Abstract: Disclosed herein are systems, computer-implemented methods, and tangible computer-readable storage media for speaker recognition personalization. The method recognizes speech received from a speaker interacting with a speech interface using a set of allocated resources, the set of allocated resources including bandwidth, processor time, memory, and storage. The method records metrics associated with the recognized speech, and after recording the metrics, modifies at least one of the allocated resources in the set of allocated resources commensurate with the recorded metrics. The method recognizes additional speech from the speaker using the modified set of allocated resources. Metrics can include a speech recognition confidence score, processing speed, dialog behavior, requests for repeats, negative responses to confirmations, and task completions.

Abstract: A method for speaker adaptation includes receiving a plurality of media files, each associated with a call center agent of a plurality of call center agents and receiving a plurality of terms. Speech processing is performed on at least some of the media files to identify putative instances of at least some of the plurality of terms. Each putative instance is associated with a hit quality that characterizes a quality of recognition of the corresponding term. One or more call center agents for performing speaker adaptation are determined, including identifying call center agents that are associated with at least one media file that includes one or more putative instances with a hit quality below a predetermined threshold. Speaker adaptation is performed for each identified call center agent based on the media files associated with the identified call center agent and the identified instances of the plurality of terms.

Abstract: A script for an interactive communication is dynamically adjusted during the interactive communication. The interactive communication is monitored over a communication network using a computer with a processor and memory for input during the interactive communication. Input incompatible with a script for the interactive communication is detected for the interactive communication. The incompatible input is categorized. The script is dynamically adjusted during the interactive communication into a dynamically updated script in accordance with the categorizing. Information is provided over the communication network to the initiator in accordance with the dynamically updated script.

Abstract: Methods and systems obtain profile information from individuals using automation to select and provide the questions that are given to the individual. The answers the individuals provide to the questions can then be used to generate the profile information. Subsequent questions are selected and presented according to analysis of the previous answers. The exchange of the questions and answers occurs over a communications network and may take the form of emails, web page interfaces, wireless data messages, or verbal communication over a voiced call. The answers are analyzed to determine certain characteristics, such as the personality type, mood, and gender of the individual. The subsequent questions are selected based on the characteristics that are found from the answers to facilitate the information exchange between the automated system and the individual.

Abstract: A system and method are presented for routing a communication through monitoring one or more of words and voice characteristics of a communicant during an interaction. A communication may be handled based on a score. A score may be calculated based on several factors that are analyzed during an interaction, such as, amplitude, word usage, call metrics, etc. Previous interactions of communicants may also be factored into a score. Such handling may include specialized routing of the communication to a designated handler, for example. A communication may be continually evaluated during its occurrence and said evaluation data stored for future use.

Abstract: Methods, systems and articles for receiving, by a telecommunication device, audio input through a unified audio interface are disclosed herein. The telecommunication device is further configured to determine whether to handle the audio input as a command, as a request of a telecommunication device application, or as a network search request, the determining being based on one or more user-configurable rules or priorities.

Abstract: For clearing transaction data selected for a processing, there is generated in a portable data carrier (1) a transaction acoustic signal (003; 103; 203) (S007; S107; S207) upon whose acoustic reproduction by an end device (10) at least transaction data selected for the processing are reproduced superimposed acoustically with a melody specific to a user of the data carrier (1) (S009; S109; S209). The generated transaction acoustic signal (003; 103; 203) is electronically transferred to an end device (10) (S108; S208), which processes the selected transaction data (S011; S121; S216) only when the user of the data carrier (1) confirms vis-à-vis the end device (10) an at least partial match both of the acoustically reproduced melody with the user-specific melody and of the acoustically reproduced transaction data with the selected transaction data (S010; S110, S116; S210).

Abstract: A two-way voice interface allows communication by telephone between a supervisory control and data acquisition (SCADA) system and a human operator. A phone-HMI gateway communicates with the SCADA system through an application programming interface (API), composes messages to the operator in text format and interprets text derived from voice commands from the operator. A cloud telephone service is used to convert from voice to text and from text to voice, and to set up the telephone connection with the human operator.

Abstract: Systems and methods to provide anonymous communication connections between customers in different countries/regions and service providers. Different call-in references are configured for customers residing in different regions and/or having different language preferences. Different prices are computed for foreign customers based on a single price of a service provider and the call-in references used by the customers to initiate the anonymous connections to take into account of the international/long distance call charges. Currency conversion is performed based on exchange rates in backend payment management. Location information of service providers and customers is provided in a configurable way, based on preference, service category, without compromising privacy.

Abstract: A smart interactive voice response (IVR) system of the connection server configured to allow customized customer handling based on information known/gathered about individual customers. For example, based on matching the parameters of the current call from a mobile device with previous calls from the mobile device, the system may identify the identity of the caller, the identity of the callee, the language preference of the caller, the payment information for settling the cost of the current call, etc. IVR prompts can be customized based on the preference of the caller and known information about the call.

Abstract: Disclosed is a method, apparatus, system and non-transitory computer program product configured to process user call responses and assign caller specific preferences to the user based on the caller's feedback. One example method of processing spoken words from a user of a calling platform may include operations, such as calling a user via a call processing device, and sending a call prompt message to the user after the user has answered the call, the call prompt message soliciting a user response. The user may respond and the response is received as a spoken call greeting from the user in response to the call prompt message. Other operations may include recording the spoken call greeting, and determining whether the spoken call greeting is indicative of a language preference. The system may process the user's word or utterances and assign language preferences to the user based on the user provided information.

Abstract: An electronic device includes a voice processing unit, a wireless communication unit, and a combining unit. The voice processing unit receives speech signals. The wireless communication unit sends the speech signals to a server. The server converts the speech signals into a text message. The wireless communication unit receives the text message from the server. The combining unit combines the text message and the speech signals into a combined message. The wireless communication unit further sends the combined message to a recipient. A related server is also provided.

Abstract: A method for interpreting messages, user-defined alert conditions, voice commands and performing an action in response is described. A method for annotating media content is described. A method for presenting additional content associated with media content identified based on a fingerprint is described. A method for identifying that an advertisement portion of media content is being played based on a fingerprint derived from the media content is described. A method of one media device recording particular media content automatically in response to another media device recording the particular media content is described. A method of concurrently playing media content on multiple devices is described. A method of publishing information associated with recording of media content is described. A method of deriving fingerprints by media devices that meet an idleness criteria is described. A method of loading, modifying, and displaying a high definition frame from a frame buffer is described.

Abstract: Techniques for topical customer service menu reconfiguration based on social media are claimed. In one embodiment, for example, an apparatus may comprise a social media gateway and an adjustment component. The social media gateway may be operative to receive social media information from one or more social media networks. The adjustment component may be operative to data mine the social media information to extract one or more characteristics, infer a trend from the extracted one or more characteristics, and adjust a customer service menu tree based upon the inferred trend. Other embodiments are described and claimed.

Abstract: A processing device local context is determined, and a communication of the processing device is filtered at least in part according to the local context.

Abstract: A voice recognition system includes: a voice input unit 11 for inputting a voice uttered a plurality of times; a registering voice data storage unit 12 for storing voice data uttered the plurality of times and input into the voice input unit 11; an utterance stability verification unit 13 for determining a similarity between the voice data uttered the plurality of times that are read from the registering voice data storage unit 12, and determining that registration of the voice data is acceptable when the similarity is greater than a threshold Tl; and a standard pattern creation unit 14 for creating a standard pattern by using the voice data where the utterance stability verification unit 13 determines that registration is acceptable.

Abstract: Provided are an apparatus and method for reporting speech recognition failures. The method includes detecting pure speech data from input speech data and outputting the detected pure speech data; checking at least one speech recognition failure for the pure speech data; and ascertaining speech recognition failure reasons from a check-result for the speech recognition failures and outputting the ascertained speech recognition failure reasons.

Abstract: A mass-scale, user-independent, device-independent, voice messaging system that converts unstructured voice messages into text for display on a screen is disclosed. The system comprises (i) computer implemented sub-systems and also (ii) a network connection to human operators providing transcription and quality control; the system being adapted to optimize the effectiveness of the human operators by further comprising 3 core sub-systems, namely (i) a pre-processing front end that determines an appropriate conversion strategy; (ii) one or more conversion resources; and (iii) a quality control sub-system.

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: In accordance with one embodiment, a method of generating language models for speech recognition includes identifying a plurality of utterances in training data corresponding to speech, generating a frequency count of each utterance in the plurality of utterances, generating a high-frequency plurality of utterances from the plurality of utterances having a frequency that exceeds a predetermined frequency threshold, generating a low-frequency plurality of utterances from the plurality of utterances having a frequency that is below the predetermined frequency threshold, generating a grammar-based language model using the high-frequency plurality of utterances as training data, and generating a statistical language model using the low-frequency plurality of utterances as training data.

Abstract: A system and method are provided for operating a call order center, comprising: obtaining voice training data for a call center service representative (CCSR) for phrases associated with an ordering process or products associated with the call order center; receiving customer call for an order by the CCSR on a telephone; activating a voice recognition system that accesses the CCSR voice training data via a switch; during a telephone call, issuing commands and providing data by the CCSR associated with the order to the voice recognition system that are translated and entered into an ordering system by the voice recognition system; and deactivating the voice recognition system via the switch. A role can be assigned to or deassigned from an employee based on their location relative to a particular location point within a work area.

Abstract: Instructions that are natively implementable by an application on an end user device are generated from interactive voice instructions that are not natively interpreted by the application. Generating natively implementable instructions in this manner allows for faster and cheaper deployment of voice, video, and/or data services by allowing legacy services based on interactive voice instructions to function seamlessly within an all data network.

Abstract: Systems and approaches are provided to enable multiple user devices to share data between devices. In one scenario, a user may click on or touch a telephone hyperlink from a browser of a desktop computer to initiate a telephone call from the user's mobile phone. In another situation, a user may begin various computing tasks from a tablet in the evening, share data associated relating to her work with a business computer, and complete her tasks the next day in the office with little to no minimal disruption to her work flow. In effect, the user may “cut” or “copy” data from a first personal computing device and paste that “data” onto a second computing device.

Abstract: A method and apparatus of processing a voice call are disclosed. One example method of operation may include recording at least a portion of a voice call, and storing the portion of the voice call in memory. The method may also include processing the portion of the voice call to identify at least one segment of interest, and forwarding the at least one segment of interest to a new call party responsive to a call transfer action.

Abstract: A method for setting a voice tag is provided, which comprises the following steps. First, counting a number of phone calls performed between a user and a contact person. If the number of phone calls exceeds a predetermined times or a voice dialing performed by the user is failed before calling to the contact person within a predetermined duration, the user is inquired whether or not to set a voice tag corresponding to the contact person after the phone call is complete. If the user decides to set the voice tag, a voice training procedure is executed for setting the voice tag corresponding to the contact person.

Abstract: An independent communication system (ICS) used in a transaction between a waiting party and a queuing party is adapted to connect to a particular node in an interactive voice response (IVR), wherein the queuing party has the IVR and the IVR has a plurality of nodes.

Abstract: Embodiments of the invention relate to effectively traversing the structure of an interactive voice response system. A menu associated with the system is organized and arranged in a hierarchy. Each received input is dynamically analyzed to enable a traversal of the hierarchy and to direct the input to an appropriate menu option associated with the system. The appropriate menu option is directly related to the input submission, and supports a direct communication with a telecommunication device that initiated communication with the system.

Abstract: Usage data associated with a user of a telephonic device is accessed by a remote learning engine. A service or a product is identified by the remote learning engine based on the accessed usage data. A recommended voice bundle application is determined by the remote learning engine. A recommendation associated with the recommended voice bundle application is transmitted to the telephonic device. The recommendation is presented to the user through voice communications. One or more input parameters associated with the recommended voice bundle application is collected by the telephonic device. The user through voice communications has accepted the recommendation determining is determined. In response to determining that the user has accepted the recommendation, the one or more input parameters to the recommended voice bundle application are loaded by the telephonic device, and the recommended voice bundle application is executed by the telephonic device.

Abstract: A mass-scale, user-independent, device-independent, voice messaging system that converts unstructured voice messages into text for display on a screen is disclosed. The system comprises (i) computer implemented sub-systems and also (ii) a network connection to human operators providing transcription and quality control; the system being adapted to optimise the effectiveness of the human operators by further comprising 3 core sub-systems, namely (i) a pre-processing front end that determines an appropriate conversion strategy; (ii) one or more conversion resources; and (iii) a quality control sub-system.

Abstract: Methods and systems for communicating with rate control. A communication is sent and received from a first device to a second device over a network, wherein the communication comprises at least one audio stream and a second communication stream. A capacity of the network is probed at the first device for the sending and receiving the communication. A presence of a voice in the at least one audio stream is detected at the first device via a voice activity detection of the at least one audio stream. A rate limit is set for the sending and receiving the communication at the first device based on the capacity of the network and the detection of the presence of the at least one audio stream.

Abstract: Automated response processing includes receiving a first audible prompt from a called system and a response to the first audible prompt from a calling system during a first phone call. Automated response processing further includes determining, using a processor, a semantic identifier for the first audible prompt using semantic analysis and storing the semantic identifier of the first audible prompt in association with the response. The stored response is played responsive to determining that a semantic identifier for a second audible prompt played to the calling system matches the semantic identifier of the first audible prompt.

Abstract: An embodiment provides a modular framework for managing multiple router applications in an interactive voice response (IVR) system. In an embodiment, a single table-driven framework approach is taken in which multiple IVR router applications, including menu/response type call routing applications and/or frequently asked question (FAQ)/response applications, may be managed in a more streamlined fashion. In an embodiment, a menu is presented to the caller. The menu is part of the router application which references information stored in a database, e.g., voice files and grammars, defined in a format, e.g., in table format. An embodiment analyzes the caller's responses against the menu's information to determine the appropriate actions to take and the appropriate data to retrieve. An embodiment also provides a centralized authentication process that may be used for all self-service router applications that require or somehow make use of authentication.

Abstract: A robocall is prevented from reaching a telephone subscriber, by an automated calling screening system that tests for presence of a human caller on the line, and disconnects calls absent a predetermined response indicating presence of a human caller.

Abstract: A system for detecting three-way calls in a monitored telephone conversation includes as speech recognition processor that transcribes the monitored telephone conversation and associates Characteristics of the monitored telephone conversation with a transcript thereof, a database to store the transcript and the characteristics associated therewith, and a three-way Call detection processor to analyze the characteristics of the conversation and to detect therefrom the addition of one or more parties to the conversation. The system preferably includes at least one domain-specific language model that the speech recognition processor utilizes to transcribe the conversation. The system may operate in real-time or on previously recorded conversations. A query and retrieval system may be used to retrieve and review call records from the database.

Abstract: This invention relates to a system and method for providing dedicated television advertisements based on speech recognition of telephone conversations. The home user makes telephone calls using a landline, cellular phone or VoIP phone. The user may also be watching TV. While doing so, the user is able to see advertisements on part or all of his TV screen, based on words and phrases he may have used during his telephone conversation(s). The system and method may be provided by a triple play or quad play service provider which associates its users' telephone calls with TV advertising. Once the user sees the advertisement he can get more information concerning the advertisement by clicking on it with a pointing device, e.g., a mouse or TV remote control, or by using any other navigation method the TV system provides, to see additional details concerning the advertisements.

Abstract: Systems and method are provided for rendering different speech-based services to a plurality of users. A service-providing system may be accessed via a plurality of connectivity ports. Each of the connectivity ports may be associated with at least one of a plurality of different speech-related services. The connectivity ports may be associated with the different speech-related services may be performed before receiving user service requests. The service-providing system may comprise a plurality of processing components, each of which may be configurable to provide one or more of a plurality of different speech-related services. The service-providing system may further comprise a connection component, which may be operable to establish a connection between the respective connectivity port and a processing component having a configuration of suitable for performing a service requested through the respective connectivity port.

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: A mass-scale, user-independent, device-independent, voice messaging system that converts unstructured voice messages into text for display on a screen is disclosed. The system comprises (i) computer implemented sub-systems and also (ii) a network connection to human operators providing transcription and quality control; the system being adapted to optimize the effectiveness of the human operators by further comprising 3 core sub-systems, namely (i) a pre-processing front end that determines an appropriate conversion strategy; (ii) one or more conversion resources; and (iii) a quality control sub-system.

Abstract: A communication system has a network-connected server comprising a processor and a coupled data repository and software executing on the processor from a non-transitory medium. The software provides a first function establishing a communication session between an initiator and an agent of an enterprise hosting the system, a second function gathering information about persons other than the initiator and the agent as potential conference participants, a third function generating and sending invitations to a conference to include the initiator and the agent to individual ones of the potential conference participants, and a fourth function connecting those accepting invitations to the conference.

Abstract: Information associated with messages and/or missed calls is provided to a subscriber. Calls received but not answered by the subscriber may be monitored. Each monitored call is classified as one of a missed call and a message. The monitored calls may be summarized based on a customizable rule set to create a summary. The summary is provided to the subscriber via, for example, a voice notification. Attorney Docket No.

Abstract: A method for responding to calls in an Interactive Voice Response system (IVR) of an organization, the method comprising receiving in an IVR a call from a customer of the organization, activating a response in the IVR based at least on former interactions with the organization, and wherein the IVR is a computerized system comprising at least one processor, and an apparatus for performing the same.

Abstract: An apparatus and method is disclosed for providing transparent enhanced telecommunications services to subscribers by implementing an enhanced services platform on a local network exchange within the public telephone network. More specifically, the apparatus and method of the present invention is capable of providing a plurality of enhanced telecommunications services to a subscriber by using a voice-activated interface to enable the subscriber to access at least one of the plurality of enhanced telecommunications services. In addition, the apparatus and method of the present invention may use a web-activated interface to enable the subscriber to access at least one of the plurality of enhanced telecommunications services.

Abstract: Disclosed herein are systems, methods, and computer-readable media to connecting to addresses received in spoken communications. The method for connecting to addresses received in spoken communications comprises receiving at least one spoken communication containing a spoken address, extracting each address automatically from the at least one spoken communication, displaying to a user at least one extracted address, and receiving from the user a selection of at least one extracted address to initiate communication.

Abstract: A communication converter is described for converting among speech signals and textual information, permitting communication between telephone users and textual instant communications users.

Abstract: A system, method and computer program product are provided for activating a cellular phone account utilizing automated speech recognition. In use, information about a user is received over a network utilizing automated speech recognition. Thereafter, a cellular phone account is activated based on the information received utilizing the automated speech recognition.

Abstract: The present invention uses natural language understanding to increase the ability of a customer service system to respond to a user's query in an automated manner. A customer service system receives a query from a user and offers the user the option of having the system contact the user at a later time with an answer. If the user accepts the offer, the customer service system processes the query offline, including providing the query to a natural language understanding interpreter. The system uses the natural language understanding interpretation to determine if the user's query is in a database of frequently-asked queries. For each query in the database of frequently-asked queries, there is a predetermined response protocol. If the user's query substantially matches a query in the database, the IVR system contacts the user with an automated response in accordance with the predetermined response protocol for the query.

Abstract: An earpiece (100) is provided. The earpiece can include an Ambient Sound Microphone (111) configured to capture ambient sound, an Ear Canal Microphone (123) configured to capture internal sound in the ear canal, a memory (208) configured to record at least a portion of the history of the ambient sound and the internal sound, and a processor (121) configured to save a recent portion of the history responsive to an event.

Abstract: Aspects of the invention provide a solution for detecting man-in-the-middle attacks in electronic transactions using prompts. One embodiment includes a method for authenticating an electronic transaction. The method includes: receiving an electronic transaction request from a user, determining an IP address associated with a client system from which the electronic transaction request originates, providing the user with a password associated with the electronic transaction request, receiving a telephonic communication from a telephonic device associated with the user, prompting the user, via a voice response unit, to input the password using the telephonic device, authenticating the user by comparing the inputted password and the provided password, determining a probable location of the user based on the determined IP address of the client system, communicating to the user the probable location of the user based on the determined IP address, and prompting the user to confirm the probable location of the user.

Abstract: The method of authorizing the transmission of a message comprises requesting the transmission of a message from a calling party to a called party and presenting a plurality of audiovisual media elements to the calling party, one of which is representative of a physical characteristic of the called party. The other audiovisual media elements are similar in form to the media element representative of the called party. The calling party selects one audiovisual media element from the presented media elements. The transmission of the message from the calling party to the called party is authorized only in the case where the selected audiovisual media element is representative of the called party.

Abstract: Systems and methods are provided for obtaining statistics from the use of a voice application. More particularly, the invention may comprise an interception engine that is configured to receive a document from an IVR application server and inject a marker(s) into the document, and pass the document on to an IVR browser. The interception engine is further configured to receive a response document from the IVR browser, remove the marker results, and pass the document on to the IVR application server. The marker results are used to create statistical information useful in the analysis of the operation of the voice application in the IVR system. In an exemplary embodiment, the markers are used in connection with a map of the call flow of the voice application.