델라인 | 교통사고 긴급출동 서비스를 제공하는 공기정화장치 |
| US11004450B2 (en) * | 2018-07-03 | 2021-05-11 | Hyundai Motor Company | Dialogue system and dialogue processing method |
| KR102317239B1 (ko) * | 2017-04-13 | 2021-10-26 | 현대모비스 주식회사 | eCall시스템 및 그 운영 방법 |
| KR20220162247A (ko) * | 2021-06-01 | 2022-12-08 | 주식회사 아모센스 | 권한 수준에 따라 화자의 음성을 처리하기 위한 음성 처리 장치 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101562591B1 (ko) | 2014-06-03 | 2015-10-23 | 엘지전자 주식회사 | 이동 단말기 및 이를 이용한 차량의 사고 발생 처리 방법 |
| KR102277290B1 (ko) | 2019-12-24 | 2021-07-14 | 주식회사 텔레칩스 | 교통사고 정보 제공 장치 및 방법 |
-
2023
- 2023-03-30 KR KR1020230041616A patent/KR20240146703A/ko active Pending
-
2024
- 2024-03-25 JP JP2025557099A patent/JP2026513301A/ja active Pending
- 2024-03-25 WO PCT/KR2024/003664 patent/WO2024205155A1/ko not_active Ceased
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015161977A (ja) * | 2014-02-26 | 2015-09-07 | 株式会社デンソー | 車両用緊急対応装置及び車両事故通報システム |
| KR102317239B1 (ko) * | 2017-04-13 | 2021-10-26 | 현대모비스 주식회사 | eCall시스템 및 그 운영 방법 |
| KR20190093094A (ko) * | 2018-01-31 | 2019-08-08 | 주식회사 비즈모델라인 | 교통사고 긴급출동 서비스를 제공하는 공기정화장치 |
| US11004450B2 (en) * | 2018-07-03 | 2021-05-11 | Hyundai Motor Company | Dialogue system and dialogue processing method |
| KR20220162247A (ko) * | 2021-06-01 | 2022-12-08 | 주식회사 아모센스 | 권한 수준에 따라 화자의 음성을 처리하기 위한 음성 처리 장치 |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2026513301A (ja) | 2026-04-23 |
| KR20240146703A (ko) | 2024-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021006491A1 (ko) | 음원 시각화 장치 및 방법 | |
| US20130017800A1 (en) | Tyy interface module signal to communicate equipment disruption to call center | |
| JP2020154996A (ja) | 情報処理システム、エージェントシステム、情報処理方法、およびプログラム | |
| WO2017122935A1 (ko) | 전달력이 향상된 터널용 스피커를 이용한 터널 정보 방송 시스템 | |
| US20200231147A1 (en) | Information processing device, information processing method and program | |
| WO2021153856A1 (ko) | 차량주변 이상 신호 알림 시스템 및 방법 | |
| WO2024205155A1 (ko) | 음성 처리 장치와 이의 작동 방법 및 음성 처리 장치를 포함하는 차량 제어 시스템 | |
| WO2024205154A1 (ko) | 음성 처리 장치와 이의 작동 방법 및 음성 처리 장치를 포함하는 차량 제어 시스템 | |
| US12444319B2 (en) | Voice output method | |
| JP6975358B1 (ja) | 記録装置、記録方法、およびプログラム | |
| CN113393643B (zh) | 异常行为预警方法、装置、车载终端以及介质 | |
| JP7276165B2 (ja) | エージェント装置、エージェントシステム、及びエージェントプログラム | |
| JPH1044894A (ja) | 車両用事故対処装置 | |
| WO2021080142A1 (ko) | 음성 인식 기술을 이용한 차량용 헤드업 디스플레이 장치 | |
| WO2018084379A1 (ko) | 발화자에 대한 신뢰도 측정 장치 및 방법 | |
| WO2023214814A1 (ko) | 대중교통 내릴 곳 및 빈자리 알림 시스템 | |
| WO2020111615A1 (ko) | 차량 하차 확인 장치, 이를 이용한 차량 하차 확인 시스템 및 방법 | |
| KR20220080474A (ko) | 차량 및 그 제어 방법 | |
| WO2020196931A1 (ko) | 차량용 전자 장치 및 차량용 전자 장치의 동작 방법 | |
| CN114275010A (zh) | 一种列车监控及联动方法、装置及系统 | |
| WO2022064684A1 (ja) | 情報送信装置、情報送信方法、及びプログラム | |
| WO2026063590A1 (ko) | 차량용 e-call 처리 시스템 | |
| WO2021251554A1 (ko) | 개인화된 안전운전 보조 방법 및 시스템 | |
| CN108203037B (zh) | 通话检查系统、通话检查装置、及通话检查方法 | |
| JP6861520B2 (ja) | エレベーター用情報提供装置 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 24781146 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2025557099 Country of ref document: JP Kind code of ref document: A |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2025557099 Country of ref document: JP |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 24781146 Country of ref document: EP Kind code of ref document: A1 |