WO2007033459A1 - Procede et systeme pour le traitement d'appel entrant mains libres et l'emission d'appel sortant mains libres - Google Patents

Procede et systeme pour le traitement d'appel entrant mains libres et l'emission d'appel sortant mains libres Download PDF

Info

Publication number
WO2007033459A1
WO2007033459A1 PCT/CA2005/001942 CA2005001942W WO2007033459A1 WO 2007033459 A1 WO2007033459 A1 WO 2007033459A1 CA 2005001942 W CA2005001942 W CA 2005001942W WO 2007033459 A1 WO2007033459 A1 WO 2007033459A1
Authority
WO
WIPO (PCT)
Prior art keywords
signal
spoken
incoming call
communication device
command
Prior art date
Application number
PCT/CA2005/001942
Other languages
English (en)
Inventor
David William Clark
Andrew James Weber
Jeffrey William Dawson
Sean M. Murray
Sanro Zlobec
Original Assignee
Bce 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
Priority claimed from PCT/CA2005/001457 external-priority patent/WO2007033458A1/fr
Priority claimed from PCT/CA2005/001456 external-priority patent/WO2007033457A1/fr
Application filed by Bce Inc. filed Critical Bce Inc.
Priority to CA2570695A priority Critical patent/CA2570695C/fr
Priority to US11/534,414 priority patent/US8433041B2/en
Publication of WO2007033459A1 publication Critical patent/WO2007033459A1/fr

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L13/00—Speech synthesis; Text to speech systems
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M1/00—Substation equipment, e.g. for use by subscribers
    • H04M1/26—Devices for calling a subscriber
    • H04M1/27—Devices whereby a plurality of signals may be stored simultaneously
    • H04M1/271—Devices whereby a plurality of signals may be stored simultaneously controlled by voice recognition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/42204—Arrangements at the exchange for service or number selection by voice
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M2250/00—Details of telephonic subscriber devices
    • H04M2250/74—Details of telephonic subscriber devices with voice recognition means

Definitions

  • the present invention relates generally to telephonic communication and, more specifically, to a method and a system for enabling a user of a communication device to handle an incoming call and originate an outgoing call without having to touch the communication device.
  • Communication devices and telephony services have evolved to facilitate the manner in which users handle incoming calls and originate outgoing calls. For example, features such as calling line identification (CLID), call forwarding, call waiting, speed dialing, and busy call return all contribute to facilitating the handling of incoming calls and the origination of outgoing calls.
  • CLID calling line identification
  • wireless communication devices such as mobile phones and cordless phones, allow incoming call handling and outgoing call origination while on the move.
  • conventional communication devices require users to touch or otherwise physically manipulate their devices (for example, by lifting a receiver of a phone, flipping a phone open, and/or interacting with a keypad) in order to handle incoming calls and originate outgoing calls. While physically manipulating a communication device in order to perform any of these two functions may represent only a slight nuisance for some users, for other users such as call center agents, receptionists, stock brokers, etc., this requirement may negatively impact their efficiency in a business environment. Just as significantly, physically manipulating a mobile phone while driving a vehicle in order to handle an incoming call or originate an outgoing call represents a distraction which may pose a safety hazard.
  • the invention provides a method to enable touch-free incoming call handling and touch-free outgoing call origination with a communication device.
  • the method comprises receiving at a network entity a signal indicative of sound sensed by a microphone associated with the communication device, the signal having been produced: - as part of one of (i) an incoming call handling process associated with an incoming call destined for the communication device; and (ii) an outgoing call origination process associated with an outgoing call to be originated using the communication device; and - without requiring the communication device to have been touched since a start of the one of the incoming call handling process and the outgoing call origination process.
  • the method also comprises processing the received signal in an attempt to detect at least one of a plurality of spoken commands potentially contained therein.
  • the plurality of spoken commands comprises at least one spoken call handling command and at least one spoken call origination command.
  • the method further comprises, responsive to detection of a specific one of the at least one spoken call handling command in the received signal, handling the incoming call associated with the incoming call handling process in accordance with the specific spoken call handling command; and, responsive to detection of a specific one of the at least one spoken call origination command in the received signal, attempting to establish the outgoing call associated with the outgoing call origination process in accordance with the specific spoken call origination command.
  • the invention provides a system for enabling touch- free incoming call handling and touch-free outgoing call origination using a communication device communicatively coupled to the system via a communications network.
  • the system comprises a communication module operative for receiving a signal indicative of sound sensed by a microphone associated with the communication device, the signal having been produced: - as part of one of (i) an incoming call handling process associated with an incoming call destined for the communication device; and (ii) an outgoing call origination process associated with an outgoing call to be originated using the communication device; and - without requiring the communication device to have been touched since a start of the one of the incoming call handling process and the outgoing call origination process.
  • the system also comprises a speech recognition module operative for processing the received signal in an attempt to detect at least one of a plurality of spoken commands potentially contained therein.
  • the plurality of spoken commands comprises at least one spoken call handling command and at least one spoken call origination command.
  • the system further comprises a control module operative for, responsive to detection of a specific one of the at least one spoken call handling command in the received signal, causing handling of the incoming call associated with the incoming call handling process in accordance with the specific spoken call handling command; and, responsive to detection of a specific one of the at least one spoken call origination command in the received signal, causing an attempt to establish the outgoing call associated with the outgoing call origination process in accordance with the specific spoken call origination command.
  • the invention provides a computer readable storage medium containing a program element for execution by a functional unit of a network entity to enable touch-free incoming call handling and touch-free outgoing call origination using a communication device communicatively coupled to the network entity.
  • the functional unit when executing the program element, is operative for receiving a signal indicative of sound sensed by a microphone associated with the communication device, the signal having been produced: - as part of one of (i) an incoming call handling process associated with an incoming call destined for the communication device; and (ii) an outgoing call origination process associated with an outgoing call to be originated using the communication device; and - without requiring the communication device to have been touched since a start of the one of the incoming call handling process and the outgoing call origination process.
  • the functional unit when executing the program element, is also operative for processing the received signal in an attempt to detect at least one of a plurality of spoken commands potentially contained therein.
  • the plurality of spoken commands comprises at least one spoken call handling command and at least one spoken call origination command.
  • the functional unit when executing the program element, is further operative for, responsive to detection of a specific one of the at least one spoken call handling command in the received signal, causing handling of the incoming call associated with the incoming call handling process in accordance with the specific spoken call handling command; and, responsive to detection of a specific one of the at least one spoken call origination command in the received signal, causing an attempt to establish the outgoing call associated with the outgoing call origination process in accordance with the specific spoken call origination command.
  • Figure 1 shows, in schematic form, a communication device, a controller, a database and other components of a system for enabling a user of the communication device to handle an incoming call and originate an outgoing call without touching the communication device, in accordance with a non-limiting embodiment of the present invention
  • Figure 2 conceptually illustrates a non-limiting example of potential contents of the database in Figure 1 ;
  • Figures 3A and 3B illustrate exchange of signals between various components in the system of Figure 1 during a touch-free incoming call handling process, in accordance with a non-limiting embodiment of the present invention
  • Figure 4 is a flowchart showing steps performed by various components of the system of Figure 1 in the context of the non-limiting example of the touch-free incoming call handling process depicted in Figures 3 A and 3B;
  • FIGS 5A and 5B illustrate exchange of signals between various components in the system of Figure 1 during a touch- free outgoing call origination process, in accordance with a non-limiting embodiment of the present invention.
  • FIGs 6 A and 6B are flowchart showing steps performed by various components of the system of Figure 1 in the context of the non-limiting example of the touch-free outgoing call origination process depicted in Figures 5 A and 5B.
  • Figure 1 depicts a communication device 12 that may be employed by a user 14 to effect various call handling and call origination activities, including but not limited to handling an incoming call originating from a calling party device, placing an outgoing call to a called party device, and dialing-in to a server to check voice mail messages.
  • the communication device 12 maybe implemented as a wired Plain Old Telephony System (POTS)-enabled phone (including a cordless phone), a wireless-enabled phone (e.g., a cellular or other mobile device including a telephony- enabled personal digital assistant), a Voice over Internet Protocol (VoIP)-enabled phone, or a soft phone (i.e., a computer equipped with telephony software).
  • POTS Plain Old Telephony System
  • VoIP Voice over Internet Protocol
  • the communication device 12 comprises a microphone 40, a speaker 42 (which may be part of an earphone), a network interface 46, and a controller 60.
  • the controller 60 comprises suitable hardware, firmware, software, control logic, or a combination thereof for implementing a plurality of functional modules, including a communication module 50, a speech recognition module 48 and a control module 54. Functionality of these components of the controller 60 as well as interaction between the various components of the communication device 12 will be described in further detail later on.
  • the communication device 12 enables the user 14 to handle an incoming call or originate an outgoing call using a touch-free approach.
  • the communication device 12 may thus be devoid of any component (e.g. a button or keypad) required to be physically touched by the user 14 in order to handle or originate a call.
  • the communication device 12 is connected to a switching/routing entity 20 via a first network portion 24i .
  • the first network portion 24 t may include a portion of the Public Switched Telephone Network (PSTN), a cellular network, a data network (such as the Internet), or a combination thereof.
  • PSTN Public Switched Telephone Network
  • cellular network such as the GSM
  • data network such as the Internet
  • the first network portion 24t may comprise a telephone line in the PSTN and the switching/routing entity 20 may be part of a central office switch.
  • the first network portion 24j may comprise a portion of a cellular network (e.g. a wireless link in combination with a base station and a network-side wireline link), and the switching/routing entity 20 may be part of a mobile switching center.
  • the first network portion 24 1 may comprise a digital communications link such as Ethernet and the switching/routing entity 20 may be part of an edge router or a Softswitch.
  • the first network portion 24i may comprise a digital communications link such as a DSL link, coaxial cable, etc., and the switching/routing entity 20 may be part of a server equipped with a modem. Still other configurations will be apparent to those skilled in the art.
  • the switching/routing entity 20 is connected to a second network portion 24 2 so as to allow the communication device 12 to reach or be reached by any of various communication subsystems, one of which is represented as reference number 28.
  • Other communication subsystems similar to the communication subsystem 28 may also be provided but are not shown for the sake of simplicity.
  • the communication subsystem 28 may be a telephone (e.g. a wired POTS, wireless, VoIP, or soft phone), hi another non-limiting example scenario, the communication subsystem 28 may be a voice mail system.
  • the second network portion 24 2 may include a portion of the PSTN, a cellular network, a data network (such as the Internet), or a combination thereof that may need to be traversed from the switching/routing entity 20 to the communication subsystem 28.
  • the switching/routing entity 20 is also communicatively coupled to a controller 22, which is described in detail later on.
  • the controller 22 implements a second communication subsystem 29 with which the communication device 12 may communicate via the switching/routing entity 20 and the first network portion 24 ⁇
  • the communication subsystem 29 may be an administration subsystem enabling the user 14 to administer, for instance, services provided by the controller 22 and which are subscribed to by the user 14, options associated with such services, billing options, or any other feature associated with interaction between the user 14 and the controller 22.
  • the switching/routing entity 20 is capable of effecting switching operations to help route an outgoing call from the communication device 12 towards a called party subsystem (such as the communication subsystem 28) via the second network portion 24 2 .
  • the switching/routing entity 20 is capable of effecting switching operations to help route an incoming call originating at a calling party subsystem (such as the communication subsystem 28), arriving from the second network portion 24 2 , and destined for the communication device 12.
  • the switching/routing entity 20 is capable of effecting switching operations to provide a communication path between the controller 22 and the communication device 12 during outgoing call origination, incoming call handling, and while a call is in progress.
  • the switching/routing entity 20 may be implemented in hardware, firmware, software, control logic, or a combination thereof.
  • the controller 22 is connected to a database 26, which is now described in further detail with reference to Figure 2.
  • the database 26 stores a plurality of records 502, 504, 506 and 508, each associated with a respective party (such as the user 14) which may be a potential calling party as well as a potential called party.
  • the record 502 stores an association between a party, Party_l, and a telephone number identifying a telephone line expected to be used by Party_l to originate and handle calls using a wired POTS-enabled phone.
  • the record 504 stores an association between a party, Party_2, and an IP address and associated subscriber telephone number of a VoIP-enabled phone expected to be used by Party_2 to originate and handle calls.
  • the record 506 stores an association between a party, Party_3, and an electronic serial number (ESN) and associated subscriber telephone number of a wireless-enabled phone expected to be used by Party_3 to originate and handle calls.
  • ESN electronic serial number
  • each of the other records 508 stores an association between a respective party and a communication device expected to be employed by that party to handle and originate calls.
  • Each of the records 502, 504, 506 and 508 in the database 26 also includes a list of communication services subscribed to by the respective party associated with that record.
  • Examples of conventionally available communication services for outgoing calls include long distance call blocking, calling line identification (CLID) blocking, and so on.
  • examples of conventionally available communication services include call forwarding, calling line identification (CLID), and so on.
  • the database 26 stores information on whether a particular party subscribes to a "voice-activated call handling and origination" (VACHO) service.
  • VACHO voice-activated call handling and origination
  • Party_l and Party_2 subscribe to the VACHO service contemplated by the present invention, while Party_3 does not.
  • subscription to different services may be completely independent from one party to another and the present invention imposes no restriction on the number or combination of services that may be subscribed to by any one party.
  • the switching/routing entity 20, the controller 22, and the database 26 may be located in a common network entity, hi other non-limiting embodiments, the switching/routing entity 20, the controller 22, and the database 26 may be located in different network entities.
  • the controller 22 is operative to interact with the switching/routing entity 20 and the database 26 in order to effect various call control operations when a communication device (such as the communication device 12) connected to the switching/routing entity 20 is the intended recipient of an incoming call, originates an outgoing call, or is involved in a call in progress.
  • the controller 22 can comprise suitable hardware, firmware, software, control logic, or a combination thereof for implementing a set of functional units for managing various services that may be subscribed to by various parties, including the user 14.
  • Functional units denoted by numerals 34 ⁇ .-34 ⁇ are associated with conventionally available services 1 through N (e.g., CLID, voice mail, call waiting, call forwarding, automatic call answering, distinctive ringing, long distance call blocking, CLID blocking, etc.).
  • the functional unit 30 associated with the VACHO service mentioned.
  • the functional unit 30 will hereinafter be referred to as a "voice-activated call handling and origination unit” 30 or simply as the VACHO unit 30.
  • the VACHO unit 30 comprises a set of functional modules, including a communication module 35, a speech recognition module 31 and a control module 38. Functionality of these components of the VACHO unit 30 will be described in further detail below.
  • the VACHO unit 30 contributes to allowing a subscriber to the VACHO service to both handle an incoming call and originate an outgoing call without having to touch his or her communication device, by way of exchange of voice messages with that communication device. This is achieved by the subscriber's communication device being operative to produce signals which capture sound in a vicinity of the communication device and by the VACHO unit 30 being operative to process these signals in an attempt to detect any of various detectable spoken commands which may be contained therein, hi response to detecting such a spoken command, the VACHO unit 30 may interact with the subscriber's communication device to effect handling of an incoming call or origination of an outgoing call, as the case may be, in an entirely touch- free manner from the subscriber's perspective.
  • the first example relates to an incoming call handling process for an incoming call destined for the communication device 12, while the second example relates to an outgoing call origination process for an outgoing call to be originated using the communication device 12.
  • an incoming call handling process for an incoming call destined for a communication device starts with detection of the incoming call at a network entity (such as the network entity in which is located the controller 22 and/or the switcliing/routing entity 20).
  • the incoming call handling process may end in many ways such as (i) with acceptance, rejection, or forwarding of the incoming call using the communication device for which the incoming call is destined; (ii) with a calling party (e.g., a calling party using the communication subsystem 28) from which the incoming call originates hanging up; or (iii) with occurrence of any other event resulting in termination of the incoming call handling process.
  • an outgoing call origination process for an outgoing call to be originated using a communication device starts with a commitment of a user (such as the user 14) of the communication device to attempt to originate the outgoing call.
  • the outgoing call origination process may end in many ways such as (i) with establishment of the outgoing call via a network entity (such as the network entity in which is located the controller 22 and/or the switching/routing entity 20); (ii) with a network entity determining that it is not capable of completing the outgoing call; or (iii) with occurrence of any other event resulting in termination of the outgoing call origination process.
  • the communication device 12 is initially not involved in either of an incoming call handling process or an outgoing call origination process. Also, for both examples, except as otherwise noted, the microphone 40 of the communication device 12 continuously generates a signal indicative of sound sensed by the microphone 40, this signal being transmitted to the controller 60 of the communication device 12.
  • controller 22 in particular the VACHO unit 30
  • communication device 12 Operation of the controller 22 (in particular the VACHO unit 30) and the communication device 12 will now be described in the context of an incoming call originating from the communication subsystem 28, arriving at the switching/routing entity 20 via the second network portion 24 2 and destined for the communication device 12.
  • the controller 22 Upon arrival of the incoming call at the switching/routing entity 20, the controller 22 detects the incoming call, which in this example marks the start of the incoming call handling process. The controller 22 determines that the call is destined for the user 14 associated with the communication device 12. This can be determined from destination information that accompanies the incoming call, such as a subscriber telephone number. The controller 22 proceeds to consult the database 26 to determine if the user 14 subscribes to one or more telephony services provided by the controller 22, including, specifically, the VACHO service. In a situation where a given party for which an incoming call is destined does not subscribe to the VACHO service, the controller 22 proceeds to handle the incoming call in a conventional manner. However, as mentioned above, for the purposes of the present example, it is'assumed that the user 14 does indeed subscribe to the VACHO service. Having determined that the user 14 subscribes to the VACHO service, the controller 22 passes control over to the VACHO unit 30.
  • the VACHO unit 30 attempts to reach the user 14 by causing the communication device 12 to emit a voice message soliciting a spoken "call handling command" from the user 14.
  • the user 14 is capable of accepting, rejecting or forwarding the incoming call without being required to touch the communication device 12.
  • the control module 38 attempts to obtain information regarding an origin of the incoming call.
  • the control module 38 may use CLDD information which may accompany the incoming call. Based on the CLID information, the control module 38 can obtain the identity of an associated calling party.
  • the control module 38 sends a signal back towards the communication subsystem 28 via the second network portion 24 2 requesting that the identity of the calling party be spoken or otherwise provided.
  • the identity of the calling party is recorded in a memory (not shown) accessible by the controller 22.
  • the VACHO unit 30 attempts to reach the user 14 over the first network portion 24 ⁇
  • the control module 38 consults the database 26 in order to learn how it should attempt to reach the user 14, e.g., by trying to communicate with the communication device 12 directly, by communicating over a telephone line to which the communication device 12 happens to be connected, etc.
  • the VACHO unit 30 proceeds to step 206, where the communication module 35 generates a signal 404 and sends the signal 404 over the first network portion 24 ! towards the communication device 12.
  • the signal 404 is a message that is reproducible at the communication device 12 as an audible voice message.
  • the signal 404 is a trigger that is recognized at the communication device 12 as being associated with an audible voice message for reproduction at the communication device 12.
  • generation of the signal 404 may use a text-to-speech conversion algorithm.
  • the signal 404 may enable a text-to-speech conversion algorithm implemented at the communication device 12 to emit an audible voice message.
  • generation of the signal 404 may include playing back this recording.
  • the signal 404 (which may have been reformatted by passage through the first network portion 24 ⁇ ) is received at the network interface 46 of the communication device 12 and detected by the controller 60.
  • the control module 54 of the controller 60 proceeds to cause the speaker 42 of the communication device 12 to emit a voice message 408.
  • the voice message 408 is designed to solicit a spoken call handling command from the user 14.
  • the signal 404 maybe operable to force the communication device 12 to acquire an off-hook state in order to allow emission of the voice message 408.
  • the voice message 408 may be "You have a call from John Doe. Do you wish to take this call?"; "John Doe is calling. How would you like to handle this call?"; or any conceivable variant thereof.
  • the speaker 42 may have volume adjustment capability so that the voice message 408 may be emitted with a volume sufficient to be heard up to several meters. In other cases, for example when the speaker 42 is part of an earphone, volume adjustment may not be required.
  • the communication device 12 may optionally also emit a ringing sound and/or provide a visual indication (e.g., a blinking light, a text message, etc.) to accompany, precede or follow the voice message 408.
  • the voice message 408 can be used to announce the incoming call to the user 14 is beneficial because the user 14 need not take his or her eyes away from what they were doing at the time of arrival of the incoming call. Also, it will be appreciated that when the voice message 408 is emitted, it is still not known whether the user 14 is willing to accept the incoming call, not even whether the user 14 can be reached. Thus, it can be said that the VACHO unit 30 is attempting to reach the user 14, but is at the same time asking for a verbal command as to how to handle the incoming call.
  • incoming call handling can be effected in an entirely touch-free manner.
  • the microphone 40 of the communication device 12 continuously generates a signal indicative of sound sensed by the microphone 40, this signal being transmitted to the controller 60.
  • the control module 54 may temporarily deactivate the microphone 40 during emission of the voice message 408 by the speaker 42 and reactivate the microphone 40 thereafter. Pn any event, at step 210, upon emission of the voice message 408, the signal generated by the microphone 40 and transmitted to the controller 60 is denoted by numeral 409.
  • the signal 409 causes a signal 410, which may be identical to the signal 409 or an amplified or otherwise processed version of that signal, to be released by the communication module 50 towards the controller 22 via the network interface 46, the first network portion 24 l5 and the switching/routing entity 20. It will be appreciated that the signal 409 and the signal 410 are produced without requiring the communication device 12 to have been touched by the user 14 since detection of the incoming call at the controller 22.
  • the speech recognition module 31 of the VACHO unit 30 receives the signal 410 and, at step 214, processes the signal 410 in an attempt to detect a call handling command which may be contained therein as a result of a spoken response to the voice message 408.
  • the speech recognition module 31 is adapted to detect several predetermined call handling commands that may be contained in the signal 410.
  • the speech recognition module 31 may employ speaker-dependent or speaker-independent recognition.
  • Data representing the predetermined call handling commands may be stored in a database (not shown) or other memory (not shown) accessible by the controller 22 and specifically the VACHO unit 30.
  • Non-limiting examples of predetermined call handling commands that may be spoken and detectable by the speech recognition module 31 include: - "yes", “accept” or “hello”, associated with a desire of the user 14 to take the incoming call; - "no” or “reject”, associated with a desire of the user 14 to not take the incoming call; - "forward to voice mail”, associated with a desire of the user 14 to forward the incoming call to a voice mail system; and - “forward to alternate number”, associated with a desire of the user 14 to forward the incoming call to an alternate telephone number.
  • these examples are not to be considered limiting in any respect as various other predetermined call handling commands are possible without departing from the scope of the invention.
  • the speech recognition module 31 determines that the signal 410 contains no spoken response whatsoever to the voice message 408 after a predetermined period of time (e.g., 5 to 10 seconds) following emission of that voice message, or if a spoken response provided by the user 14 does not correspond to one of the predetermined call handling commands, then the VACHO unit 30 is deemed not to have detected a call handling command in the signal 410.
  • the control module 38 thus proceeds to step 216 and handles the incoming call in accordance with a default call handling option.
  • the control module 38 may cause emission from the speaker 42 of recurring voice messages each similar or identical to the voice message 408 until the calling party hangs up (which would be detected by the switching/routing entity 20).
  • the appropriate one of the functional units 34 ! ...34 ⁇ r of the controller 22 may proceed to automatically forward the incoming call to a voice mail system.
  • the appropriate one of the functional units 34 ⁇ ...34 ⁇ ⁇ of the controller 22 may proceed to automatically forward the incoming call to a suitable telephone number.
  • each one of the predetermined call handling commands recognizable by the speech recognition module 31 is associated with a respective action to be performed by the control module 38. Examples of actions performed by the control module 38 based on the detected call handling command are presented below.
  • the control module 38 exerts control over the switching/routing entity 20 such that it effects appropriate connections to connect the incoming call to the communication device 12. That is, the control module 38 interacts with the switching/routing entity 20 so that a voice communication path is established between the called party (i.e., the user 14) and the calling party (at the communication subsystem 28).
  • control module 38 may release a signal towards the communication device 12 to cause the communication device 12 to acquire a state as if the user 14 had actually answered the incoming call in a standard fashion, for example, by lifting a receiver of the communication device" 12 or pressing a button thereon.
  • the spoken response provided by the user 14 is "no" or "reject", which indicates a desire of the user 14 to not take the incoming call.
  • This can be referred to as a "call rejection command”.
  • the control module 38 since the user's desire to not take the incoming call is known, the control module 38 no longer causes emission of any voice message (and possibly ringing sound) from the speaker 42 to inform the user 14 of the incoming call.
  • the control module 38 may effectively disregard the incoming call signal being received at the switching/routing entity 20 until this signal is no longer received due to, for instance, the calling party (at the communication subsystem 28) hanging up.
  • control module 38 may generate a signal that is released into the second network portion 24 2 towards the communication subsystem 28, this signal being intended to indicate to the calling party that the user 14 (i.e. the called party) cannot be reached at this time.
  • the control module 38 may invoke the appropriate one of the functional units 34 1 ...34 ⁇ in order to allow the calling party to leave a voice mail message for the user 14.
  • the spoken response provided by the user 14 is "forward to voice mail", which indicates a desire of the user 14 to forward the incoming call to a voice mail system. This can be referred to as a "call forwarding command”.
  • the control module 38 proceeds to invoke the appropriate one of the functional units 34 ⁇ ...34jv in order to allow the calling party to leave a voice mail message for the user 14.
  • control module 38 may exert control over the switching/routing entity 20 such that it effects appropriate connections to forward the incoming call to the external entity' s voice mail system.
  • the user 14 may forward the incoming call in accordance with other telephony services to which the user 14 may be subscribed, by providing the appropriate call handling command. For instance, if call forwarding to an alternate telephone number is subscribed to, the user 14 may forward the incoming call to the alternate telephone number by uttering the appropriate call handling command such as "forward to office number" or any other command indicative of the alternate telephone number. In that case, the control module 38 proceeds to invoke the appropriate one of the functional units 34i...34;v in order to effect forwarding of the incoming call to the alternate telephone number.
  • the VACHO unit 30 attempts to reach the user 14 by causing the communication device 12 to emit an audible signal soliciting a spoken call handling command from the user 14.
  • the user 14 may indicate how he or she desires the incoming call to be handled. From the point of view of the user 14, he or she is able to (1) obtain knowledge about the calling party and (2) indicate how the incoming call is to be handled, without having to undertake any tactile interaction with the communication device 12 and even without looking at a display of the communication device 12. Incoming call handling can thus be effected in a touch-free manner from the perspective of the user 14.
  • eligibility of the user 14 to handle an incoming call using the VACHO service is established solely on a basis of the user's identity, regardless of the telephone number, IP address, or ESN which may be associated with the communication device 12.
  • the speech recognition module 31 of the VACHO unit 30 processes the signal 410 and detects the call handling command contained therein, but also effects a biometric signal processing operation.
  • This biometric signal processing operation is intended to verify whether the voice of the user 14 as contained in the signal 410 presents characteristics of one of the subscribers to the VACHO service.
  • the speech recognition module 31 may consult the database 26 or another memory (not shown) accessible by the speech recognition module 31, which will store biometric indicia (referred to as voice prints) for each subscriber to the VACHO service.
  • the VACHO unit 30 Upon finding a match between the voice of the user 14 as contained in the signal 410 and a voice print of a given subscriber to the VACHO service, the VACHO unit 30 concludes that the user 14 is eligible to handle the incoming call and thus proceeds to handle the incoming call in accordance with the detected call handling command. However, when a match is not found, the VACHO unit 3 O may send a signal to the communication device 12 to cause it to emit a message informing the user 14 that he or she may not handle the incoming call or prompting the user 14 to once again provide a spoken utterance to reattempt to find a matching voice print.
  • the above approaches to enhancing security may be particularly useful to prevent individuals who happen to be in the vicinity of the communication device 12 but are not necessarily allowed or authorized to handle incoming calls, from actually handling such incoming calls. Examples of situations in which this may arise include parents not wanting their children to handle incoming calls (e.g., when the parents are absent); visitors in an office, house or other building which should not be allowed to handle incoming calls; and several proximate subscribers to the VACHO service (e.g., call center agents in a room) not wanting call handling commands spoken by their neighbors to be interpreted as their own.
  • the outgoing call to be originated is destined for a called party subsystem which may be, for example, a communication subsystem reachable via the second network portion 24 2 such as the communication subsystem 28 or the communication subsystem 29 of the controller 22.
  • interaction between the communication device 12 and the VACHO unit 30 enables the VACHO unit 30 to process a signal produced by the communication device 12 in an attempt to detect a "call origination command" which may be contained in that signal as a result of an utterance spoken by the user 14. This allows the user 14 to originate an outgoing call without having to physically manipulate the communication device 12.
  • the microphone 40 of the communication device 12 continuously generates a signal indicative of sound sensed by the microphone 40, this signal being transmitted to the controller 60.
  • this signal is denoted by numeral 600 and is fed to the speech recognition module 48.
  • the user 14 in order for touch-free call origination to be effected, the user 14 is required to utter a "detectable" activation command in order to "wake up” (activate) the communication device 12.
  • detecttable is meant an activation command that can be detected by the speech recognition module 48, which may employ speaker-dependent or speaker-independent recognition.
  • detectable activation command may be the spoken utterance "phone on” or some other utterance that is not expected to be used regularly during ordinary conversation in the vicinity of the communication device 12.
  • a set of detectable activation commands may include commands that are intended to activate the communication device 12 in anticipation of a specific call origination activity.
  • the set of detectable activation commands may include utterances such as "phone on dial out” and "phone on voice mail".
  • a wide variety of other conceivable variants are within the scope of the present invention.
  • the speech recognition module 48 monitors the signal 600 produced by the microphone 40 and, at step 306, processes the signal 600 in an attempt to detect therein one of the detectable activation commands. In the absence of detection of a detectable activation command, i.e., the "NO" branch of step 306, the speech recognition module 48 returns to step 304 and continues its monitoring process. However, assuming that the user 14 does indeed utter (with sufficient volume) a specific activation command that is in fact a detectable activation command, this specific activation command will be contained in the signal 600 that was produced by the microphone 40 and hence will be detected by the speech recognition module 48. As a result, the "YES" branch of step 306 is taken and the communication module 50 proceeds to execute step 308.
  • a signal 602 indicative of the specific activation command is generated by the communication module 50.
  • the signal 602 is intended to indicate to the VACHO unit 30 that effecting a call origination activity using the communication device 12 appears to be desired.
  • the signal 602 may also include a replica of the signal 600 containing the specific activation command uttered by the user 14. It is noted that the signal 602 is produced with the communication device 12 not having been touched since the commitment of the user 14 to attempt to originate the outgoing call.
  • the signal 602 is then provided to the VACHO unit 30, specifically to the communication module 35, using a protocol such as SS7 (Signaling System 7), SEP (Session Initiation Protocol), etc., depending on the nature of the communication device 12 and the first network portion 24 1 .
  • SS7 Signal-to-Signaling System 7
  • SEP Session Initiation Protocol
  • the VACHO unit 30, specifically the communication module 35 receives the signal 602 and becomes aware that the user 14 desires to effect a call origination activity using the communication device 12. At this point, eligibility of the user 14 to effect a touch-free call origination activity is still unknown. Thus, at step 312, the control module 38 consults the database 26 to determine whether the user 14 subscribes to the VACHO service. The identity of the user 14 can be learned in various ways based on the signal 602, e.g., by the telephone number of the residence at which the communication device 12 is located (for a wired POTS phone), an IP address of the communication device 12 (for a VoIP phone), an ESN emitted by the communication device 12 (for a wireless phone), etc.
  • step 312 If it would have been determined that the user 14 did not subscribe to the VACHO service, no further action would have to be taken (i.e., the "NO" branch of step 312). However, as mentioned previously, for the purposes of the present example, it is assumed that the user 14 does indeed subscribe to the VACHO service. Having determined that the user 14 does subscribe to the VACHO service (i.e., the "YES" branch of step 312), the communication module 35 of the VACHO unit 30 proceeds to step 314, where it establishes a communication path 604 between itself and the communication module 50 of the communication device 12. Establishment of the communication path 604 can be done using a protocol such as SS7, SIP, etc., depending on the nature of the communication device 12 and the first network portion 24] .
  • a protocol such as SS7, SIP, etc.
  • the VACHO unit 30 thus knows that an eligible user (in this case the user 14) is accessing the VACHO service and therefore likely desires to effect a call origination activity.
  • the specific activation command uttered by the user 14 may already contain an indication of the nature of the call origination activity (such as placing a call or accessing a voice mail system), while in other cases (i.e., when it served merely to activate the communication device 12) it may not. 1
  • the communication module 35 may
  • This signal may contain either a confirmation request message or a command to emit
  • control module 54 causes the
  • VACHO service 17 wishes to continue with the VACHO service (e.g., by the user 14 having responded
  • the communication path 604 is kept alive and will convey the signal that is
  • the signal 608 is produced by the microphone 40 without requiring the
  • step 316 which is executed by the speech recognition
  • the speech recognition module 31 of the VACHO unit 30. Specifically, the speech recognition module 31
  • call origination command capable of being detected by the speech recognition module 31 is call destination information (e.g., a telephone number) uttered by the user 14.
  • the speech recognition module 31 compares each segment of speech to a plurality of recognizable speech segments such as various enunciations of the digits "zero", "one", "two”, etc.
  • a call origination command capable of being detected by the speech recognition module 31 is a recipient identifier (e.g., "John Smith", "voice mail") uttered by the user 14.
  • the speech recognition module 31 may employ speaker-dependent or speaker-independent recognition and thus the speech recognition module 31 may or may not have previously undergone a speech recognition training session with the user 14 to obtain a list of recipient identifiers expected to be used by the user 14.
  • Each recipient identifier is associated with respective call destination information (e.g., a telephone number) that allows proper routing of a call towards its destination, as if the user 14 had himself or herself submitted the call destination information.
  • the association between each recipient identifier and its respective call destination information may be stored in the database 26 or in another memory (not shown) accessible by the speech recognition module 31.
  • step 318 the speech recognition module 31 returns to step 316 and continues its monitoring process. However, assuming that the user 14 does indeed utter (with sufficient volume) a specific call origination command detectable by the speech recognition module 31 , this specific call origination command will be contained in the signal 608 that is produced by the microphone 40 and hence will be detected by the speech recognition module 31 , i.e., the "YES" branch of step 318 is taken.
  • the speech recognition module 31 extracts the call destination information corresponding to the specific call origination command. It is recalled that the call destination information can be obtained either directly from the user's utterance or indirectly by consulting the database 26 or other memory (not shown) accessible by the speech recognition module 31 after first processing a recipient identifier extracted from the user's utterance.
  • the control module 38 then proceeds with step 322. Specifically, responsive to obtaining call destination information (e.g. a telephone number) for the outgoing call, the control module 38 exerts control over the switching/routing entity 20 in order to set up the outgoing call as if the telephone number corresponding to the called party subsystem (such as the communication subsystem 28 or the communication subsystem 29) had been dialed by the user 14. In the case where the call is destined for the communication subsystem 28, control exerted on the switching/routing entity 20 may cause initiation of signaling activities with the second network portion 24 2 . Of course, the call may succeed or fail depending on various factors such as network congestion, availability of the called party subsystem, etc.
  • call destination information e.g. a telephone number
  • the communication device 12 and the VACHO unit 30 are capable of cooperating to enable entirely touch-free call origination.
  • the communication device 12 and the VACHO unit 30 are capable of cooperating to enable entirely touch-free call origination.
  • the user 14 he or she can originate an outgoing call without the need to lift a receiver, press any buttons, or make any keystrokes, penstrokes, mouse clicks or contact with a touch screen.
  • greater processing capabilities and databases are available for speech recognition purposes to effect outgoing call origination for the user 14.
  • by initiating outgoing call origination only after having received an indication that such call origination is desired one prevents wastage of bandwidth and processing power which would otherwise be needed to listen to communication devices of all subscribers of the VACHO service for potential spoken call origination commands.
  • the signal 602 indicative of the specific activation command that is generated by the communication module 50 and transmitted to the VACHO unit 30 includes a replica of the signal 600 containing the specific activation command uttered by the user 14.
  • the speech recognition module 31 effects a biometric signal processing operation to verify whether the voice of the user 14 as contained in the replica of the signal 600 presents characteristics of one of the subscribers to the VACHO service.
  • the speech recognition module 31 may consult the database 26 or another memory (not shown) accessible by the speech recognition module 31, which will store biometric indicia (referred to as voice prints) for each subscriber to the VACHO service.
  • biometric signal processing to verify the voice of the user 14 maybe effected on the signal 608 potentially containing a spoken call origination command.
  • controller 22 and/or the controller 60 may be implemented as pre-programmed hardware or firmware elements (e.g., application specific integrated circuits (ASICs), electrically erasable programmable read-only memories (EEPROMs), etc.), or other related components.
  • ASICs application specific integrated circuits
  • EEPROMs electrically erasable programmable read-only memories
  • certain portions of the controller 22 and/or the controller 60 may be implemented as an arithmetic and logic unit (ALU) having access to a code memory (not shown) which stores program instructions for the operation of the ALU.
  • ALU arithmetic and logic unit
  • the program instructions may be stored on a medium which is fixed, tangible and readable directly by these certain portions of the controller 22 and/or the controller 60 (e.g., removable diskette, CD-ROM, ROM, USB key or fixed disk).
  • the program instructions may be stored remotely but transmittable to these certain portions of the controller 22 and/or the controller 60 via a modem or other interface device (e.g., a communications adapter) connected to a network over a transmission medium.
  • the transmission medium may be either a tangible medium (e.g., optical or analog communications lines) or a medium implemented using wireless techniques (e.g., microwave, infrared or other transmission schemes).

Landscapes

  • Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Telephonic Communication Services (AREA)

Abstract

Système pour utilisateur de dispositif de communications, permettant le traitement d'appel entrant et l'émission d'appel sortant mains libres, par échange de messages vocaux avec le dispositif. Le système reçoit un signal produit par un microphone associé au dispositif et le traite pour tenter de détecter au moins tel ou tel commande vocale d'une pluralité de commandes vocales potentiellement inhérentes au signal. Les commandes comprennent au moins une commande de traitement d'appel vocale et au moins une commande d'émission d'appel vocale. Suite à la détection de la commande de traitement d'appel, le système lance le traitement d'appel entrant destiné au dispositif selon ladite commande détectée. Suite à la détection de commande d'émission d'appel, le système lance une tentative d'établissement d'appel sortant utilisant le dispositif selon ladite commande détectée.
PCT/CA2005/001942 2005-09-23 2005-12-21 Procede et systeme pour le traitement d'appel entrant mains libres et l'emission d'appel sortant mains libres WO2007033459A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CA2570695A CA2570695C (fr) 2005-09-23 2005-12-21 Methode et systeme de traitement sans touche des appels d'arrivee et d'envoi sans touche des appels de depart
US11/534,414 US8433041B2 (en) 2005-09-23 2006-09-22 Method and system to enable touch-free incoming call handling and touch-free outgoing call origination

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CAPCT/CA2005/001456 2005-09-23
PCT/CA2005/001457 WO2007033458A1 (fr) 2005-09-23 2005-09-23 Procedes et systemes pour gerer des appels sans contact
PCT/CA2005/001456 WO2007033457A1 (fr) 2005-09-23 2005-09-23 Procedes et systemes pour l'emission d'appel mains libres
CAPCT/CA2005/001457 2005-09-23

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
PCT/CA2005/001456 Continuation-In-Part WO2007033457A1 (fr) 2005-09-23 2005-09-23 Procedes et systemes pour l'emission d'appel mains libres

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US11/534,414 Continuation US8433041B2 (en) 2005-09-23 2006-09-22 Method and system to enable touch-free incoming call handling and touch-free outgoing call origination

Publications (1)

Publication Number Publication Date
WO2007033459A1 true WO2007033459A1 (fr) 2007-03-29

Family

ID=37888483

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CA2005/001942 WO2007033459A1 (fr) 2005-09-23 2005-12-21 Procede et systeme pour le traitement d'appel entrant mains libres et l'emission d'appel sortant mains libres

Country Status (1)

Country Link
WO (1) WO2007033459A1 (fr)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1981256A1 (fr) * 2007-04-11 2008-10-15 Huawei Technologies Co., Ltd. Procédé de reconnaissance vocale et serveur de reconnaissance vocale
EP2381659A1 (fr) * 2010-04-23 2011-10-26 Research In Motion Limited Mise en attente d'appel audible pendant un appel
WO2018035461A1 (fr) * 2016-08-19 2018-02-22 Amazon Technologies, Inc. Activation de la commande vocale d'un dispositif téléphonique
US10194023B1 (en) 2017-08-31 2019-01-29 Amazon Technologies, Inc. Voice user interface for wired communications system
US10326886B1 (en) 2017-08-31 2019-06-18 Amazon Technologies, Inc. Enabling additional endpoints to connect to audio mixing device
US10911596B1 (en) 2017-08-31 2021-02-02 Amazon Technologies, Inc. Voice user interface for wired communications system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6101473A (en) * 1997-08-08 2000-08-08 Board Of Trustees, Leland Stanford Jr., University Using speech recognition to access the internet, including access via a telephone
JP2001339504A (ja) * 2000-05-26 2001-12-07 Sharp Corp 無線通信機
US6505163B1 (en) * 2000-08-09 2003-01-07 Bellsouth Intellectual Property Corporation Network and method for providing an automatic recall telecommunications service with automatic speech recognition capability
US6728671B1 (en) * 2000-03-29 2004-04-27 Lucent Technologies Inc. Automatic speech recognition caller input rate control
US6799098B2 (en) * 2000-09-01 2004-09-28 Beltpack Corporation Remote control system for a locomotive using voice commands

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6101473A (en) * 1997-08-08 2000-08-08 Board Of Trustees, Leland Stanford Jr., University Using speech recognition to access the internet, including access via a telephone
US6728671B1 (en) * 2000-03-29 2004-04-27 Lucent Technologies Inc. Automatic speech recognition caller input rate control
JP2001339504A (ja) * 2000-05-26 2001-12-07 Sharp Corp 無線通信機
US6505163B1 (en) * 2000-08-09 2003-01-07 Bellsouth Intellectual Property Corporation Network and method for providing an automatic recall telecommunications service with automatic speech recognition capability
US6799098B2 (en) * 2000-09-01 2004-09-28 Beltpack Corporation Remote control system for a locomotive using voice commands

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1981256A1 (fr) * 2007-04-11 2008-10-15 Huawei Technologies Co., Ltd. Procédé de reconnaissance vocale et serveur de reconnaissance vocale
EP2381659A1 (fr) * 2010-04-23 2011-10-26 Research In Motion Limited Mise en attente d'appel audible pendant un appel
US8620282B2 (en) 2010-04-23 2013-12-31 Blackberry Limited In-call, audible call waiting
WO2018035461A1 (fr) * 2016-08-19 2018-02-22 Amazon Technologies, Inc. Activation de la commande vocale d'un dispositif téléphonique
US9967382B2 (en) 2016-08-19 2018-05-08 Amazon Technologies, Inc. Enabling voice control of telephone device
US10187503B2 (en) 2016-08-19 2019-01-22 Amazon Technologies, Inc. Enabling voice control of telephone device
US10326869B2 (en) 2016-08-19 2019-06-18 Amazon Technologies, Inc. Enabling voice control of telephone device
US10194023B1 (en) 2017-08-31 2019-01-29 Amazon Technologies, Inc. Voice user interface for wired communications system
US10326886B1 (en) 2017-08-31 2019-06-18 Amazon Technologies, Inc. Enabling additional endpoints to connect to audio mixing device
US10911596B1 (en) 2017-08-31 2021-02-02 Amazon Technologies, Inc. Voice user interface for wired communications system

Similar Documents

Publication Publication Date Title
US8433041B2 (en) Method and system to enable touch-free incoming call handling and touch-free outgoing call origination
US9247037B2 (en) Methods and systems for touch-free call origination
EP3577646B1 (fr) Gestion d'appels sur un dispositif partagé à activation vocale
US7899447B2 (en) Telephone and method of controlling telephone
US5905774A (en) Method and system of accessing and operating a voice message system
US7395057B2 (en) System and method for reconnecting dropped cellular phone calls
US8774369B2 (en) Method and system to provide priority indicating calls
WO2007033459A1 (fr) Procede et systeme pour le traitement d'appel entrant mains libres et l'emission d'appel sortant mains libres
US20070003045A1 (en) Off hold notification in communication networks
WO2011050646A1 (fr) Procédé et dispositif de traitement d'appel
US9042526B2 (en) Method and apparatus for enabling a calling party to leave a voice message for a called party in response to a command provided by the calling party
JP2008060674A (ja) 迷惑電話対応機能を備える構内交換機及び電話機
JP2016149636A (ja) 認証装置、電話端末、認証方法および認証プログラム
CA2570695C (fr) Methode et systeme de traitement sans touche des appels d'arrivee et d'envoi sans touche des appels de depart
EP1737205B1 (fr) Initiation centralisée de conferences
TW200307447A (en) In-bound call directed telephone station and method of directing a telephone station based on an in-bound call
JP6090027B2 (ja) 特定音付き音声コマンド対応情報端末
US9014346B2 (en) Methods and systems for touch-free call handling
CN111884886B (zh) 一种基于话机的智能家居的通信方法和通信系统
US8897427B2 (en) Method and apparatus for enabling a calling party to leave a voice message for a called party
JP2015023485A5 (fr)
US6963637B2 (en) Methods, systems, and media to capture a redialing sequence and to redial
JPS607259A (ja) 音声処理交換方式
JPH09214599A (ja) 特定者着信方法および特定者着信機能付き電話機
US20150023482A1 (en) Telephone to computational device association

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 11534414

Country of ref document: US

WWE Wipo information: entry into national phase

Ref document number: 2570695

Country of ref document: CA

WWP Wipo information: published in national office

Ref document number: 11534414

Country of ref document: US

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

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 05823541

Country of ref document: EP

Kind code of ref document: A1