[go: up one dir, main page]

WO1995006309A1 - Systeme de commande a distance a fonctionnement vocal - Google Patents

Systeme de commande a distance a fonctionnement vocal Download PDF

Info

Publication number
WO1995006309A1
WO1995006309A1 PCT/US1994/009544 US9409544W WO9506309A1 WO 1995006309 A1 WO1995006309 A1 WO 1995006309A1 US 9409544 W US9409544 W US 9409544W WO 9506309 A1 WO9506309 A1 WO 9506309A1
Authority
WO
WIPO (PCT)
Prior art keywords
voice
signal
remote control
accordance
analog
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/US1994/009544
Other languages
English (en)
Inventor
George H. Fischer
Mark P. Fortunato
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Voice Powered Technology International Inc
Original Assignee
Voice Powered Technology International Inc
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Voice Powered Technology International Inc filed Critical Voice Powered Technology International Inc
Priority to AU76371/94A priority Critical patent/AU7637194A/en
Publication of WO1995006309A1 publication Critical patent/WO1995006309A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10K—SOUND-PRODUCING DEVICES; METHODS OR DEVICES FOR PROTECTING AGAINST, OR FOR DAMPING, NOISE OR OTHER ACOUSTIC WAVES IN GENERAL; ACOUSTICS NOT OTHERWISE PROVIDED FOR
    • G10K11/00—Methods or devices for transmitting, conducting or directing sound in general; Methods or devices for protecting against, or for damping, noise or other acoustic waves in general
    • G—PHYSICS
    • G08—SIGNALLING
    • G08C—TRANSMISSION SYSTEMS FOR MEASURED VALUES, CONTROL OR SIMILAR SIGNALS
    • G08C23/00—Non-electrical signal transmission systems, e.g. optical systems
    • G08C23/02—Non-electrical signal transmission systems, e.g. optical systems using infrasonic, sonic or ultrasonic waves
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B11/00—Transmission systems employing sonic, ultrasonic or infrasonic waves
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B1/00—Details of transmission systems, not covered by a single one of groups H04B3/00 - H04B13/00; Details of transmission systems not characterised by the medium used for transmission
    • H04B1/06—Receivers
    • H04B1/16—Circuits
    • H04B1/20—Circuits for coupling gramophone pick-up, recorder output, or microphone to receiver
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Definitions

  • the present invention relates to systems for controlling a device by using voice recognition of spoken commands, and more particularly to systems of that type in which the commands are communicated to the controlled device by wireless transmission.
  • the wireless remote controls transmit signals to the controlled appliance or other device in response to the pressing of appropriate buttons by a user.
  • the controlled devices receive such signals, decode them and perform a function based on the specific signal received.
  • the transmitted signals are usually digital in nature, and typically are transmitted using infrared light transmission. Alternatively, radio frequency transmission is used in some systems.
  • Co-pending application Serial No. 07/915,112 describes a system utilizing a voice operated, hand- held, battery powered portable remote control device for controlling remote electronic devices by the transmission of infrared control signals.
  • the voice operated remote control device accepts voice commands spoken by the user, performs voice recognition pattern matching on the spoken word by comparing the same against pretrained templates to determine the appropriate corresponding command, determines the specific infrared remote control code or set of codes that represent the function corresponding to the command, and transmits the infrared remote control codes to the electronic device to be controlled.
  • the voice operated remote control device can be operated by multiple users, either by voice or by manual control of the selected function on the remote control device.
  • the voice commands can represent either real time commands, which are transmitted immediately after the determination of the voice command, or programmed delay events which delay the transmission of the remote control codes or set of remote control codes for a preset period of time specified by the user.
  • Co-pending application Serial No. 07/915,938 describes a method and apparatus for improving the quality of voice templates for speaker dependent voice recognition devices, through the use of two word templates for each word in a vocabulary and qualification of the word templates.
  • the apparatus takes the result of the comparison and performs an evaluation to determine the relative quality of the word templates. If word template quality is deemed to be less than an acceptable level, the apparatus requests the user to retrain the specific word in order to improve the recognition accuracy rate of the apparatus. Both resulting templates are later used during voice recognition.
  • the system includes a noise rejection system using noise templates during a pattern matching process to significantly reduce the required processing power over commonly used digital noise filters.
  • the system further includes means for correcting voice recognition errors through use of a voice command. Correcting errors by means of voice commands enables the user to correct errors while speaking into the apparatus, without interrupting the flow of the voice process. The fact that an error occurred on a particular word within a particular word group is used to assist in replacing the word template.
  • Co-pending application Serial No. 07/915,114 describes a method and apparatus whereby a remote control device executes system control functions in response to a single user command request.
  • the apparatus self-configures based on the configuration of the equipment to be used.
  • System control functions which can consist of one or more controls from a single remote control or from multiple remote controls, are controlled by transmitting a string or sequence of commands from the apparatus to single or to multiple pieces of equipment for control of that equipment.
  • the system control functions are selected by the user by activation of a single key representing the specific function.
  • the apparatus self-configures, determining what system functions are applicable based on the equipment which the user has and based on the functions learned from the user's
  • the approach exemplified by the three co-pending applications identified above allows the use of voice recognition technology with controlled devices that were not designed for such technology.
  • the voice remote control mimics the traditional remote control in the way in which it communicates with the controlled device.
  • this requires the addition of a significantly higher level of technology in the remote control device itself, much of which is already present in the controlled device.
  • virtually all television sets and VCRs utilize 8-bit microcontrollers with on-board ROM and RAM memory capacity.
  • Such devices often include some type of display. Many newer television sets have on ⁇ screen displays. All such devices have power supplies for powering the electronics.
  • a voice activated remote control must duplicate all such components.
  • voice activated remote control devices in order to mimic the digital remote control signals, such voice activated remote control devices must have the ability to either "learn” the control signals or have a substantial library of existing codes built into the ROM thereof.
  • the remote control device would only have to transmit the voice signal without the need for the sophisticated voice activated remote controls.
  • the remote control device would only have to convert the voice signal from the microphone into a format that can be transmitted. The result would be a relatively simple remote control device in which multiple buttons and the microcontroller used to interpret button operation would not be needed.
  • the controlled device would desirably include the voice recognition apparatus, so as to utilize the existing microprocessing and memory capacities of the controlled device with only minor additions thereto and so as to greatly simplify the remote control device.
  • the present invention provides a voice operated remote control system in which a remote control device responds to voice commands from the user to transmit representations of the voice commands to a controlled device, in wireless fashion.
  • the controlled device responds to the transmitted representations by undergoing a voice recognition process in an attempt to recognize the voice commands of the user. Recognized voice commands are used to produce action routines for specific functions to be performed by the controlled device.
  • voice recognition apparatus within the controlled device enables the remote control device to be of simple and inexpensive design.
  • the remote control device need only include apparatus such as a microphone for converting the voice commands into analog audio signals and apparatus for modulating or otherwise processing such signals for transmission to the controlled device.
  • an audio wireless remote control device includes a microphone for converting voice commands into analog audio signals. Following amplification of such signals by an audio amplifier, the signals are applied to a voltage controlled oscillator or other appropriate circuit for frequency modulation, prior to application to a driver and an infrared transmitter.
  • the infrared transmitter transmits the frequency modulated audio signal to the remotely located controlled device, in wireless fashion.
  • the remote control device is battery powered and includes a push-to-talk switch for conserving battery power by turning on the circuitry only when the user desires to enter a voice command into the remote control device.
  • An audio receiver located within the controlled device includes an infrared sensor for sensing the transmitted signals from the remote control device.
  • the sensed signals are amplified and filtered prior to application to a phase-locked loop receiver for demodulation of the frequency modulated signal.
  • the demodulated output of the phase-locked loop receiver is filtered and amplified to provide a voice signal.
  • the phase-locked loop receiver also provides a lock detect output to indicate when a transmitted signal has been received.
  • the voice signals from the audio receiver are applied to voice recognition apparatus within the controlled device.
  • the voice recognition apparatus comprises a microcontroller which may include an analog-to-digital converter, together with a microprocessor and ROM and RAM memories.
  • the analog- to-digital converter converts each voice signal produced by the audio receiver into an incoming digital voice signal.
  • the memories include a reference memory for storing a plurality of reference digital voice templates, and a program memory for storing a control program.
  • the microprocessor generates an incoming digital voice template from the incoming digital voice signal, executes the control program to determine whether the incoming digital voice template is substantially equivalent to one of the reference digital voice templates, and determines what action to take based on the incoming digital voice template.
  • the controlled device may comprise any appliance or other device capable of being electronically controlled.
  • An example of such a device is a television set having functions such as on/off, channel selection, volume and mute which are controlled in response to voice commands from the user entered at the remote control device.
  • the lock detect signal from the phase-locked loop receiver within the audio receiver may be used with such device to determine when a voice command is no longer being transmitted from the remote control device.
  • Fig. 1 is a basic block diagram of a voice operated remote control system in accordance with the invention
  • Fig. 2 is a detailed block diagram of the remote control device of Fig. 1;
  • Fig. 3 is a detailed block diagram of the audio receiver of Fig. 1;
  • Fig. 4 is a detailed block diagram of the controlled device of Fig. 1;
  • Fig. 5 is a basic flow chart illustrating the operation of the system of Fig. 1;
  • Fig. 6 is a detailed flow chart illustrating the operation of the system of Fig. 1 in connection with the television set shown in Fig. 4. Detailed Description
  • Fig. 1 shows a voice operated remote control system 10 in accordance with the invention.
  • the remote control system 10 of Fig. 1 includes a remote control device 12 for transmitting voice signals to a remotely located controlled device 14 in response to voice commands.
  • the remote control device 12 includes a microphone 16 for receiving voice commands from the user in the form of spoken words.
  • the microphone 16 converts the spoken words into analog audio signals for application to an audio wireless remote control circuit 18.
  • the audio wireless remote control circuit 18 processes the analog audio signals from the microphone 16 into an appropriate form for transmission to the controlled device 14, using an infrared transmitter 20.
  • the audio wireless remote control circuit 18 includes circuitry for frequency modulating (FM) the analog audio signal prior to application to a transmitting device in the form of the infrared transmitter 20.
  • the infrared transmitter 20 transmits the voice commands from the user to the controlled device 14 in wireless fashion.
  • voice operated remote control system 10 is described herein in connection with frequency modulation and demodulation of the voice commands and transmission in the form of an infrared signal, it should be understood that other signal processing and transmission techniques can be used.
  • forms of modulation other than frequency modulation such as amplitude modulation (AM)
  • AM amplitude modulation
  • modulated or otherwise modified signals can be transmitted in other than infrared signal form, such as in the form of a radio frequency signal.
  • the remote control device 12 comprises a small, portable, hand-held unit into which the user speaks the voice commands.
  • the remote control device 12 is remotely located relative to the controlled device 14, but nevertheless is close enough to the controlled device 14 so that the voice signals transmitted by the remote control device 12 are received by the controlled device 14.
  • the controlled device 14 comprises a television set, in the present example.
  • the controlled device 14 can comprise any appliance or device capable of being controlled electronically.
  • the controlled device may comprise a video cassette recorder (VCR) in which the spoken commands dictate the date, time and channel selection for future recording by the VCR, or simple commands such as play or rewind.
  • VCR video cassette recorder
  • the voice signals transmitted by the remote control device 12 are received by the controlled device 14.
  • the controlled device 14 includes an infrared sensor 22 for sensing the infrared signals transmitted by the infrared transmitter 20.
  • the sensed signals are processed by an audio receiver 24 which demodulates the transmitted signal as well as amplifying and filtering such signal to provide to a voice recognition circuit 26 the voice signal represented thereby.
  • the voice recognition circuit 26 performs a voice recognition process in which the voice signal is compared with pre-stored representations of different words of a vocabulary. If substantial similarity is found, then an action routine corresponding to the pre-stored word found to be substantially similar to the voice signal is provided to the controlled device 14 by the voice recognition circuit 26, so that a desired function is performed within the controlled device 14.
  • FIG. 2 A detailed example of the remote control device 12 of Fig. 1 is shown in Fig. 2.
  • the microphone 16 responds to a word spoken by the user by producing an analog audio signal. Such signal is amplified in an audio amplifier 28.
  • the audio amplifier 28 conditions the signal for proper application to a voltage controlled oscillator (VCO) 30 to frequency modulate (FM) a signal at the output of the VCO 30 in accordance with the analog audio signal from the amplifier 28.
  • VCO voltage controlled oscillator
  • FM frequency modulate
  • the output of the VCO 30 is conditioned by a driver circuit 32 prior to driving the infrared transmitter 20.
  • the remote control device 12 is powered by batteries 34. Because there is no memory or microprocessor in the remote control device 12, there is no need to keep the remote control device 12 powered when not in use. Accordingly, a push-to-talk switch 36 is used to provide the power from the batteries 34 only when the user wishes to speak into the remote control device 12. Pushing a button on the outside of the remote control device 12 closes the push-to-talk switch 36 to couple the batteries 34 to a voltage regulator 38.
  • the voltage regulator 38 which is coupled between a common ground line 40 and the push-to-talk switch 36, has an output terminal 42 thereof coupled to provide a supply voltage (+V) at a terminal 44. This regulated supply voltage is applied to the microphone 16, the audio amplifier 28 and the voltage controlled oscillator 30.
  • the batteries 34 are directly coupled to the driver 32 by the push-to-talk switch 36.
  • the regulated supply voltage +V optimizes the operating conditions of the voltage controlled oscillator 30.
  • the user pushes the button to close the push-to-talk switch 36 and speaks the voice command into the microphone 16.
  • the resulting analog audio signal is amplified by the amplifier 28 and applied to the VCO 30 to frequency modulate the output of the VCO 30.
  • This FM signal is applied via the driver 32 to the infrared transmitter 20, for transmission as an infrared signal to the controlled device 14.
  • the push-to-talk switch 36 is open, and the batteries 34 are not coupled to the voltage regulator 38 or to the driver 32.
  • the remote control device 12 transmits a frequency modulated infrared signal from the infrared transmitter 20.
  • the infrared transmitter 20 may comprise an infrared diode or other appropriate infrared transmitting device.
  • Such infrared signals are sensed by the infrared sensor 22 and applied to the audio receiver 24.
  • a detailed example of the audio receiver 24 is shown in Fig. 3.
  • the infrared sensor 22, which may comprise any appropriate form of infrared sensor such as those typically used in remote control devices, provides the received signal for amplification by an amplifier 46 and filtering by a filter 48.
  • the output of the filter 48 is applied to a phase-locked loop receiver 50 which demodulates the frequency modulated signal by converting it back to a voice signal.
  • the phase-locked loop receiver 50 is of conventional phase- locked loop (PLL) configuration, and includes a phase detector 52 coupled to the filter 48 and having an output and a second input coupled in a loop which includes a loop filter 54 and a voltage controlled oscillator (VCO) 56.
  • the output of the phase-locked loop receiver 50 is filtered by an audio filter 58 and amplified by an audio amplifier 60 to provide the demodulated voice signal.
  • the phase-locked loop receiver 50 also provides a lock detect signal, which indicates when a transmitted signal is present in the audio receiver 24.
  • the phase-locked loop receiver 50 is described herein by way of example only, and it should be understood that other demodulation receivers can be used as desired. For example, a super-heterodyne receiver can be used in applications posing more stringent requirements.
  • Fig. 4 shows the voice recognition circuit 26 of Fig. 1 in greater detail in conjunction with a television set 62.
  • the television set 62 comprises the appliance or device being controlled by the voice commands from the remote control device 12.
  • the television set 62 is of conventional configuration and includes a cathode ray tube (CRT) 64 for providing the TV screen.
  • the CRT 64 is driven by a tuner 66 through a video circuit 68.
  • An on-screen display circuit 70 which is coupled to the video circuit 68, provides additional screen displays such as menus of the type which invite the viewer to make selections by speaking further voice commands into the remote control device 12.
  • the on-screen display circuit 70 is used to provide on ⁇ screen displays requesting the user of the remote control device 12 to enter further voice commands.
  • the television set 62 also includes an audio circuit 72 which is coupled to speakers 74 for the television set 62.
  • the voice recognition circuit 26 comprises a microcontroller which includes an analog-to-digital converter (A/D) 76 coupled to receive the voice signal from the audio receiver 24.
  • the microcontroller of the voice recognition circuit 26 also includes a microprocessor (MP) 78 coupled to the A/D converter 76, and having access to both a read only memory (ROM) 80 and a random access memory (RAM) 82.
  • MP microprocessor
  • the microcontroller comprising the voice recognition circuit 26 is coupled to a digital IR input 84 and to an external DRAM 86.
  • the remaining components shown in Fig. 4, including those within the microcontroller of the voice recognition circuit 26, are standard components found in most modern television sets.
  • the external DRAM 86 is utilized for voice recognition storage requirements; primarily storage of voice templates. Therefore, the conventional television set 62 is easily modified by addition of the audio receiver 24 and the external DRAM 86 in order to make it responsive to voice commands transmitted by the remote control device 12.
  • the microcontroller comprising the voice recognition circuit 26 is part of the existing circuitry within the conventional television set 62.
  • voice operated remote control systems 10 in accordance with the invention do not require the addition of a microprocessor but only the modification of an existing one within the controlled device 14, principally through the addition of the external DRAM 86.
  • the microcontroller comprising the voice recognition circuit 26 operates in the same manner as described in the previously referred to co-pending applications. Serial Nos. 07/915,112, 07/915,938 and
  • the A/D converter 76 of Fig. 4 may comprise an 8-bit converter which samples incoming data at a preassigned frequency such as 9.6 KHz.
  • the A/D converter 76 outputs a digital signal representing the input analog voice signal from the audio receiver 24.
  • the microprocessor 78 processes the digital voice signal together with a voice recognition software routine forming part of a control program stored in the ROM 80.
  • the digital voice signal is converted into an incoming voice template that is compared against previously stored voice templates of the user's voice, stored in the external DRAM 86.
  • the program decodes the voice templates.
  • the RAM 82 comprises a reference memory for temporary storage of data.
  • the analog voice signal from the audio receiver 24 is applied to the A/D converter 76 for conversion into an incoming digital voice signal.
  • the reference memory comprised of the external DRAM 86 in conjunction with the RAM 82, stores a plurality of reference digital voice templates.
  • the ROM 80 stores the control program.
  • the microprocessor 78 which is coupled to the A/D converter 76, the ROM 80 and the RAM 82, generates an incoming digital voice template from the incoming digital voice signal at the output of the A/D converter 76.
  • the microprocessor 78 then executes the control program to determine whether the incoming digital voice template is substantially equivalent to one of the reference digital voice templates, stored in the reference memory comprised of the RAM 82 and the external DRAM 86.
  • the microprocessor 78 determines what action to take corresponding to a reference digital voice template, if the incoming digital voice template is found to have substantial similarity to the reference digital voice template.
  • the microcontroller effects the appropriate components of the television set to perform the desired function within the controlled device 14.
  • Voice control is made possible, in the voice operated remote control system 10, by first voice training the collection of reference digital voice templates in accordance with the user's voice. Such templates are collected in the same manner as described in co-pending application Serial No. 07/915,112.
  • the screen of the television set 62 (CRT 64) is used to provide an on ⁇ screen display which prompts the user by requesting the needed words. The user responds by pressing the button to close the push-to-talk switch 36 and speaking the prompted word into the microphone 16 of the remote control device 12.
  • the basic flow chart of Fig. 5 illustrates the manner in which the controlled device 14 operates in conjunction with the remote control device 12.
  • the controlled device 14 is in an idle mode 88, waiting for commands.
  • the lock detect signal causes an exit from the idle mode 88, with a visual cue to be presented to the user.
  • the absence (No) of a lock detect 90 causes the system to return to the idle mode 88.
  • visual feedback 92 is provided the user. This comes in the form of an on-screen display.
  • the user responds by speaking the desired command or string of commands, and voice recognition 94 thereof produces selected action 96 within the controlled device 14 through execution of an action routine by the microprocessor 78. Afterward, the idle mode 88 is returned to.
  • Fig. 6 comprises a detailed flow chart illustrating the operation of the circuit of Fig. 4 in conjunction with the remote control device 12.
  • the starting point in the flow chart of Fig. 6 is an idle mode 98.
  • the system always returns to the idle mode 98.
  • the idle mode 98 is exited and a check is made to determine if the television set 62 is turned on ("TV on" block 102) . If the television set 62 is not turned on (No) , then the set is turned on ("turn on” block 104) .
  • the system proceeds to an initial visual ("cue" block 106) .
  • This feature allows the user to turn on the television set 62 without using a voice command or a separate button therefor on the remote control device 12.
  • the visual cue 106 can simply be a symbol indicative of speech. Because the controlled device 14 is designed with voice recognition in mind, it is also possible for the volume of the television set 62 to automatically be decreased to a moderate level to facilitate better voice recognition, at this point. Once the visual cue 106 is displayed, the user knows that the television set 62 is "listening".
  • the user has a choice of turning the television set 62 off ("Off"), changing the channel (“Channel”), adjusting the volume (“Volume”), or muting the audio (“Mute”) , as represented by a function block 108 in Fig. 6.
  • the on-screen display shows the word recognized or an appropriate symbol indicative of the word or the action denoted thereby.
  • the television set 62 is turned off ("turn off" block 110) and the idle mode 98 is returned to.
  • the word “Channel” is displayed on the television screen and a second group of words is possible. This includes the possibility of either “Up” or “Down” commands, or entry of the digits 0 through 9. “up” or “Down” commands result in changing the channel by one channel and returning to the same choices. This allows the user to single-step through the channels by speaking the words “Up” or “Down” several times. If a channel number is spoken and recognized, then the user can either release the push-to-talk switch 36, which causes the channel to change to the appropriate single-digit channel, or the user can speak another digit causing the channel to be changed to the appropriate 2-digit channel.
  • a block 112 which represents the choices of entering a particular channel number (0-9) or an "Up” or “Down” command. Again, an indication of lock lost results in returning to the idle mode 98.
  • the system increments in the "Up” or “Down” direction, as represented by a "channel up” block 114 or a “channel down” block 116, respectively.
  • the user can speak a number in the 0-9 range. If the spoken number is recognized, the user can release the push-to-talk switch 36 and this causes the channel to be changed to the appropriate single- digit channel, as represented by a block 118 shown in Fig. 6.
  • the user can continue pushing the push-to-talk switch 36 and speak a second digit, causing the channel to be changed to the appropriate 2- digit channel, as represented by a block 120 in Fig. 6.
  • volume is displayed together with a visual indication of the present volume on the screen of the television set 62, and a second word consisting of either “Up” or “Down” is accessed, as represented by a block 122 in Fig. 6.
  • Speaking the word “Up” causes the volume to be increased by one level, as represented by a block 124.
  • speaking the word “Down” causes the volume to decrease by one level, as represented by a block 126.
  • the microcontroller checks the state of the audio output, in a "muted” block 126. If the audio output is on (No) , then the audio signal is turned off, as represented by a mute sound block 128. Conversely, if the audio output is off (Yes) , then the audio output is turned back on to the level where it was prior to being muted ("enable sound” block 130) .
  • the voice operated remote control system 10 in accordance with the invention is described herein in terms of transmission of an infrared signal for purposes of example only. In actual practice, other transmission media such as FM or AM radio frequency (RF) signals can be used. VCRs, audio tape and disc players, and radio receivers, can all be controlled using the techniques described herein. Also, other appliances or devices such as household appliances, automotive accessories, home security systems, and office equipment can be controlled in accordance with the techniques described herein.
  • RF radio frequency
  • multiple users can utilize a single remote control device 12.
  • the voice of each user is trained, and the templates which result therefrom are stored in the controlled device 14 separately from templates of the other users.
  • each user speaks his or her name at the appropriate word group, and this causes the controlled device 14 to change to the new user's voice templates.
  • the on-screen display shows the user's name and proceeds to use that user's templates, until the name is changed.
  • the remote control device 12 does not have any components added to support multiple voices. In fact, the number of user voices supported is practically limited by the choice of the system software. Also, this method does not require that the user remember a switch number or other identification corresponding to his or her voice.
  • the disadvantage of such method relates to the need to add more words to the word groups, as well as possible confusion as to whose voice templates are presently being used.
  • a second, multiple position switch is incorporated into the remote control device 12.
  • a series of pulses is transmitted to the controlled device 14 for interpretation to identify the user.
  • the controlled device 14 then changes to the new user's templates.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • General Physics & Mathematics (AREA)
  • Selective Calling Equipment (AREA)

Abstract

Système (10) de commande à distance à fonctionnement vocal qui transmet des représentations des commandes vocales à un dispositif commandé (14). Ledit dispositif de commande à distance produit des signaux vocaux en réponse aux représentations transmises. Ledit dispositif de commande qui comporte un commutateur de conversation destiné à économiser la puissance des piles reçoit les commandes vocales par l'intermédiaire d'un microphone (16) et d'un amplificateur audio pour produire un signal audio qui est appliqué à un oscillateur en vue de la modulation de fréquence d'un signal transmis par un émetteur infrarouge (20). Au niveau du dispositif commandé, un récepteur audio (24) reçoit le signal transmis et l'applique à un récepteur en vue de la démodulation. A la suite du filtrage et de l'amplification, le signal vocal est utilisé pour générer un modèle vocal en vue de la comparaison avec une pluralité de modèles vocaux numériques de référence. Si un équivalent substantiel est trouvé, une routine d'action correspondante est exécutée pour parvenir à une action désirée au sein du dispositif commandé (14).
PCT/US1994/009544 1993-08-27 1994-08-23 Systeme de commande a distance a fonctionnement vocal Ceased WO1995006309A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
AU76371/94A AU7637194A (en) 1993-08-27 1994-08-23 Voice operated remote control system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US11339493A 1993-08-27 1993-08-27
US08/113,394 1993-08-27

Publications (1)

Publication Number Publication Date
WO1995006309A1 true WO1995006309A1 (fr) 1995-03-02

Family

ID=22349142

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US1994/009544 Ceased WO1995006309A1 (fr) 1993-08-27 1994-08-23 Systeme de commande a distance a fonctionnement vocal

Country Status (2)

Country Link
AU (1) AU7637194A (fr)
WO (1) WO1995006309A1 (fr)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5794205A (en) * 1995-10-19 1998-08-11 Voice It Worldwide, Inc. Voice recognition interface apparatus and method for interacting with a programmable timekeeping device
DE19709990A1 (de) * 1997-03-11 1998-09-24 Philips Patentverwaltung System zur Spracherkennung von Ziffern
WO1999028897A1 (fr) * 1997-12-04 1999-06-10 Voquette Networks, Ltd. Systeme de sonorisation personnel
EP1079352A1 (fr) * 1999-08-27 2001-02-28 Deutsche Thomson-Brandt Gmbh Système de commande vocale à distance
WO2001037262A1 (fr) * 1999-11-12 2001-05-25 Telefonaktiebolaget Lm Ericsson (Publ) Dispositif de commande à distance sans fil à commande vocale
WO2002011122A1 (fr) * 2000-07-28 2002-02-07 Koninklijke Philips Electronics N.V. Systeme de commande d'un appareil avec des commandes vocales
EP0921508A3 (fr) * 1997-12-08 2005-04-13 Fujitsu Siemens Computers GmbH Combinaison d'un téléviseur et d'un calculateur avec un accès à un réseau de communication et commande à distance correspondante
US6978475B1 (en) 1999-11-24 2005-12-20 Ecable, Llc Method and apparatus for internet TV
WO2008000052A3 (fr) * 2006-06-26 2008-03-20 Leonardo Senna Da Silva Bracelet auquel est fixé un dispositif de commande
US8886541B2 (en) 2010-02-04 2014-11-11 Sony Corporation Remote controller with position actuatated voice transmission
EP2881941A1 (fr) * 2013-12-09 2015-06-10 Thomson Licensing Procédé et appareil pour filigranage d'un signal audio
US10257576B2 (en) 2001-10-03 2019-04-09 Promptu Systems Corporation Global speech user interface

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4641292A (en) * 1983-06-20 1987-02-03 George Tunnell Voice controlled welding system
US5199080A (en) * 1989-12-29 1993-03-30 Pioneer Electronic Corporation Voice-operated remote control system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4641292A (en) * 1983-06-20 1987-02-03 George Tunnell Voice controlled welding system
US5199080A (en) * 1989-12-29 1993-03-30 Pioneer Electronic Corporation Voice-operated remote control system

Cited By (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5794205A (en) * 1995-10-19 1998-08-11 Voice It Worldwide, Inc. Voice recognition interface apparatus and method for interacting with a programmable timekeeping device
DE19709990A1 (de) * 1997-03-11 1998-09-24 Philips Patentverwaltung System zur Spracherkennung von Ziffern
DE19709990C2 (de) * 1997-03-11 2000-03-02 Philips Corp Intellectual Pty System zur Erkennung gesprochener Ziffernfolgen
US6078887A (en) * 1997-03-11 2000-06-20 U.S. Philips Corporation Speech recognition system for numeric characters
WO1999028897A1 (fr) * 1997-12-04 1999-06-10 Voquette Networks, Ltd. Systeme de sonorisation personnel
EP0921508A3 (fr) * 1997-12-08 2005-04-13 Fujitsu Siemens Computers GmbH Combinaison d'un téléviseur et d'un calculateur avec un accès à un réseau de communication et commande à distance correspondante
EP1079352A1 (fr) * 1999-08-27 2001-02-28 Deutsche Thomson-Brandt Gmbh Système de commande vocale à distance
WO2001037262A1 (fr) * 1999-11-12 2001-05-25 Telefonaktiebolaget Lm Ericsson (Publ) Dispositif de commande à distance sans fil à commande vocale
US6339706B1 (en) 1999-11-12 2002-01-15 Telefonaktiebolaget L M Ericsson (Publ) Wireless voice-activated remote control device
US6978475B1 (en) 1999-11-24 2005-12-20 Ecable, Llc Method and apparatus for internet TV
US7086079B1 (en) 1999-11-24 2006-08-01 Ecable, Llc Method and apparatus for internet TV
WO2002011122A1 (fr) * 2000-07-28 2002-02-07 Koninklijke Philips Electronics N.V. Systeme de commande d'un appareil avec des commandes vocales
US10257576B2 (en) 2001-10-03 2019-04-09 Promptu Systems Corporation Global speech user interface
US10932005B2 (en) 2001-10-03 2021-02-23 Promptu Systems Corporation Speech interface
US11070882B2 (en) 2001-10-03 2021-07-20 Promptu Systems Corporation Global speech user interface
US11172260B2 (en) 2001-10-03 2021-11-09 Promptu Systems Corporation Speech interface
WO2008000052A3 (fr) * 2006-06-26 2008-03-20 Leonardo Senna Da Silva Bracelet auquel est fixé un dispositif de commande
US8886541B2 (en) 2010-02-04 2014-11-11 Sony Corporation Remote controller with position actuatated voice transmission
EP2881941A1 (fr) * 2013-12-09 2015-06-10 Thomson Licensing Procédé et appareil pour filigranage d'un signal audio
WO2015086360A1 (fr) * 2013-12-09 2015-06-18 Thomson Licensing Procédé et appareil pour le filigranage d'un signal audio

Also Published As

Publication number Publication date
AU7637194A (en) 1995-03-21

Similar Documents

Publication Publication Date Title
US6119088A (en) Appliance control programmer using voice recognition
US7080014B2 (en) Hands-free, voice-operated remote control transmitter
US6747566B2 (en) Voice-activated remote control unit for multiple electrical apparatuses
US8653950B2 (en) State-based remote control system
US8271287B1 (en) Voice command remote control system
JP2846021B2 (ja) テレビジョン受信機
US6879351B1 (en) Method and apparatus for remote control
US7006974B2 (en) Voice controller and voice-controller system having a voice-controller apparatus
US6998997B2 (en) System and method for learning macro routines in a remote control
US6012029A (en) Voice activated system for locating misplaced items
US7039590B2 (en) General remote using spoken commands
WO1995006309A1 (fr) Systeme de commande a distance a fonctionnement vocal
US20010045819A1 (en) State-based remote control system
US20030018479A1 (en) Electronic appliance capable of preventing malfunction in speech recognition and improving the speech recognition rate
JP2004507936A (ja) ダウンロード可能な音声命令の集合による音声制御型遠隔制御装置
US20050151886A1 (en) Remote controller
WO2001050454A1 (fr) Regleur de dispositif, systeme de reglage de dispositif et support enregistre comportant le programme de reglage de dispositif
US20060235701A1 (en) Activity-based control of a set of electronic devices
WO2001027895A1 (fr) Telephone sans fil et telecommande combines, a commande vocale
JPS59200597A (ja) 種々の装置を無線制御するための遠隔制御装置
HK1206180A1 (en) A remote control
WO1994003020A1 (fr) Dispositif vocal de commande a distance
US20050212685A1 (en) Talking remote appliance-controller for the blind
US20060235698A1 (en) Apparatus for controlling a home theater system by speech commands
WO1994003017A1 (fr) Dispositif de commande a distance polyvalent

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): AU CA DK JP KR NO

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): AT BE CH DE DK ES FR GB GR IE IT LU MC NL PT SE

121 Ep: the epo has been informed by wipo that ep was designated in this application
122 Ep: pct application non-entry in european phase
NENP Non-entry into the national phase

Ref country code: CA