Abstract: Methods for analysing an interactive voice response (IVR) system are disclosed. In the methods, prompts are issued from the IVR system and user input made in response to the prompts from the IVR system is received. One method involves displaying the prompts issued by the IVR system to an operator; and receiving input data from the operator, the data defining whether any change to the IVR system is recommended and/or any recommended changes to the IVR system. Another method involves detecting the occurrence of an unexpected event by comparing the user input against a predefined set of rules, each rule being associated with one or more of the unexpected events; and taking a predefined action in response to the detection of one or more of the unexpected events.

Abstract: An interactive voice response process that permits an intelligent interactive voice system to communicate with a caller includes receiving a call and connecting the caller with the system. The process also includes identifying the caller, determining if the caller is a first time caller or a repeat caller, and interactively communicating with the caller in accordance with an interactive script. For each first time caller, the process establishes a personal profile of the caller from information gathered from the caller. The process then develops a predictive personalized interactive communication dialog for future calls from the caller based on information gathered from the caller during the interactive communication and stored in the caller's personal profile.

Abstract: Systems and techniques for improved user prompting. A system according to one aspect of the invention includes a central server hosting various modules providing services to users. The modules suitably employ voice recognition in order to interpret user inputs. Each module has access to user information that includes information indicating the user's experience with each function of each module. When a module needs to issue a prompt to the user, it retrieves and examines the user information to determine the user's experience with the module and function. Suitably, each module is operative to categorize a user as belonging to an experience category, such as novice, intermediate and expert based on the user's level of experience with the function. The module selects a prompt associated with the user's level of experience with the function and presents it to the user.

Abstract: A method for improving the recognition confidence of alphanumeric spoken input, suitable for use in a speech recognition telephony application such as a voice response system. An alphanumeric candidate is determined from the spoken input, which may be the best available representation of the spoken input. Recognition confidence is compared with a preestablished threshold. If the recognition confidence exceeds the threshold, the alphanumeric candidate is selected to represent the spoken input. Otherwise, present call data associated with the spoken input is determined. Call data may include automatic number identification (ANI) information, caller-ID information, and/or dialed number information service (DNIS) information. Information associated with the alphanumeric candidate and information associated with the present call data are correlated in order to select alphanumeric information that best represents the spoken input.

Abstract: A method of registering a multi mode communications device for service can include registering a multi-mode communications device by receiving and transmitting registration information over separate communications networks.

Abstract: A messaging system is provided that includes: (a) an interface 206 for receiving a request to play a message audibly to a subscriber; and (b) a message retrieval agent 224 for determining whether the message comprises marked information. When the message comprises marked information, the agent 224 performs one or more of the following operations: (b1) display the marked information to the subscriber; (b2) alter an audio playback speed of the marked information to the subscriber, the playback speed of the marked information being different from a playback speed of unmarked information; and (b3) audibly play only one of the marked information and unmarked information to the subscriber.

Abstract: A method comprises receiving a plurality of voice sessions and creating a unique identifier for each of the plurality of voice sessions, wherein each identifier is unique for the duration of its associated voice session. The method also includes assigning the unique identifiers to the associated voice session, and creating a unique data session for each voice session. The method further includes assigning the unique identifier of each voice session to the data session associated with its voice session. The method also includes receiving a plurality of voice sessions and a plurality of data sessions at a manager, and matching one of the plurality of received voice sessions with its associated data session based at least in part on the unique identifier. The method further includes communicating the matched voice session and data session to one of a plurality of agents.

Abstract: The system monitors the activity of customers, agents, and industry-experts in a network for new topics relevant to a business and the interests in those topics. A determination is made automatically if there is enough interest to warrant adding a skill. If there is not enough interest, the system continues to monitor for topics and interests. If there is enough interest, the system automatically projects a resource needed for a skill. The system monitors internal resources and the network to determine if the resource needed for the skill exists in an internal resource. If the resource needed for the skill exists in an internal resource, the internal resource is reallocated. If the resource needed for the skill does exist in the internal resource, the system monitors the network for an external resource that has the skill.

Abstract: A system and method for provisioning communications services. A remote device controlled by a user is linked with a provisioning system. A verbal selection of a menu associated with a library is received for performing one or more actions within the provisioning system. One or more verbal commands associated with the menu are received. A determination is made of an action within the library associated with the one or more verbal commands. The action associated with the one or more verbal commands is performed in the provisioning system to provision the communications services.

Abstract: A single, subjective numerical rating to evaluate the performance of a telephone-based spoken dialog system is disclosed. This CE rating is provided by expert human listeners who have knowledge of the design of the dialog system. Different human raters can be trained to achieve a satisfactory level of agreement. Furthermore, a classifier trained on ratings by human experts can reproduce the human ratings with the same degree of consistency. More calls can be given a CE rating than would be possible with limited human resources. More information can be provided about individual calls, e.g., to help decide between two disparate ratings by different human experts.

Abstract: A method implemented in a computer infrastructure having computer executable code having programming instructions tangibly embodied on a computer readable storage medium. The programming instructions are operable to receive an audio stream of a communication between a plurality of participants. Additionally, the programming instructions are operable to filter the audio stream of the communication into separate audio streams, one for each of the plurality of participants, wherein each of the separate audio streams contains portions of the communication attributable to a respective participant of the plurality of participants. Furthermore, the programming instructions are operable to output the separate audio streams to a storage system.

Abstract: A method for performing automated telemarketing is disclosed. The method includes receiving potential customer data that includes a telephone number; initiating a telephone call to the telephone number using an auto-dialing technology; receiving notification that the potential customer has answered the telephone call; sending a verbal greeting to the potential customer in response to receiving the notification; conversing with the potential customer using speech recognition technology, the conversing including receiving a message from the potential customer; and updating the potential customer data responsive to the message received from the potential customer.

Abstract: A voice channel connection and a data channel connection are established with a structured voice interaction system. Navigation information for and provided by the structured voice interaction system is received over the data channel connection. The data channel navigation information is coordinated with navigation information provided by the structured voice interaction system over the voice channel connection.

Abstract: An interactive voice and data response system that directs input to a voice, text, and web-capable software-based router, which is able to intelligently respond to the input by drawing on a combination of human agents, advanced speech recognition and expert systems, connected to the router via a TCP/IP network. The digitized input is broken down into components so that the customer interaction is managed as a series of small tasks performed by a pool of human agents, rather than one ongoing conversation between the customer and a single agent. The router manages the interactions and keeps pace with a real-time conversation. The system utilizes both speech recognition and human intelligence for purposes of interpreting customer utterances or customer text, where the role of the human agent(s) is to input the intent of caller utterances, and where the computer system—not the human agent—determines which response to provide given the customer's stated intent (as interpreted/captured by the human agents).

Abstract: A system and method for secure payment transactions is provided. The system may include an adaptive payment server including one or more processors configured to receive a first communication including first identification information from a first communication device on a first communication channel. The adaptive payment server may identify a second communication device based on the first identification information and initiate a second communication to the second communication device on a second communication channel, which may be discrete from the first communication channel. The adaptive payment server may receive second identification information from the second communication device on the second communication channel and authenticate the payment transaction using the first identification information and the second identification information.

Abstract: A system and method to select and retrieve contact center transactions from a set of transactions stored in a queuing mechanism. The system includes an interactive voice response system configured to accept at least one call and dynamically populate a web form with call data associated with the at least one call. The system also includes a queuing engine configured to allow a call agent to access the call data prior to the at least one call being connected to the call agent.

Abstract: Tags, such as XML tags, are inserted into email to separate email content from signature blocks, privacy notices and confidentiality notices, and to separate original email messages from replies and replies from further replies. The tags are detected by a system that renders email as speech, such as voice command platform or network-based virtual assistant or message center. For example, the system can detect the signature block or privacy notice tags and not render the signature block or privacy notice as speech. The system can render an original email message in one voice mode and the reply in a different voice mode. The tags can be inserted to identify a voice memo in which a user responds to a particular portion of an email message. Preferably, an email server that receives and stored the email message inserts the tags into the email. Alternatively, the tags could be inserted by an email client application.

Abstract: A method and system for implementing run-time control over voice application behavior. The method includes identifying a plurality of control point locations within a given voice application and a plurality of corresponding required responses to the control points. A design-for-control methodology is used to instrument the control points of voice application. A control agent is configured with web-based controls to manage the control points. The control points are used to alter the voice application's behavior during run-time.

Abstract: A telephone and a method for routing a telephone call using the telephone is provided. The telephone includes a microprocessor and a transceiver coupled to the microprocessor. The telephone further includes a voice recognition unit coupled to the microprocessor. The unit is further configured to determine when the user is speaking proximate the unit and to generate a match signal when the user is speaking. The microprocessor is configured to generate a command signal to induce the transceiver to transmit a voice mailbox routing signal to a telephone switching center upon receipt of the match signal from the unit.

Abstract: The architecture of the present invention includes a multi-media multi-network communication server connected to a variety of access and delivery platforms via a variety of communication networks. Access to services is controlled and billed by a virtual prepaid card and account that can be converted into a physical prepaid card that is delivered to the user via a physical delivery network such as the Postal Service or a point of sale. The access platforms are used by senders, recipients or agents to access their digital mailboxes on a multi-network communication server and to send and receive calls and messages. The messages can be in electronic format such as text, audio, graphic images, video, and audio-video. The calls can be packet switched or circuit switched. The multi-network communication may send a notification message to the recipient, indicating that a message has been received. The message can be accessed remotely or wireless.

Abstract: A secure payment method, system or computer readable medium for a merchant's interactive voice response system are disclosed. The merchant's interactive voice response system receives customer calls and requests a payment from the customer. The customer responds to the request by providing over a data network authentication information and payment amounts for a payment service. The payment service provides the customer with a token which is communicated to the merchant's interactive voice response system, and the merchant's interactive voice response system transmits the token back to the payment service. Upon validating the token, the payment service issues an electronic payment or payment information to the merchant. The merchant's interactive voice response system announces a successful payment to the customer.

Abstract: Methods and apparatuses are disclosed for generating commissions from e-commerce transaction assistance provided by a network-based text-to-speech (TTS) alert system. The network-based text-to-speech (TTS) alert system takes a user's textual and/or multimedia input from a user interface to schedule delivery of text-to-speech-converted information as a reminder call to a user once the user's desired time or an event for the reminder delivery is reached. If the delivered reminder call is associated with a particular e-commerce transaction, then the network-based text-to-speech (TTS) alert system is capable of taking a user feedback for authorization of the particular e-commerce transaction over an IVR interface during the reminder call or an online calendar interface.

Abstract: Methods and systems for operating a virtual collections call center system are described. A system may include a database server, a telephony server, an auto dialer system, a Web server, and call agent computer systems, each geographically separated from the database server, the telephony server, the auto dialer system, the Web server and other call agent computer systems. The database server may store debtor records, each including a debtor telephone number. The telephony server may retrieve a debtor record from the database server. The auto dialer system may initiate a communication session with a debtor based on the debtor telephone number of the retrieved debtor record, establish a connection with the call agent after the debtor has accepted the communication session, and alert the telephony server that the communication session has been established. The Web server may initiate a Web session with the call agent computer system.

Abstract: A method includes storing a profile associated with a user of a telephone and, based upon the profile, presenting the user with an option to search, browse, subscribe to, or bookmark content provided by a plurality of IVR content providers.

Abstract: A transaction authorisation system for allowing a customer to authorise transactions relating to an institution account, the system including a data storage for enabling access to identification data associated with the customer and a remote communication device (RCD) of the customer, and security identifier data associating the customer account with the identification data. The system also includes a communication device for receiving an authorisation request, which is referenced to the security identifier data, in relation to the transaction from the institution and for enabling communication with the customer via the RCD to authorise a transaction on the customer account. A system data processor identifies the customer and RCD using the identification data and determines if the transaction is authorised by the customer. The communication device provides an indication, which is referenced to the security identifier data, to the institution of whether or not the transaction is authorised by the customer.

Abstract: Answering machines and voice mailbox systems are normally provided in modern communications systems. When a communications subscriber is temporarily unreachable at the location of their fixed network telephone, incoming calls can be accepted by an answering machine and voice messages can be recorded. The drawback of this procedure is that messages containing important information cannot be promptly conveyed to the communications subscriber. During incoming voice messages, their content is evaluated with the aid of a speech recognition system. As a result, content-based prioritization of voice messages is made possible in a communications system and the receiver is notified of the incoming voice messages according to the prioritization.

Abstract: Certain exemplary embodiments provide a method, comprising: automatically detecting at an agent an installation of a communications device to a local network coupled to the agent; automatically offering via the communications device a plurality of user-selectable service options relating to a service provider's network and relating to at least one capability of the communications device, the at least one capability detected by the agent; in response to a selection of at least one service option from the plurality of service options, providing via the agent a user connection address.

Abstract: A system, method and software for implementing an automated call routing application in a speech enabled call center environment are provided. In operation, the invention provides for the identification of a call center transaction selection from a natural language user utterance and the invocation of one or more scripts operable to route the user to a call center service agent configured to service the selected transaction. In the event a transaction selection cannot be readily identified or can only be partially identified, the invention provides for the initiation of a dialog module or script directed to eliciting a discernable transaction selection and/or the presentation of one or more menus from which the user may select an available call center transaction.

Abstract: A recruiting system and method includes an automated candidate opt-in confirmation system for identifying and screening job candidate resumes that permits at least one potential candidate to opt-in to seek a job opportunity. The recruiting system enables a candidate to opt-in using a telephone, the Internet, or through any other suitable mediums or methods. The recruiting system and method provides a highly effective tool for job recruiters to select and identify qualified candidates that want to pursue a specified job opportunity quickly and efficiently.

Abstract: A system, method and software are described for facilitating transitions between speech-enabled applications employing action-object matrices. In an exemplary embodiment, an automatic call router determines a service agent destination by identifying an action-object combination included in a user utterance. In addition to forwarding the user to the service agent destination, the automatic call router sends one or more aspects of the user utterance to the service agent for use therewith. The service agent may then use aspects of the forwarded information to request further information from the user or to begin performance of a user desired transaction.

Abstract: Methods and systems are disclosed for allowing financial transactions to be conducted using consumer devices. In some embodiments, the consumer device is a mobile communication device, such as a mobile phone. A payer initiates a transaction by sending a payment request message from a mobile phone which specifies the payee and amount to be paid. Payees are identified by unique aliases, which are maintained in a database. The aliases, in turn, are comprised of multiple parts. Each part of the alias may identify a relevant aspect of the transaction. For example, one part of the alias may identify the payee and another part of the alias may identify the financial institution of the account of the payee. Methods for assembling the enrollment and alias database are included.

Abstract: A system and method for delivering interactive voice messages using a voice messaging system are disclosed. In an illustrative embodiment, the system comprises a voice messaging processor and memory containing machine readable instructions which, when executed by the processor, enable the voice messaging system to: receive an inbound call from a sender; record an interactive voice message from the sender directed to at least one recipient; receive a voice message retrieval request from a recipient; play the interactive voice message for the recipient; and initiate an interactive session with the recipient to elicit responses from the recipient regarding the interactive voice message. In one aspect of the invention, an application server is provided for generating interactive voicemails and placing the inbound call from the sender to the voice messaging processor.

Abstract: Methods, apparatus, and products are disclosed for dynamically publishing directory information for a plurality of interactive voice response (‘IVR’) systems through an IVR directory service that include: providing a description of a web services publication interface for the IVR directory service; receiving, on behalf of one or more IVR systems, web services publication requests through the publication interface; determining, in response to the web services publication requests, directory information for each IVR system requesting publication; adding the directory information for each IVR system to an IVR system directory; generating a voice mode user interface to reflect the directory information for each IVR system added to the IVR system directory; and interacting, using the voice mode user interface, with a caller to identify a particular IVR system in dependence upon the IVR system directory and query information provided by the caller and to connect the caller with the identified IVR system.

Abstract: The inventive method for remotely maintaining and controlling a security system comprises using a device to communicate using voice capable technology with an IVR in a host facility, selecting an action from a plurality of actions provided by the IVR, performing the action on the security system, and receiving notification of performance of the action, wherein the host facility contacts the security system to perform the action. In one embodiment, the actions can control and/or monitor the security system. The method can further comprise creating an account with an identification code on the host facility, and validating the code on the IVR. The method can also include translating the selected action into a command, sending a message to a GSM device in the security system, and, in response to the message, establishing a GPRS session between the security system and the host facility, wherein the session performs the command.

Abstract: An apparatus, method, and a computer program on a computer readable medium are provided for speedy delivery of a communication for a customer from a server to a client vehicle communication unit (VCU) installed in a vehicle of the customer, by establishing a connection between the server and the client VCU, and acquiring an ignition status from the client VCU as an indication of whether the customer is available in the vehicle for receiving the communication. The communication may be delivered immediately upon acquiring an IGNITION ON status. The message is stored if an IGNITION OFF status is acquired, and available for immediate delivery when the ignition is next turned on.

Abstract: A computer-implemented method and system for confirming that a remote consultation between a professional and a client occurred, including monitoring a remote consultation call between a professional and a client using a remote consultation system, storing information of the consultation, and confirming that the consultation took place using the stored information. The consultant can be a healthcare professional such as a doctor, and the client can be a patient.

Abstract: Systems and methods are introduced for accessing information content while holding on a telephone call. Instructions provide an automated message voice recognition menu selection system when a caller is placed on hold. A spoken voice recognition response unit associates a category context and, responsive to the user category selection, provides one or more information content titles representing information files including fractional samples of information content. Sales data and critic reviews of the information content via a streaming data page is uploaded into the user instance of the system. The streaming data page is a fractional, recognizable portion of a song. A context based artificial intelligence voice recognition systems further interacts with the user while holding on a telephone call subsequently playing at least a portion of a user selected title unless the user returns to the previous menu or terminates the service to complete the held call.

Abstract: A system for generating usage statistics for a communications routing system from data generated at routing points and at end points of the system has a processor having access to the communications routing system for analyzing the data and generating the statistics, and a server having access to the processor for rendering the generated statistics into a format for display. The data used to generate the statistics includes routing path information for events routed through the communications routing system and optionally interaction histories recorded at certain routing points and end points in the communications routing system.

Abstract: The invention concerns an automated task classification system that operates on a task objective of a user. The system may include a meaningful phrase generator that generates a plurality of meaningful phrases from a set of verbal and non-verbal speech. Each of the meaningful phrases may be generated based on one of a predetermined set of the task objectives. A recognizer may recognize at least one of the generated meaningful phrases in an input communication of the user and a task classifier may make a classification decision in response to the recognized meaningful phrases relating to one of the set of predetermined task objectives.

Abstract: Email subscribers are notified of the receipt of new email messages when they are not at their computers via voice or page. An email notification server polls the email server corresponding to the subscriber's email account for the presence of new email messages. New email messages are obtained. Header information is extracted. If new email notification is by voicemail, the extracted header information is converted from text to voice. A voicemail message containing the extracted header information is saved on the voicemail system corresponding to the subscriber for whom the email message was intended. The email notification server can also send a page to notify the subscriber of the presence of new email.

Abstract: A personal Interactive Voice Response (IVR) system includes a plurality of IVR servers communicating personal IVR service node information in a network and a plurality of personal IVR service node clients coupled to the plurality of IVR servers communicating the personal IVR service node information. The plurality of personal IVR service node clients have a client—server relationship with the plurality of IVR servers. The personal IVR system further includes facilities for managing transmission of the personal IVR service node information using a Voice over Internet Protocol (VoIP) technology.

Abstract: An interactive voice response mapping system (IVRMS) is used in a transaction between a waiting party and a queuing party, with the queuing party having a queuing calling system (QCS), and the IVRMS adapted to communicate with the QCS and to build an IVR map of the QCS.

Abstract: An independent communications system (ICS) is used in a transaction between a waiting party and a queuing party, with the queuing party having a interactive voice response (IVR). The IVR includes multiple nodes and the ICS is adapted to connect to a particular node in the IVR.

Abstract: A method comprising receiving a request to compose a message; outputting a first prompt requesting a recipient for the message; receiving a first audible response to the first prompt, the first audible response including a recipient of the message; outputting a second prompt requesting a body for the message; receiving a second audible response to the second prompt, the second audible response including a body of the message; and composing the message. An electronic device for voice messaging comprising an audible guide module for audibly prompting a user for recipient information and for audibly prompting a user for message information; a voice recognition module for interpreting received responses to the audible prompt for the recipient information and the audible prompt for the message information; and a message compiler module for creating a message from the responses to the audible prompt for the recipient information and the audible prompt for the message information.

Abstract: An automated multimedia call center device may receive a verbal request for information from a user device during a multimedia session between the automated multimedia call center device and the user device. The automated multimedia call center device may further obtain a group of recognition results for the verbal request using speech recognition, cause at least two recognition results of the group of recognition results to be visually displayed on the user device, receive selection of one recognition result of the at least two recognition results, perform a search using the selected one recognition result to obtain multimedia content, and provide the multimedia content to the user device.

Abstract: A call holding voice message transmitting apparatus and method in a mobile communication terminal are disclosed that transmit voice data, preferably stored in the terminal, to a caller in a situation in which the user of the terminal cannot receive an incoming call from the caller. The apparatus can include a key input unit to input a command to the terminal, a controller that generates a control signal adapted to execute the command, a microphone that converts a voice into an analog voice signal and a voice encoder that converts the analog voice signal into a digital voice signal. A memory can retrievably store the digital voice signal outputted from the voice encoder and a voice decoder converts the digital voice signal into an outgoing analog voice signal. A selection device outputs a selected one of the analog voice signal from the microphone and the outgoing analog voice signal from the voice decoder in response to the control signal from the control unit.

Abstract: A unified messaging interface and associated methods that enables mobile communication device users to initiate the creation of a message for a recipient without being required to explicitly specify the type of message that is to be created. The mobile communication device supports multiple message types, such as voice, text, and picture messages. The user begins providing message content to the communication device by, for example, speaking, entering text, or clicking a shutter of a camera. The unified messaging interface detects the nature of the content and creates a corresponding type of message. The user can indicate a desire to create and send a message by performing “one-click” action. The one-click action is an operation performed on the device that can be instantiated as a single button-press on the keypad; selection of a single soft key by depressing a button on the keypad or touching the screen of the device; or issuance of a single voice command.

Abstract: A voice response system attempts to respond to spoken user input and to provide computer-generated responses. If the system decides it cannot provide valid responses, the current state of user session is determined and forwarded to a human operator for further action. The system maintains a recorded history of the session in the form of a dialog history log. The dialog history and information as to the reliability of past speech recognition efforts is employed in making the current state determination. The system includes formatting rules for controlling the display of information presented to the human operator.

Abstract: A method and apparatus for resuming a session between a client device and an IVR system in customer service. The method includes the following steps: reestablishing the session in customer service; determining whether there is status information of an abnormally terminated session corresponding to the reestablished session in customer service; retrieving the status information of the abnormally terminated session in customer service; and resuming the session between the client device and the IVR system in customer service according to the retrieved status information.

Abstract: A method for operating a voice-based interactive entertainment program, the method including: a) receiving a voice communication from at least one user; b) selecting output in accordance with a voice-based interactive entertainment program, programmed with a plurality of interacting autonomous virtual performers; c) presenting the output to the user; d) prompting the user for input at a plot point of the voice-based interactive entertainment program; e) receiving the input from the user; f) selecting output at least partly in accordance with the voice-based interactive entertainment program and the input; and g) presenting to the user the output selected in step f).