CN1282470A - Voice recognition unit for audience measurement system - Google Patents
Voice recognition unit for audience measurement system Download PDFInfo
- Publication number
- CN1282470A CN1282470A CN98811419.4A CN98811419A CN1282470A CN 1282470 A CN1282470 A CN 1282470A CN 98811419 A CN98811419 A CN 98811419A CN 1282470 A CN1282470 A CN 1282470A
- Authority
- CN
- China
- Prior art keywords
- audience
- recognition unit
- program
- receiver
- sign
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04H—BROADCAST COMMUNICATION
- H04H60/00—Arrangements for broadcast applications with a direct linking to broadcast information or broadcast space-time; Broadcast-related systems
- H04H60/35—Arrangements for identifying or recognising characteristics with a direct linkage to broadcast information or to broadcast space-time, e.g. for identifying broadcast stations or for identifying users
- H04H60/45—Arrangements for identifying or recognising characteristics with a direct linkage to broadcast information or to broadcast space-time, e.g. for identifying broadcast stations or for identifying users for identifying users
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/41—Structure of client; Structure of client peripherals
- H04N21/422—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS]
- H04N21/42201—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS] biosensors, e.g. heat sensor for presence detection, EEG sensors or any limb activity sensors worn by the user
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/41—Structure of client; Structure of client peripherals
- H04N21/422—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS]
- H04N21/42203—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS] sound input device, e.g. microphone
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04H—BROADCAST COMMUNICATION
- H04H60/00—Arrangements for broadcast applications with a direct linking to broadcast information or broadcast space-time; Broadcast-related systems
- H04H60/56—Arrangements characterised by components specially adapted for monitoring, identification or recognition covered by groups H04H60/29-H04H60/54
- H04H60/58—Arrangements characterised by components specially adapted for monitoring, identification or recognition covered by groups H04H60/29-H04H60/54 of audio
Abstract
A member of an audience of a program to which a receiver is tuned is identified by a system which includes first and second microphones, a noise cancellation unit, and a voice recognition unit. One of the first and second microphones picks up relatively more of a voice signal from the member of the audience, and the other of the first and second microphones picks up relatively more of a sound signal from the receiver. The noise cancellation unit substantially eliminates the sound signal from the voice signal. The voice recognition unit identifies the member from the member's voice signal. The first and second microphones, the noise cancellation unit, and the voice recognition unit may be housed in a hand held housing or in a table top housing. The system may also include a passive people meter to passively identify the member, and a program to identify the program or channel to which the receiver is tuned.
Description
TECHNICAL FIELD OF THE INVENTION
The present invention relates generally to audience (audience) measuring system, the audience member of the program that the receiver of its identification such as television set, radio or computer is tuned to, and/or discern a program that is tuned to such as television set, radio or receiver.
Background of invention
Program supplier and advertiser are very interested in the audience of measuring program for a long time, because the audience measurement provides the data of estimating program and advertising results institute foundation.Adopted various known methods that estimation to whole audiences of the part of a program, a program and/or advertisement is provided.Except whole audiences, these methods provide the additional estimation of audience section important in the demography (for example, watching the man between some age and/or woman's quantity of the selected portion of given program).These methods comprise artificial and/or measure the seeing and/or listen custom of audience member of the selected family of statistics automatically, measure according to these then and estimate whole audiences.The audience member that will add up selected family usually is called answerer (panelist).
Audience is seen and/or is listened the measurement of custom generally to require three determining of separating: (1) determine in the selected family of statistics with monitored receiver be tuned to channel or radio station; (2) determine with receiver be tuned to during these channels or the radio station, on institute's adjusting channel, can obtain program; (3) determine with receiver be tuned to during the selected program, the kinsfolk and the visitor of appearance in the zone of receiver.
Determining for all three to influence the accuracy that audience is measured.In above-mentioned three are determined, determine that (3) perhaps influence most the accuracy that audience is measured, because generally in identification processing procedure, need the audience member of receiver to cooperate with each other.When requiring the member to participate in the identification processing, they make a mistake through regular meeting, and perhaps they have forgotten identification themselves or other audience member simply.For example, allow the audience member to discern themselves to represent that a kind of known system that they occur is " population measurement's device (PeopleMeter) "." population measurement's device " can be Long-distance Control and/or a plurality of buttons of being started by the audience member when they enter or withdraw from the monitored area.Yet the audience member often forgets at all and presses any button, and perhaps they make a mistake aspect the correct button pressing sometimes.
Overcome in the process of these problems in trial, developed several measuring systems.For example, at U.S. Patent number 3,056, in No. 135 (people such as Currey), describe a kind of system,, also utilize photographic recorder to come the composition (composition) of periodic logging audience in that it utilizes the switch that is provided with to count the number that enters, leaves and stay in the area to be monitored on the strategy.This method requires the operator to watch the photo record, and this had both invaded audience member's privacy, made the cost of measuring operation very high again.
These problems cause multiple suggestion for the spectator attendance of counting (but nonrecognition) in the area to be monitored and the passive unconstrained method that moves of following the tracks of them.For example, people such as Kiewit are at U.S. Patent number 4,644, describe counting in 509 and follow the tracks of ultrasonic wave sonar (ultrasonic sonar) system of audience quantity.Yet therefore the described nonrecognition audience member of system requires audience member manual identified oneself.
Other system, such as by Kiewit at U.S. Patent number 4,930, described in 011, rely on the audience member put on or carry and these audiences of unique identification member in corresponding person's electronics active label (active tag).No matter when the spectators audience member that puts on label appears in the monitored area, and these systems are all in response to label.Yet audience is often forgotten the label of putting on them, in this case these audiences of nonrecognition member.
Lu is at U.S. Patent number 4,858,000 and U.S. Patent number 5,031,228 in disclosed the audience member's who is used to discern computer image recognition system.This system employs video camera obtains audience member's face image, and computer subsystem is recognized the face in these images by these faces and the reference appearance that is stored in the database are compared.Spectators are also located and followed the tracks of in this system, and comprise the infrared illumination device that imperceptible controlled light quantity (level) is provided.Yet general such system is very expensive, and is difficult to install.
At U.S. Patent number 5,550, the system that discloses in 928 also uses image recognition to discern the audience member by people such as Lu.The human body that this system adds the member who is used to find audience is the algorithm of head then.In case find head, facial finding algorithm is provided by the face image representation that provides to two face recognition routines (Eigenface identification routine and model coupling routine).This system can be identified in the audience member that the area to be monitored moved and/or do not face video camera on every side.Yet it remains complicated and expensive.
Above-mentionedly determine that (1) and (2) can also influence the accuracy that audience is measured because only these determine to be not enough to discern receiver will be tuned to program.That is, do not knowing that through which program on the tuning in to channels be under the obtainable situation, determine add up receiver in the selected family be tuned to channel do not cause definite through tuner program.Do not know with the receiver of statistics in the selected family be tuned under the situation of which channel, by identical mark (token), determine not cause determining determining through tuned program at obtainable program on tuning in to channels.So, generally need these two kinds to determine, with the program of determining to be regulated by the audience member.Catch and be input to database about the information that can obtain program and this information so that cause catching that input makes mistakes with data with being complementary through tuning in to channels later on, it has influenced the accuracy that audience is measured unfriendly.
People such as Thomas are at U.S. Patent number 5,481, propose these problems about audience measurement system in No. 294, the tuning measuring system of wherein above-mentioned spectators detects and record embeds and identification will with receiver be tuned to the auxiliary code of channel.So,, so only need make one and determine if auxiliary code in the program of being watched, occurs.If in tuned program, can not obtain auxiliary code, from program, extract program marker figure (program signature) so, and compare in the reference marker figure that extracts previously.
The metering that is disclosed in present patent application (metering) device comprises non-invasive type (non-intrusive) transducer, and such as near the microphone receiver, it detects the auxiliary code in the audio frequency output of monitored receiver.If detect auxiliary code, can provide second microphone to pick up background noise so with microphone.The output of handling auxiliary code sensing microphone and noise sensing microphone is with subtracting background noise from the signal that is provided by auxiliary code sensing microphone.
This audience measurement system comprises also that as mentioned above " population measurement's device " is used for additional backup.
People such as Turner are at U.S. Patent number 4,907, have disclosed the system of the audience that is used for monitoring receiver in No. 079.The member of audience provides control command (such as channel selection) by the infrared unit that comprises keyboard to microprocessor.Can pass through traditional phone line, the information stores that will collect by microprocessor and send to central receiver.The moving detector that is coupled to microprocessor detects the audience member and when enters or leave other monitored area.The character generator that is coupled to microprocessor allows to communicate by character digital massage and the audience that for example is presented on the video screen.In addition, the voice-output unit that is coupled to microprocessor produces the voice signal send to the audience member.
Robot systems such as Turner comprise that also the voice-input unit that is coupled to microprocessor discerns themselves audibly to allow the audience member.Amplification, digitlization and the voice heard from the audience member that can be detected by microphone are provided to microprocessor.Microprocessor is carried out the power density analysis of spectrum to derive niche audience audience member's phonetic symbol figure to signal.The reference marker figure that these signature and front are stored during initialization system compares, with the identification spectators.Microprocessor is the normalization digital audio data also, and removes sampling by a small margin so that background noise influence minimum.During the system that disclosed in being enabled in people's patents such as Turner, initial display message is arranged on watches on the screen, it requires first name and last name that audience says them so that reference marker figure to be provided.Yet the speech recognition of oneself being carried out by it does not allow feasible (viable) audience measurement system.In addition, in multiple situation, it is not enough making the signal processing that is disclosed that influences minimum of background noise.
Purport of the present invention is in a kind of system that discerns the audience member of receiver and solve above-mentioned one or more problems.
Summary of the invention
According to a first aspect of the invention, a kind of system that is used to discern the audience member of receiver, it comprises first and second microphones, noise cancellation unit and voice recognition unit.Thereby arrange one of first and second microphones, first and second microphones to pick up relatively more more voice signal, and in first and second microphones another pick up the more relatively voice signals from receiver from the member of audience.The noise cancellation unit is coupled to first and second microphones, arranges noise cancellation unit basic voice signal of eliminating from voice signal.Voice recognition unit is coupled to the noise cancellation unit, and arranges the voice signal of voice recognition unit identification from the audience member.
According to another aspect of the present invention, system comprises microphone, voice recognition unit and program transducer.System identification with receiver be tuned to the member of audience of program.Microphone is set receives voice signal from the member.Voice recognition unit is coupled to microphone, and arranges according to voice signal identification member.The transducer that programs identification program.
According to a further aspect of the invention, system comprises passive population measurement's device, microphone, voice recognition unit and controller.System identification with receiver be tuned to the member of audience of program.Arrange passive population measurement's device so that this member's first identification to be provided by passive identification member.Microphone is set receives voice signal from the member.Voice recognition unit is coupled to microphone, and arranges to provide member's second identification by discern the member according to voice signal.Arrange controller to select at least one in first and second identifications so that discern the member.
According to a further aspect of the invention, the audience recognition unit comprise shell, the microphone that supports by shell and the voice recognition unit that supports and be coupled to microphone by shell.Arrange the member of voice recognition unit according to the identifier identification audience of saying by the member.Therefore, audience recognition unit identification with receiver be tuned to the member of audience of program.
Description of drawings
In conjunction with the accompanying drawings, from following detailed description of the present invention, these and other characteristics of the present invention and advantage will be apparent, wherein:
Fig. 1 illustrate be used to discern with television receiver be tuned to audience member's the system of the present invention of program;
Fig. 2 is wherein according to the present invention and comprise the block diagram of embodiment of the system of audience recognition unit (ARU);
Fig. 3 is the more detailed view of audience recognition unit as shown in Figure 2;
Fig. 4 is the diagrammatic sketch that is used for the noise cancellation circuit of audience recognition unit as shown in Figure 2;
Fig. 5 illustrates hand-hold type audience recognition unit as shown in Figure 3;
Fig. 6 illustrates Table top type audience recognition unit as shown in Figure 3;
Fig. 7 is the flow chart that is illustrated in the program of training period audience recognition unit execution as shown in Figure 3; With
Fig. 8 is the flow chart that is illustrated in the program of being carried out by audience recognition unit as shown in Figure 3 during audience member's the speech recognition.
Describe in detail
Fig. 1 illustrates audience measurement system 10, and it detects the member of the audience of the program that monitored receiver is selected.Audience measurement system 10 comprises audience recognition unit 12, and it is a hand-hold type as shown in Figure 1, but also can be the unit of any kind, such as the Table top type unit.Audience recognition unit 12 allows passive or discerns the audience member on one's own initiative, and can or can not produce reciprocation with receiver 14 in identification processing procedure.
So as shown in Figure 2, audience recognition unit 12 utilizes communication link 20 to provide its recognition data to elementary cell 18, wherein for example above-mentioned communication link 20 can be infrared ray or RF communication link.Program transducer 16 utilizes communication link 21, provides its program identification data to elementary cell 18, and wherein for example above-mentioned communication link 21 can be hard lead, but can be any other communication link on the other hand, such as infrared ray or RF communication link.Elementary cell 18 is collected from the audience recognition data of audience recognition unit 12, and from the program identification data of program transducer 16, and can these data be sent to central station 24 by public telephone system 22, it is collected from the class likelihood data of other families.
As shown in Figure 2, audience measurement system 10 also can comprise passive population measurement's device 26.For example, passive population measurement's device 26 can be according to passive the sort of of audience member in the area to be monitored that be identified in of the principle of above-mentioned U.S. Patent number 5,550,928.Passive meter 26 utilizes communication link 28 to provide its population recognition data to elementary cell 18, and wherein for example, above-mentioned communication link 28 can be a hardware, can be any other communication link but then, such as infrared ray or RF communication link.
Therefore, if audience measurement system 10 comprises audience recognition unit 12 and passive population measurement's device 26, under the situation that audience recognition unit 12 can not be done like this, available passive population measurement's device 26 passive identification audience members.On the other hand, under passive population measurement's device 26 can not passive identification audience member's situation, audience recognition unit 12 can be used to active or passive identification ground audience member.Another aspect can provide the output of audience recognition unit 12 and passive population measurement's device 26 simultaneously to the soft-decision logic, these output identification audience members of wherein above-mentioned soft-decision logical foundation.In any of these alternatives, the confidence level of audience can be accurately discerned in increase.
Be shown specifically audience recognition unit 12 among Fig. 3.Audience recognition unit 12 comprises first and second microphones 30 and 32.First and second microphones 30 and 32 are arranged in the audience recognition unit 12, thereby first and second microphones 30 and one of 32 are tending towards picking up relative more voice signal from the audience member, and in first and second microphones 30 and 32 another picks up relative more audio frequency output from monitored receiver.For example, can and open in 32 minutes first and second microphones 30, thereby on most of directions of audience recognition unit 12, first and second microphones 30 and one of 32 more approach the audience member, and in first and second microphones 30 and 32 another more approaches monitored receiver.Between first and second microphones 30 and 32, preferably separate 6.72 inches, though can adopt any other suitable distance of separation.In this embodiment of the present invention, first and second microphones 30 and 32 can point to relative direction.On the other hand, one of first and second microphones 30 and 32 or both can be arranged on the position away from audience recognition unit 12, thereby one of first and second microphones more approach the audience member, and in first and second microphones another more approaches through monitoring receiver.
Amplify the simulation of first microphone 30 by amplifier 34 and export, and should convert digital signal to through amplifying simulation output by analog-to-digital converter 36.Similarly, amplify the simulation of second microphone 32 by amplifier 38 and export, and this is converted to digital signal through amplifying simulation output by analog-to-digital converter 40.
Thereby be tending towards from the audience member, picking up relative more more voice signal even can adjust first and second microphones 30 and 32 position and orientation first and second microphones 30 and one of 32, and in first and second microphones 30 and 32 another is tending towards picking up relative more multitone and exports frequently from monitored receiver, and first and second microphones 30 and 32 also can pick up from audience member's audio frequency output and from the audio frequency output of receiver 14.In addition, first and second microphones 30 and 32 pick up other background noises except audio frequency output from receiver 14.In order to reduce or to eliminate influence from the background noise of receiver 14 and audio frequency output, the output that provides from analog-to-digital converter 36 and 40 to noise cancellation circuit (arrangement) 42.The output that noise cancellation circuit 42 is handled from analog-to-digital converter 36 and 40, thereby offset the audio frequency output of receiver 14, and the background noise that comes the voice signal that free audience member provides, thereby can discern these voice signals more easily.
S
p=aV
p+bV
r (1)
S wherein
pBe signal, V from first microphone 30
pBe since audience member's voice signal to contribution, V from the signal of first microphone 30
rBe since the output of the audio frequency of receiver 14 and other background noises to contribution from the signal of first microphone 30, a and b are that following parameter and a are greater than b.
Similarly, provide signal S according to following equation
r:
S
r=cV
p+dV
r (2)
S wherein
rBe the signal from second microphone 32, c and d are following parameters, and c is less than d.According to following equation, the available weights parameter is subtracted each other equation (1) and (2):
D=eS
p-S
r=(ae-c)·V
p+(be-d)·V
r (3)
D is that weighted difference and the e between equation (1) and (2) is following weighting parameters.
If a, b, c and d are first parameters of being determined by the characteristic of environment and first and second microphones 30 and 32, can select weighting parameters e so, thereby (be-d)=0, perhaps e=d/b＞1.Therefore, if (be-d)=0, difference D includes only signal V
pIn this case, provide signal V by following equation from equation (3)
p:
Because a, e and c are constants under given family condition, so these constants can be regarded as single constant k according to following equation:
Thereby signal provides signal V by following equation
p:
V
p=kD (6)
But receiver open do not have the audience member speaking during, can determine weighting parameters e with adapting to.During this, audience recognition unit 12 can find weighting parameters e automatically, thus D=0.So, weighting parameters e is inserted equation (5) and (6), to determine V
p, and by following voice recognition unit 44 processing V
p
This noise cancellation method supposes that first microphone 30 points to audience or more approaches audience than second microphone 32, and second microphone, 32 beacon receivers 14, perhaps more approaches receiver 14 than first microphone 30.For example, if audience recognition unit 12 is handheld units, first microphone 30 and second microphone 32 can be installed in audience recognition unit 12 so, thereby they are separated, and the direct directed audience recognition unit 12 of user, make the microphone 30 of winning point to audience and second microphone, 32 beacon receivers 14.Similarly, if audience recognition unit 12 is table-top unit, first microphone 30 and second microphone 32 can be installed in audience recognition unit 12 once more so, thereby they are separated, and the direct directed audience recognition unit 12 of user, make the microphone 30 of winning point to audience and second microphone, 32 beacon receivers 14.On the other hand, no matter audience recognition unit 12 is hand-hold types, or Table top type unit, all can pass through electric wire or other communication medium, first and second microphones 30 and 32 are connected to audience recognition unit 12, electric wire or other communication medium position that allows first microphone to be installed in to be close to audience and second microphone is installed in the position that is close to receiver 14 wherein.
Replace above-mentionedly to eliminated noise, noise cancellation circuit 42 can use phase cancellation.Notice that sound is propagated with about 1,120 foot per second aloft.Not equidistant, do not arrive these microphones simultaneously, and offseted or partly offseted at least in first and second microphones 30 and 32 sound that send (preferably separating 6.72 feet).According to the actual frequency of sound, and the space between first and second microphones 30 and 32, the out of phase angle produced.Noise cancellation circuit that excute phase offsets 42 these out of phase angles of utilization to be offseting the audio frequency output from receiver 14, and other background noises that come the voice signal that free audience member provides.In this embodiment of the present invention, first and second microphones 30 and 32 preferably are installed in the directional microphone on the same side of audience recognition unit 12.As long as the not direct beacon receiver 14 of first and second microphones 30 and 32, audience recognition unit 12 can have any orientation with respect to audience and receiver 14.
In this embodiment of the present invention, noise cancellation circuit 42 can be a form as shown in Figure 4.According to present embodiment, noise cancellation part 42 comprises that amplification is from the amplifier 60 of the signal of first microphone 30 with amplify amplifier 62 from the signal of second microphone 32.Because in fact amplifier 60 and 62 can be identical, so Fig. 4 only is shown specifically an amplifier.Always add the output of amplifier 60 and 62 by adder 64, thus the actual background noise of eliminating.Detection is from the output of adder 64, and converts it to DC level by detector 66, and provides to timer 68.
If the deletion of adder 64 is higher than predetermined threshold, triggers timer 68 so, and provide output, so that voice recognition unit 44 is linked in the output of adder 64 to switch 70.Voice recognition unit 44 provides inhibit signal by terminal 72, to keep timer 68 under its triggering state, until the scheduled time after voice recognition unit 44 last identification voice.
Also Tip element 54 can be coupled to controller 46.Controller 46 control Tip elements 54 so that prompting audience member provides their corresponding voice signal to first and second microphones 30 and 32, perhaps use keyboard 56, so that manually identify themselves.Tip element 54 can be arrange to the audience member provide can hear and/or the VODER of the audience recognition unit 12 of visual cues and/or image or video show (such as, LCD or LED).On the other hand, Tip element 54 can be microphone and/or receiver 14 screens, arranges them to provide to the audience member with the response and the reciprocation of audience recognition unit 12 and can hear and/or visual cues.
As shown in Figure 5, audience recognition unit 12 can be implemented as handheld unit 90.Handheld unit 90 comprises shell 92, and it covers the element of audience recognition unit 12, as shown in Figure 3.Shell 92 supports the light-emitting diode display 94 of the function that can carry out Tip element 54.Yet as mentioned above, on the other hand, Tip element 54 can be a VODER, and in this case, shell 92 can add the output microphone, to broadcast the audible voice prompting of VODER to the audience member.Light-emitting diode display 94 (and/or VODER) can be carried out the function except prompting.Also comprise IR transmitter 96 in the shell 92, to set up communication link 20 as shown in Figure 2.On the other hand, can pass through ultrasonic wave or RF link, hard lead or the like, set up communication link 20.Shell 92 also supports keyboard 98, and it can be a keyboard 56 as shown in Figure 3, is used to allow the audience member to import data.For example, the key that can be distributed in the predetermined number in the keyboard 98 to the member and the visitor of audience, thus if they can not discern them by themselves voice signal, they can identify themselves so.Shell 92 can comprise rechargeable battery, arranges above-mentioned battery with to audience recognition unit 12 power supply, and can charge all night or charging when not using audience recognition unit 12.Handheld unit 90 also has energising/cut-off button 95, so that switch handheld unit 90 also has LED97 and prepares identification audience member and visitor with expression handheld unit 90.
On the other hand, can implement audience recognition unit 12 as Table top type unit 100, as shown in Figure 6.Table top type unit 100 comprises shell 102, the element of dress audience recognition unit 12 in it, as shown in Figure 3.Shell 102 can support light-emitting diode display (figure does not show), so that carry out the function of Tip element 54.Yet as mentioned above, Tip element 54 can be VODER on the other hand, and in this case, shell 102 can add the output microphone to broadcast the audible voice prompting to audience member's VODER.Light-emitting diode display or VODER can be carried out other functions except prompting.Shell 102 can also in dress IF or RF transmitter (not shown) to set up communication link 20, as shown in Figure 2.On the other hand, can set up communication link 20 by ultrasound link, hard lead or the like.Shell 102 supports keyboard 104, and it can be a keyboard 56 as shown in Figure 3, is used for allowing the audience member to import data.For example, can distribute to the audience member to the key of predetermined number in 104, thereby if they can not discern them by their voice signal, they can manually identify themselves so.Table top type unit 100 can comprise rechargeable battery, arrange above-mentioned battery to come to 12 power supplies of audience recognition unit, and the latter that can charge all night charges when not in use.On the other hand, Table top type unit 100 can have power line, to power to audience recognition unit 12 from socket.In addition, Table top type unit 100 can make indicator light 106 and 108 energisings of sound detection indicator light.
During training mode, the controller 46 of audience recognition unit 12 can be implemented as shown in Figure 7 program 120 by flow chart.Executive program 120 during training mode, so that storage identifier word or the sound property relevant with the audience member.At training period, the audience member should suppose the position of the specified distance of leaving audience recognition unit 12.This audience member starts training by pressing suitable key or the button on the keyboard of audience recognition unit 12.
When starting training mode, thereby during executive program 120, audience recognition unit 12 determines whether to have spent the scheduled volume time in frame 122 after last audience member's activity.If audience recognition unit 12 determine scheduled volume in the time without any audience member activity, program 120 supposition training modes finish so, and program 120 withdraws from.If also do not have the scheduled volume time after last audience member activity, audience recognition unit 12 is waited for saying in the continuation of frame 124 places and is waken order so.Waking order should be the unique word that normally appears in the audio frequency of computer 14, perhaps word combination.The audience member should wake order to say to first and second microphones 30 and 32 in the normal sound.When order was waken in 12 detections of audience recognition unit, audience recognition unit 12 was said spectators frame 126 places prompting audience member and is selected to discern he oneself or the identifier word of herself.This identifier word can be spectators' a name.
Then, audience recognition unit 12 determines at frame 128 places whether the audience member has described identifier.If not, audience recognition unit 12 points out the audience member to say identifier word at frame 126 places once more so.If audience recognition unit 12 goes out to determine the audience member that at frame 128 oneself says identifier word, audience recognition unit 12 is suitably handled identifier word at frame 130 places and identifier word is stored in the memory 48 so.Flow process is got back to frame 122, wherein stops training mode, and perhaps another audience member imports the respective identifier word.
During recognition mode, the controller 46 of audience recognition unit 12 can be by flow chart enforcement program as shown in Figure 8.During recognition mode, executive program 140 is so that the member of identification audience.By pressing suitable key or the button on the keyboard of audience recognition unit 12, can start recognition mode.
When starting recognition mode, thereby during executive program 140, audience recognition unit 12 by pressing suitable key or the button on the keyboard of audience recognition unit 12, determines whether the audience member wishes to finish recognition mode at frame 142 places.If audience recognition unit 12 determines that the audience member wishes to finish recognition mode, program 140 withdraws from so.If audience recognition unit 12 determines that the audience member does not wish to finish recognition mode, audience recognition unit 12 is waited for saying at frame 144 places and is waken order so.The audience member should say to first and second microphones 30 and 32 with normal sound and wake order.When audience recognition unit 12 detects when waking order, audience recognition unit 12 is said his or his identifier word frame 146 places prompting audience member.
So audience recognition unit 12 determines at frame 148 places whether the audience member has described identifier word.If no, audience recognition unit 12 continues at frame 146 places to point out the audience member to say identifier word so.If audience recognition unit 12 determines that at frame 148 places the audience member has said identifier word, audience recognition unit 12 is compared identifier word at frame 150 places order voice recognition unit 44 with the vocabulary of identifier word in being stored in memory 48 so.
If audience recognition unit 12 is determined at frame 152 places that voice recognition unit 44 detects and is being said identifier word and be stored in coupling between one of identifier word in the memory 48, audience recognition unit 12 is said identifier word and the identification record of conduct match time in memory 48 in the storage of frame 154 places so, to propagate into elementary cell 18 immediately or later on.(on the other hand, audience recognition unit 12 can directly propagate into elementary cell 18 saying identifier word and time at frame 154 places.) if audience recognition unit 12 determines that at frame 152 places voice recognition unit 44 can not match one of identifier word that is stored in the memory 48 with saying identifier word, audience recognition unit 12 is attempted or with the recognition methods of another kind of form once more frame 156 places prompting audience member so.For example, prompting 140 can point out the audience member prompting audience member with the recognition methods of another kind of form (such as, by using keyboard 56 input identifier words) before scheduled volume is in the time, says his or his identifier word.On the other hand, perhaps in addition, if controller 46 determines that voice recognition unit 44 can not detect the coupling at frame 152 places, controller 46 can send to elementary cell 18 to message at frame 156 places so, and its expression can be discerned according to passive population measurement's device 26.At audience recognition unit 12 at frame 154 places saying identifier word and be stored in the memory 48 match time as identification record, perhaps attempt once more frame 156 places prompting audience member at audience recognition unit 12, perhaps use the identification of another kind of form, perhaps suitable message is sent to elementary cell 18 with in the identification of seeking from passive population measurement's device 26, or the like, flow process is got back to frame 142.
Using the advantage of waking order between the normal voice recognition phase is to simplify comparison process.That is, between normal audience recognition phase, each identifier word of saying is compared with each the reference identifier word in being stored in memory 48.Yet, only need to compare with a reference in memory 48 waking order.
Can arrange the frame 126 of Fig. 7 and the frame 146 of Fig. 8, so that point out each audience member to say code word (cue) except member's identifier word.The benefit that code word is coupled to identifier word is when comprising someone identifier word in the audio frequency output at computer 14 when but that people did not appear in the audience again, audience recognition unit 12 makes may be discerned this people improperly and reduce to minimum as audience member's possibility.For example, identifier word can be a name, and prompting can be the word that all audience members have, " enter " or word " withdraws from " such as word, or the like.So when entering (or leaving) area to be monitored, the audience member says his or his the name with code word coupling, as identifier word.For example, the member we can say " John enters " or " Mary enters ".On the other hand, code word can be unique to each audience member.Any layout has all reduced the word heard that is sent by receiver 14 is thought by mistake be the identifier word of being said by the audience member.
Some change of the present invention has been described above.For the personnel that put into practice technology of the present invention, other changes may take place.For example, in conjunction with the audience of measuring TV programme, the present invention is described.Yet the present invention also can be used for measuring the audience of the program of radio programming and other medium.
In addition, described program transducer 16 as with receiver be tuned to program and/or channel.Replace, can arrange audience recognition unit 12 to accept the program identification by 56 inputs of utilization keyboard by the audience member.
In addition, the function of Long-distance Control can be added audience recognition unit 12.
In addition, audience recognition unit 12 responsible single (rather than two), shotgun microphone closely.If like this, noise cancellation can be optional so.
In addition, can not re-use and wake order.
In addition, as mentioned above, passive population measurement's device 26 can be according to the content of No. 5,550,928, above-mentioned U.S. Patent number, passive the sort of of audience member in the area to be monitored that be identified in.Yet, passive population measurement's device 26 can be can passive identification audience member any kind of passive device.For example, passive population measurement's device 26 can use ultrasonic wave and/or infrared ray transducer or this transducer array, catching the image in audience zone, and can use Processing Algorithm, so that be identified in the member in the audience.
In addition, as mentioned above, passive population measurement's device 26 passive audience members that are identified in the area to be monitored.If passive population measurement's device 26 can not passively be identified in the member in the audience, it can arrange to count the audience number of members so, and prompting member's manual identified, equals count results until manual identified member's quantity.On the other hand, if passive population measurement's device 26 can not passively be identified in each member in the audience, it can arrange to count audience member's quantity so, and prompting to those can not passive identification member's manual identified.Another aspect can use counter, and need not passive population measurement's device 26.Counter can comprise the array of ultrasonic wave and/or infrared ray transducer or this transducer, or other devices, perhaps can detect the number in audience and can count the device of detected population quantity.So audience measurement system 10 can arrange to point out manual identified, equal count results until the size of population of manual identified.
In addition, Fig. 2 illustrates the audience measurement and equals 12, and program transducer 16 and passive population measurement's device 26 are as discrete element.Replace, audience measuring unit 12 can comprise program transducer 16 and/or passive population measurement's device 26.
Therefore, description of the invention only is used for explanation and tells those skilled in the art that to implement optimal mode of the present invention, can actually change its details, and do not depart from principle of the present invention, and keep proprietary use to all changes within the scope of the appended claims that fall.
Claims (72)
1. the member's of an audience that is used to discern receiver system is characterized in that, comprising:
First and second microphones, arrange them so that one of described first and second microphones pick up the more relatively voice signal from the described member of described audience, and in described first and second microphones another picks up the more relatively voice signal from described receiver;
Be coupled to the noise cancellation unit of described first and second microphones, wherein arrange described noise cancellation unit described voice signal of basic elimination from described voice signal; With
Be coupled to the voice recognition unit of described noise cancellation unit, wherein arrange described voice recognition unit to discern the described member of described audience according to described voice signal.
2. the system as claimed in claim 1 is characterized in that, also comprises the program transducer of arranging to discern the program that is received by described receiver.
3. system as claimed in claim 2 is characterized in that, described program transducer comprises the channel transducer.
4. system as claimed in claim 2 is characterized in that, described program transducer comprise arrange to detect with described receiver be tuned to program in the sign indicating number reader of program identification code.
5. system as claimed in claim 2 is characterized in that, described program transducer comprise arrange from described receiver be tuned to program extract the signature extractor of unique discernible signature.
6. system as claimed in claim 2 is characterized in that, described program transducer comprises arranges to allow described audience member to key in the keyboard of program or channel identication.
7. the system as claimed in claim 1, it is characterized in that, also comprise clock and memory, described memory is according to the described voice signal from described member, store described audience member's sign, and described memory stores is come the described member's of identification of self-clock the moment.
8. the system as claimed in claim 1 is characterized in that, described receiver is a television set.
9. the system as claimed in claim 1 is characterized in that, described receiver is a radio receiver.
10. the system as claimed in claim 1 is characterized in that, described receiver is the multimedia receiving system.
11. the system as claimed in claim 1 is characterized in that, also comprises arranging the keyboard of acceptance from described audience member's sign input.
12. the system as claimed in claim 1 is characterized in that, also comprises arranging the described audience member of prompting to say the suggestion device of described voice signal.
13. system as claimed in claim 12 is characterized in that, also comprises the program that identification is received by described receiver or the transducer of channel.
14. system as claimed in claim 12 is characterized in that, also comprises passive population measurement's device of arranging the described audience member of passive identification.
15. system as claimed in claim 14 is characterized in that, also comprises the program that identification is received by described receiver or the transducer of channel.
16. the system as claimed in claim 1 is characterized in that, described voice signal comprises described audience member's identifier.
17. the system as claimed in claim 1 is characterized in that, described voice signal comprises described audience member's identifier and code word.
18. the system as claimed in claim 1 is characterized in that, also comprises passive population measurement's device of arranging the described audience member of passive identification.
19. the system as claimed in claim 1 is characterized in that, comprises that also arrangement propagates into described member's sign and/or program identification the communication unit of remote spots.
20. system as claimed in claim 19 is characterized in that, arranges described communication unit by infrared signal, and described member's described sign is sent to described remote spots.
21. the system as claimed in claim 1 is characterized in that, described first and second microphones, described noise cancellation unit and described voice recognition unit are loaded in the hand-hold type shell.
22. the system as claimed in claim 1 is characterized in that, described first and second microphones, described noise cancellation unit and described voice recognition unit are loaded in the Table top type shell.
23. the system as claimed in claim 1 is characterized in that, along basic phase counter sense direction, and directed described first and second microphones.
24. the system as claimed in claim 1, it is characterized in that, described first microphone is installed on the position than the more close described audience of described second microphone, and described second microphone is installed on the position than the more close described receiver of described first microphone.
25. the system as claimed in claim 1, it is characterized in that, also comprise counter, display and artificial input loading, wherein arrange described voice recognition unit to provide prompting to described display, to point out described audience member to carry out manual identified, equal the count results that provides by described counter until the described number of members that so recognizes by the utilization manual input device.
26. one kind be used to discern with receiver be tuned to audience member's the system of program, it is characterized in that described system comprises:
The microphone of reception from described member's voice signal is set;
Be coupled to described member is discerned in described microphone and arrangement according to described voice signal voice recognition unit; With
Arrange the transducer of described program of identification or channel.
27. system as claimed in claim 26, it is characterized in that, also comprise and arrange storage and the corresponding memory of described member, and arrange described voice recognition unit to come to discern described member according to described voice signal and described comparative result with reference to identifying information with reference to identifying information.
28. system as claimed in claim 27 is characterized in that, arranges described transducer to discern described program according to the characteristic of described program.
29. system as claimed in claim 28 is characterized in that, described characteristic is the identification code that is embedded in the described program.
30. system as claimed in claim 28 is characterized in that, described characteristic is the unique identifiable marker figure that extracts from described program.
31. system as claimed in claim 26 is characterized in that, described receiver is a television set.
32. system as claimed in claim 26 is characterized in that, described receiver is a radio receiver.
33. system as claimed in claim 26 is characterized in that, described receiver is the multimedia receiving system.
34. system as claimed in claim 26 is characterized in that, also comprises the keyboard of arranging to receive from described member's sign input.
35. system as claimed in claim 34 is characterized in that, described sign input is described member's a sign.
36. system as claimed in claim 34 is characterized in that, described sign input is the sign of program or channel.
37. system as claimed in claim 26 is characterized in that, also comprises arranging the described member of prompting to say the suggestion device of described voice signal.
38. system as claimed in claim 37 is characterized in that, also comprises passive population measurement's device of arranging the described member of passive identification.
39. system as claimed in claim 26 is characterized in that, described voice signal comprises described member's identifier.
40. system as claimed in claim 26 is characterized in that, described voice signal comprises described member's identifier and code word.
41. system as claimed in claim 26 is characterized in that, also comprises passive population measurement's device of arranging the described member of passive identification.
42. system as claimed in claim 26 is characterized in that, also comprises the communication unit of arranging described member's described sign is propagated into remote spots.
43. system as claimed in claim 42 is characterized in that, arranges described communication unit to utilize infrared signal, and described member's described sign is propagated into described remote spots,
44. system as claimed in claim 26 is characterized in that, described microphone and described voice recognition unit are loaded in the hand-hold type shell.
45. system as claimed in claim 26 is characterized in that, described microphone and described voice recognition unit are loaded in the Table top type shell.
46. system as claimed in claim 26, it is characterized in that, also comprise counter, display and manual input device, wherein arrange described voice recognition unit to provide prompting to described display, pointing out described audience member to carry out manual identified, equal the count results that provides by described counter until the described number of members of identification like this by using described manual input device.
47. one kind be used to discern with receiver be tuned to audience member's the system of program, it is characterized in that described system comprises:
Arranging provides passive population measurement's device to described member's first sign by the described member of passive identification;
Setting is to receive the microphone from described member's voice signal;
Be coupled to described microphone and arrange and provide the voice recognition unit of described member's second sign by discern described member according to described voice signal; With
In described first and second signs of arrangement selection at least one is so that discern described member's controller.
48. system as claimed in claim 47 is characterized in that, described controller comprises arranges the described member of prompting to say the Tip element of described voice signal.
49. system as claimed in claim 48 is characterized in that, also comprises the transducer of arranging to discern described program or channel.
50. system as claimed in claim 47 is characterized in that, described controller comprises if described passive population measurement's device can not provide described first sign, arranges the described member of prompting to say the Tip element of described voice signal so.
51. system as claimed in claim 47 is characterized in that, if described voice recognition unit can not provide described second sign, arranges described controller to select described first sign so.
52. system as claimed in claim 47 is characterized in that, described voice signal comprises identifier.
53. system as claimed in claim 47 is characterized in that, described voice signal comprises identifier and code word.
54. system as claimed in claim 47 is characterized in that, also comprises the transducer of arranging to discern described program or channel.
55. system as claimed in claim 47 is characterized in that, comprises that also arrangement propagates into described member's described sign the communication unit of remote spots.
56. system as claimed in claim 55 is characterized in that, arranges described communication unit by infrared signal, and described member's described sign is propagated into described remote spots.
57. system as claimed in claim 47 is characterized in that, described microphone and described voice recognition unit are loaded in the hand-hold type shell.
58. system as claimed in claim 47 is characterized in that, described microphone and described voice recognition unit are loaded in the Table top type shell.
59. system as claimed in claim 47, it is characterized in that, also comprise counter, display and manual input device, wherein arrange described controller to provide prompting to described display, pointing out described audience member manually to identify, equal the count results that provides by described counter until the described member of identification like this by using described manual input device.
60. an identification with receiver be tuned to audience member's the audience recognition unit of program, it is characterized in that described audience recognition unit comprises:
Shell;
Microphone by described shell support; With
Support and be coupled to the voice recognition unit of described microphone by described shell, arrange described voice recognition unit to discern described member according to the identifier of saying by described member.
61. audience recognition unit as claimed in claim 60 is characterized in that, also comprises the Tip element that is supported by described shell, wherein arranges described Tip element to point out described member to take action.
62. audience recognition unit as claimed in claim 61 is characterized in that, also comprises the keyboard that is supported by described shell, wherein arranges described keyboard to allow described member to import data.
63. audience recognition unit as claimed in claim 62 is characterized in that, also comprises the communication unit that is supported by described shell, wherein arranges described communication unit so that described communication data is propagated into base station unit.
64. as the described audience recognition unit of claim 63, it is characterized in that, also comprise the clock and the memory that support by described shell, wherein said memory is stored described member's sign according to described identifier of saying, and described memory stores when discerning described member from moment of described clock.
65., it is characterized in that described identifier comprises word and code word as the described audience recognition unit of claim 64.
66. audience recognition unit as claimed in claim 60 is characterized in that, also comprises the keyboard that is supported by described shell, wherein arranges described keyboard to allow described member to import data.
67., it is characterized in that as the described audience recognition unit of claim 66, also comprise the communication unit that supports by described shell, wherein arrange described communication unit that data dissemination is arrived base station unit.
68. audience recognition unit as claimed in claim 60 is characterized in that, also comprises the communication unit that is supported by described shell, wherein arranges described communication unit that data dissemination is arrived base station unit.
69. audience recognition unit as claimed in claim 60, it is characterized in that, also comprise the clock and the memory that support by described shell, wherein said memory is stored described member's sign according to described identifier of saying, and described memory stores when discerning described member from moment of described clock.
70. audience recognition unit as claimed in claim 60 is characterized in that described identifier comprises word and code word.
71. audience recognition unit as claimed in claim 60 is characterized in that, described audience recognition unit is a handheld unit.
72. audience recognition unit as claimed in claim 60 is characterized in that, described audience recognition unit is the Table top type unit.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US97469997A | 1997-11-20 | 1997-11-20 | |
| US08/974,699 | 1997-11-20 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN1282470A true CN1282470A (en) | 2001-01-31 |
Family
ID=25522351
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN98811419.4A Pending CN1282470A (en) | 1997-11-20 | 1998-06-09 | Voice recognition unit for audience measurement system |
Country Status (6)
| Country | Link |
|---|---|
| EP (1) | EP1032998A1 (en) |
| JP (1) | JP2001524776A (en) |
| CN (1) | CN1282470A (en) |
| AU (1) | AU7833898A (en) |
| CA (1) | CA2306095A1 (en) |
| WO (1) | WO1999027668A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102984559A (en) * | 2012-10-31 | 2013-03-20 | 上海尚恩华科网络科技股份有限公司 | Audience rating statistical system and method based on voice recognition |
| WO2017071453A1 (en) * | 2015-10-28 | 2017-05-04 | 宇龙计算机通信科技(深圳)有限公司 | Method and device for voice recognition |
| CN106658183A (en) * | 2015-10-30 | 2017-05-10 | 北京国双科技有限公司 | Method and device for popping out video login dialog box |
Families Citing this family (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1079615A3 (en) * | 1999-08-26 | 2002-09-25 | Matsushita Electric Industrial Co., Ltd. | System for identifying and adapting a TV-user profile by means of speech technology |
| DE60120062T2 (en) * | 2000-09-19 | 2006-11-16 | Thomson Licensing | Voice control of electronic devices |
| US20020178440A1 (en) * | 2001-03-28 | 2002-11-28 | Philips Electronics North America Corp. | Method and apparatus for automatically selecting an alternate item based on user behavior |
| US8091100B2 (en) | 2001-06-18 | 2012-01-03 | The Nielsen Company (Us), Llc | Prompting of audience member identification |
| FR2828604A1 (en) * | 2001-08-13 | 2003-02-14 | Scm Microsystems Gmbh | Television programme audience measurement has audience digital word transmission to processing center and viewer presence verification using visual warning/spectator confirmation system |
| EP1576815A1 (en) | 2002-12-11 | 2005-09-21 | Nielsen Media Research, Inc. | Detecting a composition of an audience |
| US7203338B2 (en) | 2002-12-11 | 2007-04-10 | Nielsen Media Research, Inc. | Methods and apparatus to count people appearing in an image |
| JP3727927B2 (en) * | 2003-02-10 | 2005-12-21 | 株式会社東芝 | Speaker verification device |
| WO2005034395A2 (en) | 2003-09-17 | 2005-04-14 | Nielsen Media Research, Inc. | Methods and apparatus to operate an audience metering device with voice commands |
| US8023882B2 (en) | 2004-01-14 | 2011-09-20 | The Nielsen Company (Us), Llc. | Portable audience measurement architectures and methods for portable audience measurement |
| WO2006036150A1 (en) | 2004-09-28 | 2006-04-06 | Nielsen Media Research, Inc | Data classification methods and apparatus for use with data fusion |
| US7631324B2 (en) | 2005-06-08 | 2009-12-08 | The Nielsen Company (Us), Llc | Methods and apparatus for indirect illumination in electronic media rating systems |
| MX2007015979A (en) | 2006-03-31 | 2009-04-07 | Nielsen Media Res Inc | Methods, systems, and apparatus for multi-purpose metering. |
| CN103593562A (en) | 2006-07-12 | 2014-02-19 | 奥比融公司 | Methods and systems for compliance confirmation and incentives |
| JP2010534366A (en) * | 2007-07-20 | 2010-11-04 | ダブル・フュージョン・インコーポレイテッド | Measuring audiences for monetizing displayable content |
| WO2009034576A2 (en) * | 2007-09-11 | 2009-03-19 | Wavebreak Technologies Ltd | Presence detector and method for estimating an audience |
| US8411963B2 (en) | 2008-08-08 | 2013-04-02 | The Nielsen Company (U.S.), Llc | Methods and apparatus to count persons in a monitored environment |
| US9124769B2 (en) | 2008-10-31 | 2015-09-01 | The Nielsen Company (Us), Llc | Methods and apparatus to verify presentation of media content |
| US8677385B2 (en) | 2010-09-21 | 2014-03-18 | The Nielsen Company (Us), Llc | Methods, apparatus, and systems to collect audience measurement data |
| US8620088B2 (en) | 2011-08-31 | 2013-12-31 | The Nielsen Company (Us), Llc | Methods and apparatus to count people in images |
| US9332363B2 (en) | 2011-12-30 | 2016-05-03 | The Nielsen Company (Us), Llc | System and method for determining meter presence utilizing ambient fingerprints |
| US8769557B1 (en) | 2012-12-27 | 2014-07-01 | The Nielsen Company (Us), Llc | Methods and apparatus to determine engagement levels of audience members |
| US9301070B2 (en) | 2013-03-11 | 2016-03-29 | Arris Enterprises, Inc. | Signature matching of corrupted audio signal |
| US9307337B2 (en) | 2013-03-11 | 2016-04-05 | Arris Enterprises, Inc. | Systems and methods for interactive broadcast content |
| US9277276B1 (en) | 2014-08-18 | 2016-03-01 | Google Inc. | Systems and methods for active training of broadcast personalization and audience measurement systems using a presence band |
| EP3851792A1 (en) * | 2016-06-24 | 2021-07-21 | The Nielsen Company (US), LLC | Invertible metering apparatus and related methods |
| US9984380B2 (en) | 2016-06-24 | 2018-05-29 | The Nielsen Company (Us), Llc. | Metering apparatus and related methods |
| US10178433B2 (en) | 2016-06-24 | 2019-01-08 | The Nielsen Company (Us), Llc | Invertible metering apparatus and related methods |
| US10405036B2 (en) | 2016-06-24 | 2019-09-03 | The Nielsen Company (Us), Llc | Invertible metering apparatus and related methods |
| KR102418952B1 (en) * | 2017-08-31 | 2022-07-08 | 삼성전자주식회사 | Home appliance having voice recognizing function |
| CN110166816B (en) * | 2019-05-29 | 2020-09-29 | 上海松鼠课堂人工智能科技有限公司 | Video editing method and system based on voice recognition for artificial intelligence education |
| US11711638B2 (en) | 2020-06-29 | 2023-07-25 | The Nielsen Company (Us), Llc | Audience monitoring systems and related methods |
| US11860704B2 (en) | 2021-08-16 | 2024-01-02 | The Nielsen Company (Us), Llc | Methods and apparatus to determine user presence |
| US11758223B2 (en) | 2021-12-23 | 2023-09-12 | The Nielsen Company (Us), Llc | Apparatus, systems, and methods for user presence detection for audience monitoring |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4907079A (en) * | 1987-09-28 | 1990-03-06 | Teleview Rating Corporation, Inc. | System for monitoring and control of home entertainment electronic devices |
| US5267323A (en) * | 1989-12-29 | 1993-11-30 | Pioneer Electronic Corporation | Voice-operated remote control system |
| US5303299A (en) * | 1990-05-15 | 1994-04-12 | Vcs Industries, Inc. | Method for continuous recognition of alphanumeric strings spoken over a telephone network |
| US5481294A (en) * | 1993-10-27 | 1996-01-02 | A. C. Nielsen Company | Audience measurement system utilizing ancillary codes and passive signatures |
-
1998
- 1998-06-09 EP EP98926519A patent/EP1032998A1/en not_active Withdrawn
- 1998-06-09 JP JP2000522692A patent/JP2001524776A/en active Pending
- 1998-06-09 AU AU78338/98A patent/AU7833898A/en not_active Abandoned
- 1998-06-09 CN CN98811419.4A patent/CN1282470A/en active Pending
- 1998-06-09 CA CA002306095A patent/CA2306095A1/en not_active Abandoned
- 1998-06-09 WO PCT/US1998/012034 patent/WO1999027668A1/en not_active Application Discontinuation
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102984559A (en) * | 2012-10-31 | 2013-03-20 | 上海尚恩华科网络科技股份有限公司 | Audience rating statistical system and method based on voice recognition |
| WO2017071453A1 (en) * | 2015-10-28 | 2017-05-04 | 宇龙计算机通信科技(深圳)有限公司 | Method and device for voice recognition |
| CN106658183A (en) * | 2015-10-30 | 2017-05-10 | 北京国双科技有限公司 | Method and device for popping out video login dialog box |
| CN106658183B (en) * | 2015-10-30 | 2019-09-06 | 北京国双科技有限公司 | Pop up the method and device of video logon dialog frame |
Also Published As
| Publication number | Publication date |
|---|---|
| EP1032998A1 (en) | 2000-09-06 |
| CA2306095A1 (en) | 1999-06-03 |
| WO1999027668A1 (en) | 1999-06-03 |
| JP2001524776A (en) | 2001-12-04 |
| AU7833898A (en) | 1999-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1282470A (en) | Voice recognition unit for audience measurement system | |
| EP1133090B1 (en) | Apparatus for identifying the members of an audience which are watching a television programme or are listening to a broadcast programme | |
| US4769697A (en) | Passive television audience measuring systems | |
| EP2654224B1 (en) | Methods and apparatus to collect audience information associated with a media presentation | |
| US6467089B1 (en) | Audience measurement system incorporating a mobile handset | |
| US20060294537A1 (en) | Fingerprint-based technique for surveying an audience | |
| CN101278568B (en) | Display device on/off detection methods and apparatus | |
| US20080148309A1 (en) | Audience measurement system and monitoring devices | |
| US8631427B2 (en) | Audience detection | |
| CN1505408A (en) | Coded/non-coded program audience measurement system | |
| WO1991011062A1 (en) | Method and apparatus for broadcast media audience measurement | |
| US20130227595A1 (en) | Methods and apparatus to identify audience members | |
| CN1505291A (en) | Audience measurement system for digital television | |
| CN107547945A (en) | The method and apparatus that audio sensor selection is performed in audience measurement devices | |
| CN106792253A (en) | Sound effect treatment method and system | |
| CN104202694A (en) | Method and system of orientation of voice pick-up device | |
| US20020023142A1 (en) | Methods and apparatus for retrieving a web site based on broadcast radio or television programming | |
| CN112688841A (en) | Intelligent home background music control system | |
| JP3696869B2 (en) | Content provision system | |
| JP2004164589A (en) | Content providing system | |
| CN211454625U (en) | Non-civilized behavior recognition warning device | |
| JP6490293B1 (en) | Listener authentication system | |
| MXPA00004781A (en) | Voice recognition unit for audience measurement system | |
| US7395062B1 (en) | Remote sensing system | |
| AU756584B2 (en) | Identification of a viewer selected television program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |