WO2006011310A1 - 音声識別装置、音声識別方法、及びプログラム - Google Patents
音声識別装置、音声識別方法、及びプログラム Download PDFInfo
- Publication number
- WO2006011310A1 WO2006011310A1 PCT/JP2005/010800 JP2005010800W WO2006011310A1 WO 2006011310 A1 WO2006011310 A1 WO 2006011310A1 JP 2005010800 W JP2005010800 W JP 2005010800W WO 2006011310 A1 WO2006011310 A1 WO 2006011310A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- voice
- output
- user
- identification result
- importance
- Prior art date
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R3/00—Circuits for transducers, loudspeakers or microphones
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/26—Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0965—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages responding to signals from another vehicle, e.g. emergency vehicle
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R2225/00—Details of deaf aids covered by H04R25/00, not provided for in any of its subgroups
- H04R2225/41—Detection or adaptation of hearing aid parameters or programs to listening situation, e.g. pub, forest
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R2499/00—Aspects covered by H04R or H04S not otherwise provided for in their subgroups
- H04R2499/10—General applications
- H04R2499/13—Acoustic transducers and sound field adaptation in vehicles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R25/00—Deaf-aid sets, i.e. electro-acoustic or electro-mechanical hearing aids; Electric tinnitus maskers providing an auditory perception
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R5/00—Stereophonic arrangements
- H04R5/033—Headphones for stereophonic communication
Definitions
- the present invention relates to a voice identification device that identifies a type of voice and presents the identification result to a user.
- FIG. 10 is a diagram showing a configuration of the first conventional technique described in Patent Document 1.
- the conventional speech recognition apparatus reproduces the sound by collecting the sound collecting means 1 for converting the sound in the external space into the electric signal s, and converting the electric signal s in the closed space. And a sound control means 2 that transmits and reproduces sound information generated in the external space to the closed space.
- the signal control means 3 that cuts off the electrical signal s and a characteristic characteristic from the electrical signal s.
- the characteristic extraction means 4 for extracting the signal, the condition storage means 5 for storing the characteristic condition of the signal, the signal converted by the sound collecting means 1 and the characteristic condition stored by the condition storage means 5 are compared.
- characteristic judging means 6 for judging whether or not the force satisfies the condition.
- the signal control unit 3 blocks the signal, and when the characteristic determining unit 6 determines that the condition is satisfied, the signal control unit 3 By letting the signal pass, it is possible to hear only the necessary sound that satisfies the predetermined conditions.
- the current position is detected by the own vehicle position detection means, and the detected current position is detected. Accordingly, by using the acoustic characteristic information stored in the volume 'frequency characteristic storage means and controlling the reproduced voice that also outputs the output device force by the volume' frequency automatic change means, the reproduced voice output in the mobile body is changed. For example, when the vehicle location detection means detects that the current location is near a railroad crossing, the car audio volume is lowered to listen to a railroad crossing warning sound. It can be made easier.
- Patent Document 2 Japanese Patent Laid-Open No. 2002-344268
- Patent Document 3 Japanese Patent Laid-Open No. 7-327295
- the voice identification result is output based only on the determination of whether or not there is a voice input that satisfies the specified acoustic feature condition, the same output is always obtained.
- the input voice information is transmitted to the user depending on the form. Therefore, there is a problem that the user cannot understand the importance of the voice identification result that changes depending on the situation where the user is placed!
- the acoustic characteristics are determined based only on the vehicle position information, for example, when the railroad crossing warning sound is not sounded if the vehicle stays in the vicinity of the railroad crossing due to traffic jams.
- the acoustic characteristics are set so as to lower the reproduction volume, and the user cannot listen to the car audio at a desired volume.
- the present invention has been made in view of these problems, and is a voice identification device that identifies a surrounding voice signal and informs the user of the identification result.
- An object of the present invention is to provide a voice identification device capable of obtaining voice identification result information in a form.
- a speech identification device includes a speech type determination unit that determines a type of the input speech using characteristics of a speech signal representing the input speech, A user action acquisition means for detecting a user action for changing the situation, and an output form for presenting the identification result relating to the input voice to the user based on the detection result in the user action detection means; And an identification result output means for outputting the identification result in the determined output form.
- the voice identification device further includes a sound source state acquisition unit that detects a sound source state indicating a direction in which the input voice arrives, and the identification result output unit further includes a sound source state acquisition unit in the sound source state acquisition unit.
- the output form may be determined in consideration of the detection result.
- the output form is determined in consideration of the direction in which the voice arrives. Therefore, the important identification result regarding the input voice that has arrived from the direction that should be paid attention to by the user and the direction from which the voice is not.
- a voice identification device capable of efficiently presenting the voice identification result to the user is realized.
- the identification result relating to the input speech is stored in the user in an appropriate output form that reflects the importance assumed in accordance with the situation that changes depending on the user's operation. Since it can be presented, it is possible to provide a voice identification device that allows the user to understand the voice identification result reliably and efficiently.
- FIG. 1 is a block diagram showing a configuration of a speech identification device according to Embodiment 1 of the present invention.
- FIG. 2A is a diagram showing an example of output processing method definition information
- FIG. 2B is a diagram showing an example of user operation
- FIG. 2C is an output format definition. It is a figure which shows an example of information
- (d) is a figure which shows an example of the present output form.
- FIG. 3 is a flowchart showing the processing operation of the voice identification apparatus according to the first embodiment.
- FIGS. 4 (a) and 4 (b) are diagrams for explaining an operation example of the speech recognition apparatus according to the first embodiment.
- FIG. 5 is a diagram showing another example of output processing method definition information
- (b) is a diagram showing another example of output form definition information
- (c) Is a diagram showing an example of a user's situation
- (d) is a diagram showing an example of a sound source state.
- FIGS. 6 (a) and 6 (b) are diagrams for explaining an operation example of the speech recognition apparatus when the direction of speech arrival is taken into account.
- FIG. 7 is a block diagram showing a configuration of a speech identification apparatus according to Embodiment 2 of the present invention.
- Fig. 8 relates to the speech identification apparatus according to Embodiment 2 of the present invention.
- (A) is a diagram showing an example of output processing method definition information
- (b) is a diagram showing importance definition information. It is a figure which shows an example
- (c) is a figure which shows an example of a user's condition.
- FIGS. 9A and 9B are diagrams for explaining an operation example of the speech recognition apparatus according to the second embodiment.
- FIG. 10 is a diagram showing a configuration of a conventional voice identification device. Explanation of symbols
- the voice identification device is provided in an automobile, identifies voice information outside the passenger compartment, and outputs an identification result regarding the voice information based on a user operation!
- This is a device that presents the identification result to the user in the determined output form.
- the user is driving a car equipped with the apparatus, and the user's action is specifically a driving action.
- the present apparatus presents the identification result to the user in a suitable output form reflecting the assumed importance, based on the current situation of the user that changes according to the user's driving action.
- the specific contents of the identification result are not limited.
- the notification information that determines the type of the audio information and is presented to the user through hearing, vision, touch, etc. according to the determination result is widely an example of the identification result.
- the voice itself outside the passenger compartment obtained by reproducing the voice information is an example of the identification result.
- FIG. 1 is a block diagram showing a functional configuration of the voice identification device according to the first embodiment.
- a speech identification device 100 includes a speech input unit 101, a feature amount extraction unit 102, a speech storage unit 103, a collation unit 104, an acoustic model storage unit 105, an output A form determining unit 106, an output form definition information storage unit 107, a user action acquisition unit 108, a sound source state information acquisition unit 109, a voice identification result output processing unit 110, and an output processing method definition information storage unit 111 are provided.
- the feature quantity extraction unit 102 and the collation unit 104 are examples of voice type determination means
- the output form determination unit 106 and the voice identification result output processing unit 110 are examples of identification result output means
- the voice The storage unit 103 is an example of a voice storage unit
- the user action acquisition unit 108 is an example of a user action detection unit.
- the audio input unit 101 can be realized by a microphone that collects an audio signal existing in an environment outside the vehicle and an AZD conversion that converts this into a digital signal with a sampling frequency of 12 kHz and an AZD conversion accuracy of 16 bits. .
- the digital signal of the input voice acquired by the voice input unit 101 is sent to the feature amount extraction unit 102 and the voice storage unit 103.
- the feature quantity extraction unit 102 uses a spectrum representing an audio feature from an input audio signal.
- An acoustic feature quantity such as a psram is extracted, and the extracted feature quantity is sent to the matching unit 104.
- an acoustic feature quantity can be constituted by a 16th-order MFCC coefficient, a 16th-order ⁇ MFCC coefficient, and a first-order ⁇ power extracted by the MFCC analysis method.
- the voice storage unit 103 is a RAM having a storage area for temporarily holding an input voice.
- the acoustic model storage unit 105 is a storage device such as a hard disk in which one or a plurality of acoustic models learned for each voice type are stored.
- the HMM (Hidden Markov Model) model that is generally used in speech recognition can be used as the configuration of the acoustic model. For example, three-state left-to-right type four-mix continuous distribution HMM model for each voice type And stored in the acoustic model storage unit 105.
- five kinds of sounds such as “level crossing alarm sound”, “fire truck siren”, “horn”, “motorcycle engine sound”, and “car engine sound” are used as ambient sound outside the vehicle. It is assumed that the acoustic model storage unit 105 stores the acoustic model having the above configuration corresponding to these voice types in the acoustic model storage unit 105.
- the collation unit 104 collates the acoustic model stored in the acoustic model storage unit 105 with the acoustic feature quantity corresponding to the input voice sent from the feature quantity extraction unit 102.
- the degree of similarity to the acoustic model is determined, and the determination result is sent to the output form determination unit 106.
- the collation unit 104 may send a determination result indicating that the voice type corresponding to the acoustic model having the highest similarity is determined as the voice type of the input voice to the output format determination unit 106.
- the output processing method definition information storage unit 111 stores definition information of an output processing method that is determined in advance for each output form of audio information.
- FIG. 2 (a) shows the output processing method stored in the output processing method definition information storage unit 111. It is a figure which shows an example of the definition information regarding. As shown in Fig. 2 (a), this output processing method definition information defines that the input sound is played back at a volume corresponding to each of the five types of output forms and output as an identification result. Yes.
- the output form illustrated here is expressed by a numerical value from 1 to 5, and the magnitude of this numerical value reflects the degree of importance that the identification result should be presented to the user.
- the user action acquisition unit 108 is realized by a sensor that detects a user action, acquires information about the user action, and outputs the information to the output form determination unit 106.
- FIG. 2B is a diagram showing an example of a user action acquired by the user action acquisition unit 108.
- the user's driving actions such as “Turn the direction indicator Z return” and “Turn the hand brake Z return”, illustrated in Fig. 2 (b), are detected by installing sensors on the handbrake and winker respectively. Is possible.
- the output form definition information storage unit 107 stores definition information of importance determined for each type of speech.
- FIG. 2 (c) is a diagram showing an example of the output form definition information stored in the output form definition information storage unit 107.
- the types of input speech to be identified are ⁇ railway crossing alarm sound '', ⁇ fire truck siren '', ⁇ horn '', ⁇ motorcycle engine sound '', ⁇ automobile engine sound ''.
- the amount of change used to update the output format when the user's driving action is detected is defined.
- the output form determination unit 106 includes the determination result acquired from the collation unit 104, information about the user action obtained from the user action acquisition unit 108, and output form definition information stored in the output form definition information storage unit 107. Based on the above, it is a processing unit that determines the output form of the identification result related to the input voice. For this processing, the output form determination unit 106 stores the current output form for each audio type using, for example, a register or a RAM (not shown).
- FIG. 2 (d) is a diagram showing an example of the current output mode for each audio type stored in the output mode determining unit 106.
- the output form determining unit 106 Upon obtaining information related to the user action from the user action obtaining unit 108, the output form determining unit 106 outputs the change amount of the output form corresponding to the user action to the output form definition information storage unit.
- the current output form is updated to a new output form represented by the number after the addition by adding the obtained change amount for each audio type to the current output form.
- the output form determination unit 106 displays the current output form of the voice type indicated in the determination result as the voice identification result. Output to the output processing unit 110.
- the speech identification result output processing unit 110 stores the output form acquired from the output form determination unit 106 and the output processing method defined for each output form stored in the output processing method definition information storage unit 111. Based on the definition information, this is a processing unit that determines what acoustic processing is to be performed on the speech signal stored in the speech storage unit 103 and applies the determined acoustic processing to the speech signal.
- the adjustment of the sound reproduction volume is taken as an example of the acoustic processing
- the sound identification result output processing unit 110 determines the sound volume at which the input sound is reproduced, and then outputs the sound identification result.
- the processing unit 110 reproduces and outputs the audio signal subjected to the determined acoustic processing (volume adjustment in this example) as an audio identification result output.
- FIG. 3 is a flowchart showing the processing operation of the voice identification device 100.
- the voice input unit 101 acquires the voice around the outside of the vehicle as the input voice (S100).
- the obtained sound around the outside of the vehicle is converted into a digital signal and then stored in the voice storage unit 103 and sent to the feature amount extraction unit 102.
- the feature amount extraction unit 102 extracts the acoustic feature amount. (S102).
- the extracted feature quantity is sent from the feature quantity extraction unit 102 to the collation unit 104, and then stored in the acoustic model storage unit 105 in the collation unit 104 and collated with the acoustic model for each voice type. Then, the voice type is determined (S106). Then, the collation unit 104 sends the audio type determination result to the output form determination unit 106.
- the output form determination unit 106 acquires information about the user action obtained by the user action acquisition unit 108 (S108), and output form definition information corresponding to the user action indicated by this information.
- the current output form is updated using the change amount of the output form stored in the storage unit 107. Then, among the updated current output forms, the output form corresponding to the voice type determined by the matching unit 104 is determined as the output form for presenting the identification result related to the input voice to the user (S110). .
- the output form determination unit 106 determines that the "direction indicator is selected from the output form definition information shown in FIG.
- the current output form is updated to the value shown in Fig. 2 (d) by referring to the amount of change corresponding to the “output” operation and adding the amount of change. Then, the output form is determined to be “5” corresponding to the current “railroad crossing warning sound” after the update.
- the output form determined in this way is sent from the output form determination unit 106 to the speech identification result output processing unit 110.
- the speech identification result output processing unit 110 refers to the output processing method definition information shown in FIG. 2A, and determines the speech processing method as a method corresponding to the received output result ( S112).
- the speech processing method since the output form is “5”, the voice recognition result output is stored in the voice storage unit 103, and when the voice signal is reproduced and output with “70dBA”! /, The voice processing method! Will be determined.
- the voice identification result output processing unit 110 reads the input voice stored in the voice storage unit 103, outputs the identification result by the determined method (S114), and ends the processing operation.
- the car 200 equipped with 00 is in the state where the handbrake is pulled before this level crossing You will be shown how to stop!
- crossing warning sound is input to the sound identification device 100 as sound around the vehicle, and “hand brake is applied” is sounded as the user's driving action. It is considered that the identification device 100 has already acquired the identification device 100.
- the voice identification device 100 determines the output form of the input voice "railroad crossing alarm sound" in this situation, the hand brake is applied from the output form definition information shown in Fig. 2 (b).
- the output form is determined by two steps lower than before the bow I (change amount “1 2”), and the voice identification device 100 obtains the voice identification result from the output processing method definition information shown in FIG. It will be output at a volume reduced by “10dBA”. Note that when the user subsequently performs a “returning the brake” operation, the volume is returned to the same level as before the hand brake was pulled by determining the output mode that is two steps higher (change amount “+2”). .
- the audio identification device 100 can maintain the audio volume while maintaining the audio volume in the interior of the automobile 200. However, it is also possible to play and output the voice identification result at a low volume.
- FIG. 4 (b) a road crossing breaker goes down and a crossing warning sound is sounded, and the automobile 200 equipped with the voice identification device 100 cannot see this crossing. From there, it is shown how to turn right at the railroad crossing.
- the voice identification device 100 determines the output form of the input voice “railroad crossing alarm sound” in this situation, the direction indicator is obtained from the output form definition information shown in FIG. 2 (b). The output form is determined two steps higher than before the output (change amount “+2”), and the speech recognition apparatus 100 obtains the speech recognition result from the output processing method definition information shown in FIG.
- the voice identification device 100 By the operation of the voice identification device 100 as described above, it is possible to prevent an accident in which the user visually enters the railroad crossing until the user returns the power after returning the direction indicator. For the purpose, it is thought that the importance of presenting the “railroad crossing warning sound” to the user is high, so that the voice identification result is reproduced and output at a high volume using a high numerical output form that reflects the importance. Can do.
- the collation unit 104 determines that the input sound is most similar to the “motorcycle engine sound”, the following processing is performed.
- the output form determination unit 106 determines the output form of the input voice higher by two levels. So Then, according to the determination, the voice identification result output processing unit 110 performs a setting process to increase the volume for reproduction output of the identification result related to the input voice by “10 dBA”, and the input stored in the voice storage unit 103 The audio is played and output at the set volume as the audio identification result output.
- the output form determination unit 106 determines the output form of the input voice one step lower. Then, according to the determination, the voice identification result output processing unit 110 performs a setting process for lowering the volume for reproduction output of the identification result related to the input voice by “5 dBA”, and the input voice stored in the voice storage unit 103. Is played and output at the set volume as a voice identification result output.
- the voice identification device 100 it is possible to output a voice identification result in an output form that reflects the degree of importance assumed in accordance with a situation that changes according to the user's action.
- the speech identification device 100 As a modification of the speech identification device 100 according to the first embodiment, the speech that presents the speech identification result to the user in an output form that is further determined in consideration of the direction of arrival of the input speech.
- the identification device will be described.
- the voice identification device according to this modification can notify the driver who is the user of the identification result related to the input voice in an output form determined in accordance with the arrival direction of the input voice and the driving operation of the user.
- the sound source state information acquisition unit 109 shown in FIG. 1 detects the sound source state of the sound input from the sound input unit 101, that is, the direction of arrival of the sound, and outputs it to the output form determination unit 106.
- the sound source state of the sound input from the sound input unit 101 that is, the direction of arrival of the sound
- the output form determination unit 106 For example, it is realized by a microphone array composed of a plurality of microphone elements.
- the sound source state information acquisition unit 109 having a function of detecting the voice arrival direction is an example of a sound source direction detection unit.
- Fig. 5 (a) is a diagram showing an example of output processing method definition information stored in the output processing method definition information storage unit 111. Similar to Fig. 2 (a), output processing method definition information is shown. In the information, it is defined that the input sound is played back at a volume corresponding to each of the five types of output forms and output as an identification result. The output form illustrated here is represented by a numerical value from 1 to 5, and the magnitude of this numerical value reflects the importance of the identification result to be presented to the user.
- FIG. 5 (b) is a diagram showing an example of output form definition information stored in the output form definition information storage unit 107.
- the output form definition information illustrated in FIG. 2 (b) defines the amount of change in the output form according to the user's action, whereas the output form definition information illustrated here is the type of input voice.
- the user situation broadly refers to a situation that changes according to the user's action, and for example, “driving situation” is an example.
- This “driving condition” becomes “stopped” by the above-mentioned “pushing the brake” and “runs” by the “returning the handbrake” operation.
- Such a user situation is stored, for example, in the output form determination unit 106 using a register RAM or the like (not shown), and is updated according to information on the user operation obtained from the user operation acquisition unit 108. It is good. Further, the user action acquisition unit 108 itself manages such a user situation and outputs the latest user situation to the output form determination unit 106.
- FIG. 5C is a diagram showing an example of the user situation stored in the output form determination unit 106. Here, an example in which the above-mentioned “driving condition” is “running” is shown.
- the output form determination unit 106 sends this “driving condition” from the user action acquisition unit 108 to the “hand When the information about the “pull rake” operation is obtained, it is changed to “stopping”, and when the information about the “return hand brake” operation is obtained, it is changed to “running”.
- FIG. 5 (d) is a diagram showing an example of a sound source state acquired by the sound source state information acquisition unit 109.
- the voice arrival directions such as “front” and “rear” exemplified in FIG. 5 (d) can be specified by a microphone array including a plurality of microphone element forces provided at the front and rear of the automobile.
- a microphone array including a plurality of microphone element forces provided at the front and rear of the automobile.
- front and “back” are illustrated, but for example, “right”, “left”, or a combination of these, voice arrival such as “right front” or “left rear” Even if you specify the direction.
- the output form determination unit 106 in this modification is obtained from the identification result acquired from the collation unit 104, the user situation stored in the output form determination unit 106, and the sound source state information acquisition unit 109. Based on the information regarding the voice arrival direction and the output form definition information stored in the output form definition information storage unit 107, the output form of the identification result is determined.
- step S110 in determining the output form, the output form determination unit 106 first updates the driving situation according to the information regarding the user action acquired in step S108, and Refer to the output form stored in the output form definition information storage unit 107 corresponding to the obtained voice arrival direction, the updated driving situation, and the voice type determination result obtained from the matching unit 104, The difference is that the referenced output form is determined as an output form for presenting the identification result to the user.
- the output form determination unit 106 determines the output form of the identification result as “5” by referring to the output form definition information shown in FIG.
- the speech identification result output processing unit 110 refers to the output processing method definition information shown in FIG. 5A, and determines an output processing method corresponding to the determined output form.
- the voice identification result output is stored in the voice storage unit 103, and when the voice signal is reproduced and output at “70 dBA”, the output is! / It will be determined by the processing method.
- the output form determination unit 106 determines the output form of the identification result as “1” by referring to the output form definition information shown in FIG.
- the speech identification result output processing unit 110 refers to the output processing method definition information shown in FIG. 5 (a) and determines an output processing method corresponding to the determined output form. In this case, since the determined output form is “1”, the voice identification result output is stored in the voice storage unit 103, and if the voice signal is reproduced and output with “50dBA”! /, Output processing It will be determined by the method.
- FIG. 6 (a) shows a state in which the car 200 equipped with the voice identification device 100 is sounded with a crossing crossing breaker and a crossing alarm sound after passing the crossing. .
- the voice identification device 100 corresponds to the output form of the input voice “railroad crossing alarm sound” with reference to the output form definition information shown in FIG.
- the voice identification device 100 determines “1” and outputs the voice identification result at “50 dBA” from the output processing method definition information shown in FIG.
- the voice identification device 100 may reproduce and output the voice identification result at a volume lower than the audio volume while maintaining the audio volume in the passenger compartment.
- FIG. 6 (b) a railroad crossing breaker goes down and a railroad crossing alarm sounds, and the automobile 200 equipped with the voice identification device 100 cannot see this railroad crossing. Then, you can see how you are going straight on the road with the help of the railroad crossing.
- the voice identification device 100 corresponds to the output possible state of the input voice “railroad crossing alarm sound” with reference to the output form definition information shown in FIG. 5 (b).
- the voice identification device 100 determines “5”, and outputs the voice identification result as “70 dBA” from the output processing method definition information shown in FIG.
- the voice identification device 100 By the operation of the voice identification device 100 as described above, if the user hears a "crossing warning sound" in the "running enabled” state and a front crossing warning sound is heard in the "running enabled” state, the importance is high. If the level crossing warning sound is heard from behind in the “running ready” state, it can be played back at a relatively low volume and output at a low volume, and changes depending on the driving conditions and the sound source state. It is possible to output the voice identification result in a form corresponding to the importance level.
- the matching unit 104 if the input voice is most similar to "fire truck siren" If the determination is V, the following processing is performed.
- the voice identification result output processing unit 110 is a voice signal stored in the voice storage unit 103 as an output processing method corresponding to the output form “5”.
- the volume is set so that is reproduced and output at “70dBA”, and this is reproduced and output as the sound identification result output.
- the output form determination unit 106 determines the output form as “2”, and the speech identification result output processing unit 110 uses the voice storage unit 103 as an output processing method corresponding to the output form “2”. Volume setting processing is performed so that the audio signal stored in is reproduced and output at “55dBA”, and this is reproduced and output as the audio identification result.
- the fire engine siren is played and output at a high volume with a high level of importance if the fire siren sound is heard in the forward direction and the fire siren sound is heard. If the fire siren sound can be heard from the rear in the “in-vehicle” state, it can be reproduced and output at a low volume with a relatively low level of importance. The identification result can be output.
- the collation unit 104, the output configuration determination unit 106, the output configuration definition information storage unit 107, the user action acquisition unit 108, the speech identification result With the configuration including the output processing unit 110 and the output processing method definition information storage unit 111, the output mode determination unit 106 determines the output mode according to the voice type determined by the matching unit 104 depending on the user's operation. Then, after the voice identification result output processing unit 110 performs processing according to the determined output form on the input voice, it can be output as a voice identification result, and voice information important for the user is output to the user. It can be reliably transmitted according to the importance of the input voice information that changes depending on the operation of.
- the configuration including the sound source state information acquisition unit 109 enables the output form determination unit 106 to determine the output form of the identification result in consideration of the voice arrival direction, which is important for the user. It is also possible to reliably transmit correct voice information according to the importance of the input voice information that changes depending on the user's operation status and voice arrival direction.
- the acoustic model stored in the acoustic model storage unit 105 should be prepared for each voice type with respect to artificially output voice such as a crossing warning sound and a fire truck siren.
- voice type such as a crossing warning sound and a fire truck siren.
- the sound source state information acquisition unit 109 acquires information about the voice arrival direction by using a microphone array, and uses this for the importance determination in the output form determination unit 106.
- the input sound is expanded or reduced to a sound volume corresponding to the importance level.
- the playback output is output.
- the playback output may be repeatedly output as many times as the importance level.
- the reproduction of the input voice has been described as an example of the method.
- the voice type corresponding to the acoustic model is described. It is also possible to output the name as a sound identification result by text display. In the case of such character display, it is possible to output the voice identification result by performing processing for changing the size, brightness, color, etc. of the displayed character according to the importance of the voice information. .
- the output of the voice identification result may be selectively used for the voice output and the character display output.
- the voice identification result output processing is performed so that the voice identification result is output by voice when the importance of the input voice is high, and is output by text display when the importance of the input voice is low. It is also possible to adopt a configuration that can be controlled by the unit 110.
- the voice identification device is integrated with the portable headphone stereo, identifies voice information of the surrounding environment of the user wearing the device, and is being used by the user. It is a device that presents the identification result to the user by means of audio playback output through a cellular phone, a headphone stereo speaker, or headphones.
- a cellular phone a headphone stereo speaker
- headphones a headphone stereo speaker
- the user wears acoustic equipment with high acoustic closure properties, such as portable headphone stereos and mobile phone earphones, it is difficult to hear the sound of the surrounding environment. It is possible to notify the user of the identification result by processing the output form of the identification result according to the user's operation status, specifically, the degree of importance depending on the user's walking status. Assuming
- the configuration and operation of the voice identification device according to the second embodiment are substantially the same as the configuration and operation of the voice identification device 100 according to the first embodiment, but the voice identification result should be transmitted to the user.
- the difference is that the importance level, which means the importance level, is explicitly used. In the following, we will focus on the differences.
- FIG. 7 is a block diagram showing a functional configuration of voice identification device 100a according to the second embodiment.
- the voice identification device 100a includes an output form definition information storage unit 107 and an output form determination unit 106 in the voice identification device 100 (see FIG. 1), an importance level definition information storage unit 207, and a voice information importance level judgment unit 206, respectively. It is constituted by replacing with.
- the voice information importance level determination unit 206 is an example of importance level determination means.
- Three types of sound are assumed: “warning sound” and “announcement sound in the vehicle that informs the arrival of the station”, and an acoustic model with the same configuration as in the first embodiment corresponds to these sound types. Stored in the model store.
- the importance level definition information storage unit 207 stores the definition information of the importance level determined for each voice type.
- FIG. 8 (b) is a diagram showing an example of importance level definition information stored in the importance level definition information storage unit 207 of the speech identification apparatus according to the second embodiment.
- the types of input voices that are identification targets are ⁇ car horn, '' ⁇ station home warning sound to notify vehicle entry, '' and ⁇ car announcement sound to notify station arrival. ”Is shown, and the importance corresponding to the user's walking motion is defined for each voice type.
- the user action acquisition unit 108 is configured by a sensor that senses a user action, acquires information related to the user action, and outputs the information to the voice information importance level determination unit 206.
- the user operation acquisition unit 108 detects the operation that is completed in a relatively short time, such as “Take out the direction indicator and Z return” in the first embodiment. In the second embodiment, for example, Detects actions with a longer time span (ie, user action status) such as “Z stop”.
- FIG. 8 (c) is a diagram showing an example of the user's walking situation acquired by the user action acquisition unit of the voice identification device according to the second embodiment.
- the user's walking situation such as “Walking” and “Stopping” illustrated in Fig. 8 (c) can be detected by configuring the user motion acquisition unit with a pedometer equipped with an acceleration sensor. is there.
- the output processing method definition information storage unit 111 stores output processing method definition information determined in advance for each importance level of audio information. As shown in FIG. 8 (a), It is defined that the input sound is played and the identification result is output at a volume corresponding to the importance level.
- the voice information importance level determination unit 206 stores the determination result acquired from the collation unit 104, information about the user action obtained from the user action acquisition unit 108, and the importance level definition information storage unit 207. Based on the importance level definition information, the importance level of the input voice is determined, and the determination result is output to the voice identification result output processing unit 110. Further, the voice identification result output processing unit 110 is determined for each importance level stored in the output processing method definition information storage unit 111 and the importance level of the voice information acquired from the voice information importance level determination unit 206. Based on the definition information of the output processing method, it is determined what kind of acoustic processing is performed on the voice signal stored in the voice storage unit 103, and the voice signal subjected to the determined processing is converted into a voice identification result.
- Playback output as output As a specific example, in the collating unit 104 of the voice identification device according to the second exemplary embodiment, the input voice around the user is most similar to “car horn”. The case will be described assuming that such a determination is made.
- the audio information importance level determination unit 206 determines the importance information shown in Fig. 8 (b). By referring to the degree definition information, the importance of the input voice is determined as “2”.
- the speech identification result output processing unit 110 refers to the output processing method definition information shown in Fig. 8 (a) and determines an output processing method corresponding to the received importance determination result.
- the voice identification result output is stored in the voice storage unit 103, and the voice signal is reproduced and output with “55dBA”. It will be a bit different.
- the voice information importance level determination unit 206 displays the importance level definition information shown in FIG. 8 (b). By referring to, the importance of the input voice is determined as “5”.
- the speech identification result output processing unit 110 refers to the output processing method definition information shown in FIG. 8A, and determines an output processing method corresponding to the received importance determination result.
- the voice identification result output is stored in the voice storage unit, and the voice signal is reproduced and output at “70 dBA”. It will be.
- FIG. 9 (a) a user wearing the voice identification device 100a according to the second embodiment stops at an intersection where there is a crosswalk, and the car 300 enters the intersection while sounding a horn. Then, the state of being shown is shown.
- the voice identification device 100a receives the input voice "car crash in this situation.
- the importance level of the input speech is low (importance level “2”) based on the importance level definition information shown in FIG. 8 (b).
- the speech identification result is output as "55dBA”.
- the voice identification device 100a keeps the audio playback volume of the integrated portable headphone stereo and keeps the voice identification result at a volume lower than the audio volume! You can make playback output.
- “car horn” is input to the voice identification device 100a as the voice around the user
- “walking” is input to the voice identification device 100a as the user's walking situation. It is considered to be acquired.
- the voice identification device 100a determines the importance of the input voice “car horn” in this situation, the importance of the input voice is determined from the importance definition information shown in FIG. 8 (b). Is determined to be high (importance “5”), and the speech identification device 100a outputs the speech identification result at “70dBA” from the output processing method definition information shown in FIG. 8 (a).
- the voice identification device 100a lowers the audio playback volume of the integrated portable headphone stereo so that it is louder than the audio volume! Even if you do it ⁇ .
- the voice identification device 100a By the operation of the voice identification device 100a as described above, a user who is moving on foot can be Car horn is important for the purpose of preventing the user from coming into contact with the car by continuing to walk without being aware of the approach of the car if the walking situation is “walking”.
- the voice recognition result can be reproduced and output at a high volume, and if the walking situation is “stopped”, the possibility of such an accident is low, so the degree of importance is low. Therefore, it is possible to reproduce and output the voice identification result at a low volume.
- collation unit 104 of the voice identification device determines that the input voice is most similar to the "announcement voice in the vehicle notifying the arrival at the station" The following processing is performed.
- the information importance level judgment unit 206 judges that the importance level of the input voice is high, that is, “5”, and the voice identification result output processing unit uses a sound as an output processing method corresponding to the importance level “5”. Volume setting processing is performed so that the audio signal stored in the voice storage unit is reproduced and output at “70 dBA”, and this is reproduced and output as an audio identification result output.
- the speech information importance level determination unit determines that the importance level of the input speech is relatively low, that is, “2”, and the voice identification result output processing unit determines the importance level.
- the sound signal stored in the sound storage unit is set to ⁇ 55 dB Aj so that it can be played back and output, and this is played back as a voice identification result output. .
- the above-mentioned operation of the voice identification device prevents over-traveling when the user is walking on the road when the "announcement in the vehicle notifying the arrival of the station" is "walking ability ⁇ stopped". It is thought that the importance is high for the purpose of doing so, so it can be played back and output at a high volume. It can be played back at a low volume, and the voice identification result can be output in an identification result output format according to the degree of importance that changes depending on the user's walking situation. It is possible to
- the collation unit 104 determines the importance level of the input speech for the similarity determination result determined by the matching unit 104, Based on the determination result, the voice identification result output processing unit 110 can add a process corresponding to the output form to the input voice and output it as a voice identification result. Can be reliably transmitted according to the importance of the input voice information that changes depending on the operation status of the.
- the user motion acquisition unit realized by a pedometer or the like acquires the user's walking situation, and based on the walking situation, the voice information importance determination unit
- the example of determining the information importance level has been described, it is also possible to specify the user's operation status from the information related to the key operation of the mobile phone and the button operation of the headphone stereo.
- the configuration of the voice identification device integrated with the headphone stereo or the mobile phone in use by the user has been described as an example.
- the configuration is integrated with these devices! / It can also be realized by an independent configuration.
- the output reflecting the importance level depending on the voice arrival direction by using the importance level definition information that takes into account the voice arrival direction, the output reflecting the importance level depending on the voice arrival direction. It is easily possible to determine the form.
- the voice identification device has been described on the assumption that it is used in a highly closed space such as the interior of a car or a portable headphone stereo.
- the user's breathing movement is detected, and the detected breathing movement is suspicious when the input sound breaks the glass window when the user is determined to be sleeping.
- the detected breathing movement is suspicious when the input sound breaks the glass window when the user is determined to be sleeping.
- the voice identification device can reliably transmit voice information important to the user according to the degree of importance that changes depending on the user's operation status, and is intended to assist the user in driving safely.
- Safety assistance devices for mobile phones, information terminal devices such as mobile phones that are intended to provide information on the surroundings to users who are walking or traveling by train, or headphone stereos equipped with this device Can be applied.
- it is also useful as a security device installed in homes and offices for the purpose of crime prevention and accident prevention.
Abstract
Description
Claims
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/632,716 US7616128B2 (en) | 2004-07-23 | 2005-06-13 | Audio identifying device, audio identifying method, and program |
JP2006528468A JP3913771B2 (ja) | 2004-07-23 | 2005-06-13 | 音声識別装置、音声識別方法、及びプログラム |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2004215139 | 2004-07-23 | ||
JP2004-215139 | 2004-07-23 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2006011310A1 true WO2006011310A1 (ja) | 2006-02-02 |
Family
ID=35786064
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2005/010800 WO2006011310A1 (ja) | 2004-07-23 | 2005-06-13 | 音声識別装置、音声識別方法、及びプログラム |
Country Status (3)
Country | Link |
---|---|
US (1) | US7616128B2 (ja) |
JP (1) | JP3913771B2 (ja) |
WO (1) | WO2006011310A1 (ja) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007243493A (ja) * | 2006-03-07 | 2007-09-20 | Sanyo Electric Co Ltd | 携帯機器 |
JP2008039856A (ja) * | 2006-08-01 | 2008-02-21 | Yamaha Corp | 電子楽器システム |
JP2009232104A (ja) * | 2008-03-21 | 2009-10-08 | Fujitsu Ltd | 音量抑制システムおよび携帯端末装置 |
JP2010510690A (ja) * | 2006-11-20 | 2010-04-02 | パナソニック株式会社 | 音を検出するための装置および方法 |
JP2011170282A (ja) * | 2010-02-22 | 2011-09-01 | Toshiba Corp | 再生装置および再生方法 |
JP2012042465A (ja) * | 2010-08-17 | 2012-03-01 | Honda Motor Co Ltd | 音源方向推定装置及び音源方向推定方法 |
JP2014066537A (ja) * | 2012-09-25 | 2014-04-17 | Zenrin Datacom Co Ltd | 端末装置、経路案内方法およびコンピュータプログラム |
CN107709079A (zh) * | 2015-06-02 | 2018-02-16 | 凯莱汽车公司 | 在车辆中使用的用于检测外部事件的系统和方法 |
JP2018527857A (ja) * | 2015-08-07 | 2018-09-20 | シーラス ロジック インターナショナル セミコンダクター リミテッド | 音響装置における再生管理のためのイベント検出 |
JP2018528485A (ja) * | 2015-07-24 | 2018-09-27 | オロサウンド | 能動型雑音制御装置 |
CN110176231A (zh) * | 2018-02-19 | 2019-08-27 | 株式会社东芝 | 音响输出系统、音响输出方法及存储介质 |
JP2020047128A (ja) * | 2018-09-21 | 2020-03-26 | パイオニア株式会社 | 情報処理装置、情報処理方法、情報処理プログラム、及び記憶媒体 |
JP2020047130A (ja) * | 2018-09-21 | 2020-03-26 | パイオニア株式会社 | 情報処理装置、情報処理方法、情報処理プログラム、及び記憶媒体 |
WO2022149360A1 (ja) * | 2021-01-05 | 2022-07-14 | 菱洋エレクトロ株式会社 | 触覚刺激を与える身体装着具 |
Families Citing this family (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080140240A1 (en) * | 2006-12-12 | 2008-06-12 | White Robert Mccall | Vehicular system for playing audio files |
KR101138396B1 (ko) | 2007-09-11 | 2012-04-26 | 삼성전자주식회사 | Iptv 단말기에서 컨텐츠 재생 방법 및 장치 |
KR100930060B1 (ko) * | 2008-01-09 | 2009-12-08 | 성균관대학교산학협력단 | 신호 검출 방법, 장치 및 그 방법을 실행하는 프로그램이기록된 기록매체 |
GB2466242B (en) | 2008-12-15 | 2013-01-02 | Audio Analytic Ltd | Sound identification systems |
US9286911B2 (en) * | 2008-12-15 | 2016-03-15 | Audio Analytic Ltd | Sound identification systems |
US9473859B2 (en) | 2008-12-31 | 2016-10-18 | Starkey Laboratories, Inc. | Systems and methods of telecommunication for bilateral hearing instruments |
US8879763B2 (en) * | 2008-12-31 | 2014-11-04 | Starkey Laboratories, Inc. | Method and apparatus for detecting user activities from within a hearing assistance device using a vibration sensor |
US8706276B2 (en) | 2009-10-09 | 2014-04-22 | The Trustees Of Columbia University In The City Of New York | Systems, methods, and media for identifying matching audio |
JP5499633B2 (ja) * | 2009-10-28 | 2014-05-21 | ソニー株式会社 | 再生装置、ヘッドホン及び再生方法 |
JP2012075039A (ja) * | 2010-09-29 | 2012-04-12 | Sony Corp | 制御装置、および制御方法 |
US9384272B2 (en) * | 2011-10-05 | 2016-07-05 | The Trustees Of Columbia University In The City Of New York | Methods, systems, and media for identifying similar songs using jumpcodes |
DE102012016820A1 (de) * | 2012-08-24 | 2014-04-10 | GM Global Technology Operations, LLC (n.d. Ges. d. Staates Delaware) | Fahrerassistenzsystem und Betriebsverfahren dafür |
US9275136B1 (en) * | 2013-12-03 | 2016-03-01 | Google Inc. | Method for siren detection based on audio samples |
US9716939B2 (en) * | 2014-01-06 | 2017-07-25 | Harman International Industries, Inc. | System and method for user controllable auditory environment customization |
US9749762B2 (en) | 2014-02-06 | 2017-08-29 | OtoSense, Inc. | Facilitating inferential sound recognition based on patterns of sound primitives |
US9466316B2 (en) * | 2014-02-06 | 2016-10-11 | Otosense Inc. | Device, method and system for instant real time neuro-compatible imaging of a signal |
US10198697B2 (en) | 2014-02-06 | 2019-02-05 | Otosense Inc. | Employing user input to facilitate inferential sound recognition based on patterns of sound primitives |
US8874448B1 (en) * | 2014-04-01 | 2014-10-28 | Google Inc. | Attention-based dynamic audio level adjustment |
US10099636B2 (en) | 2015-11-27 | 2018-10-16 | Bragi GmbH | System and method for determining a user role and user settings associated with a vehicle |
US20170156000A1 (en) * | 2015-11-27 | 2017-06-01 | Bragi GmbH | Vehicle with ear piece to provide audio safety |
US10104460B2 (en) | 2015-11-27 | 2018-10-16 | Bragi GmbH | Vehicle with interaction between entertainment systems and wearable devices |
US9944295B2 (en) | 2015-11-27 | 2018-04-17 | Bragi GmbH | Vehicle with wearable for identifying role of one or more users and adjustment of user settings |
US10565834B2 (en) * | 2016-03-09 | 2020-02-18 | Hyundai Motor Company | Apparatus and method for emergency rescue service |
US10339933B2 (en) | 2016-05-11 | 2019-07-02 | International Business Machines Corporation | Visualization of audio announcements using augmented reality |
US10319228B2 (en) | 2017-06-27 | 2019-06-11 | Waymo Llc | Detecting and responding to sirens |
US11158310B2 (en) * | 2018-05-01 | 2021-10-26 | Dell Products, L.P. | Intelligent assistance for handling usage modes |
US10800409B2 (en) * | 2018-09-04 | 2020-10-13 | Caterpillar Paving Products Inc. | Systems and methods for operating a mobile machine using detected sounds |
US10789819B1 (en) * | 2019-03-06 | 2020-09-29 | Motorola Solutions, Inc. | System and method for voice announcement over communication path in siren system |
US20230347952A1 (en) * | 2020-02-26 | 2023-11-02 | Rowan University | Mobile sensor-based railway crossing safety device |
US11958505B2 (en) | 2020-07-21 | 2024-04-16 | Waymo Llc | Identifying the position of a horn honk or other acoustical information using multiple autonomous vehicles |
US11282382B1 (en) * | 2020-12-22 | 2022-03-22 | Waymo Llc | Phase lock loop siren detection |
US20230377459A1 (en) * | 2022-05-19 | 2023-11-23 | Alert The Mechanism LLC | System and method for emergency vehicle detection and alerting |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07182587A (ja) * | 1993-12-21 | 1995-07-21 | Honda Motor Co Ltd | 電気車両用擬似音発生装置 |
JPH1090406A (ja) * | 1996-09-13 | 1998-04-10 | Omron Corp | 警報装置 |
JPH10258688A (ja) * | 1997-03-19 | 1998-09-29 | Furukawa Electric Co Ltd:The | 車載用音声出力システム |
JP2002213985A (ja) * | 2001-01-15 | 2002-07-31 | Matsushita Electric Ind Co Ltd | オーディオ装置とナビゲーション装置 |
Family Cites Families (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4952931A (en) * | 1987-01-27 | 1990-08-28 | Serageldin Ahmedelhadi Y | Signal adaptive processor |
JP3163868B2 (ja) | 1993-09-20 | 2001-05-08 | 富士通株式会社 | 音選択再生装置 |
JPH07327295A (ja) | 1994-05-31 | 1995-12-12 | Junji Baba | サイレンや警報音が聞き取りやすくするための、音響機器用強制音量調節機 |
JP3779774B2 (ja) | 1996-08-22 | 2006-05-31 | 富士通テン株式会社 | ナビゲーション装置 |
JP3805923B2 (ja) * | 1999-04-28 | 2006-08-09 | 本田技研工業株式会社 | 車両通信装置 |
JP4337130B2 (ja) | 1999-06-10 | 2009-09-30 | マツダ株式会社 | 運転装置の制御装置 |
US6404351B1 (en) * | 2000-10-20 | 2002-06-11 | Dennis Beinke | Emergency vehicle warning system |
JP2002344268A (ja) | 2001-05-14 | 2002-11-29 | Matsushita Electric Ind Co Ltd | 音声再生装置 |
US6362749B1 (en) * | 2001-06-18 | 2002-03-26 | William E. Brill | Emergency vehicle detection system |
JP2003004521A (ja) | 2001-06-27 | 2003-01-08 | Kenwood Corp | 車外音の識別装置 |
US6812854B1 (en) * | 2001-11-05 | 2004-11-02 | Luke Edwin | Mirror mounted emergency vehicle alert system |
US6859147B2 (en) * | 2002-04-24 | 2005-02-22 | Salvatore Buscemi | System to warn of an approaching emergency vehicle |
JP3855840B2 (ja) | 2002-05-13 | 2006-12-13 | 株式会社デンソー | 車載ナビゲーション装置 |
JP2004020817A (ja) | 2002-06-14 | 2004-01-22 | Nisca Corp | 報知音変換装置 |
-
2005
- 2005-06-13 WO PCT/JP2005/010800 patent/WO2006011310A1/ja active Application Filing
- 2005-06-13 JP JP2006528468A patent/JP3913771B2/ja active Active
- 2005-06-13 US US11/632,716 patent/US7616128B2/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07182587A (ja) * | 1993-12-21 | 1995-07-21 | Honda Motor Co Ltd | 電気車両用擬似音発生装置 |
JPH1090406A (ja) * | 1996-09-13 | 1998-04-10 | Omron Corp | 警報装置 |
JPH10258688A (ja) * | 1997-03-19 | 1998-09-29 | Furukawa Electric Co Ltd:The | 車載用音声出力システム |
JP2002213985A (ja) * | 2001-01-15 | 2002-07-31 | Matsushita Electric Ind Co Ltd | オーディオ装置とナビゲーション装置 |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007243493A (ja) * | 2006-03-07 | 2007-09-20 | Sanyo Electric Co Ltd | 携帯機器 |
JP2008039856A (ja) * | 2006-08-01 | 2008-02-21 | Yamaha Corp | 電子楽器システム |
JP2010510690A (ja) * | 2006-11-20 | 2010-04-02 | パナソニック株式会社 | 音を検出するための装置および方法 |
JP2009232104A (ja) * | 2008-03-21 | 2009-10-08 | Fujitsu Ltd | 音量抑制システムおよび携帯端末装置 |
JP2011170282A (ja) * | 2010-02-22 | 2011-09-01 | Toshiba Corp | 再生装置および再生方法 |
JP2012042465A (ja) * | 2010-08-17 | 2012-03-01 | Honda Motor Co Ltd | 音源方向推定装置及び音源方向推定方法 |
JP2014066537A (ja) * | 2012-09-25 | 2014-04-17 | Zenrin Datacom Co Ltd | 端末装置、経路案内方法およびコンピュータプログラム |
CN107709079A (zh) * | 2015-06-02 | 2018-02-16 | 凯莱汽车公司 | 在车辆中使用的用于检测外部事件的系统和方法 |
JP2018528485A (ja) * | 2015-07-24 | 2018-09-27 | オロサウンド | 能動型雑音制御装置 |
JP2018527857A (ja) * | 2015-08-07 | 2018-09-20 | シーラス ロジック インターナショナル セミコンダクター リミテッド | 音響装置における再生管理のためのイベント検出 |
US11621017B2 (en) | 2015-08-07 | 2023-04-04 | Cirrus Logic, Inc. | Event detection for playback management in an audio device |
CN110176231A (zh) * | 2018-02-19 | 2019-08-27 | 株式会社东芝 | 音响输出系统、音响输出方法及存储介质 |
JP2019145944A (ja) * | 2018-02-19 | 2019-08-29 | 株式会社東芝 | 音響出力システム、音響出力方法及びプログラム |
JP7163035B2 (ja) | 2018-02-19 | 2022-10-31 | 株式会社東芝 | 音響出力システム、音響出力方法及びプログラム |
JP2020047128A (ja) * | 2018-09-21 | 2020-03-26 | パイオニア株式会社 | 情報処理装置、情報処理方法、情報処理プログラム、及び記憶媒体 |
JP2020047130A (ja) * | 2018-09-21 | 2020-03-26 | パイオニア株式会社 | 情報処理装置、情報処理方法、情報処理プログラム、及び記憶媒体 |
WO2022149360A1 (ja) * | 2021-01-05 | 2022-07-14 | 菱洋エレクトロ株式会社 | 触覚刺激を与える身体装着具 |
Also Published As
Publication number | Publication date |
---|---|
JPWO2006011310A1 (ja) | 2008-05-01 |
US20080001780A1 (en) | 2008-01-03 |
JP3913771B2 (ja) | 2007-05-09 |
US7616128B2 (en) | 2009-11-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP3913771B2 (ja) | 音声識別装置、音声識別方法、及びプログラム | |
JP6525175B2 (ja) | 通信システムおよび通信装置 | |
CN104658548B (zh) | 用外部声音向车辆驾乘人员警告外部事件并掩蔽车内谈话 | |
US7443284B2 (en) | Method and system for sending events between vehicles | |
WO2012097150A1 (en) | Automotive sound recognition system for enhanced situation awareness | |
CN110310618B (zh) | 车辆行驶环境声音的处理方法、处理装置和车辆 | |
CN104290653B (zh) | 一种基于车载音响系统的声音提示及报警系统 | |
JP2009290789A (ja) | 緊急通報システム、緊急通報方法 | |
WO2018163545A1 (ja) | 情報処理装置、情報処理方法及び記録媒体 | |
CN112995844A (zh) | 声音播放方法和声音播放装置 | |
JP3897946B2 (ja) | 緊急情報送信システム | |
JP4883039B2 (ja) | 緊急通報システム端末装置 | |
JP4632974B2 (ja) | 車載オーディオシステム | |
JP4080986B2 (ja) | 音声通知装置 | |
CN116783636A (zh) | 舱内音频滤波 | |
KR20220054504A (ko) | 차량 및 그 제어방법 | |
JP2005333599A (ja) | 携帯端末の事故防止付加機能動作システム及び方法 | |
JP2006144432A (ja) | 報知装置及び報知方法 | |
KR100341915B1 (ko) | 긴급차량 인식용 오디오장치 | |
JP6799615B2 (ja) | 情報処理装置、外部音再生方法、およびプログラム | |
JPH07327295A (ja) | サイレンや警報音が聞き取りやすくするための、音響機器用強制音量調節機 | |
JP2002271863A (ja) | 車載用電話装置 | |
CN114734914A (zh) | 车辆的警示提醒方法、装置、车辆及计算机可读存储介质 | |
KR100815884B1 (ko) | 이동 통신 장치의 사용자에게 경고하기 위한 방법 및시스템 | |
CN114162042A (zh) | 一种基于bp神经网络开发的自适应车用喇叭 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KM KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NA NG NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SM SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): GM KE LS MW MZ NA SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LT LU MC NL PL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG |
|
DPEN | Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed from 20040101) | ||
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
WWE | Wipo information: entry into national phase |
Ref document number: 2006528468 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 11632716 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase | ||
WWP | Wipo information: published in national office |
Ref document number: 11632716 Country of ref document: US |