Abstract: Provided is a method and a telephone-based system with voice-verification capabilities that enable a user to safely and securely conduct transactions with his or her online financial transaction program account over the phone in a convenient and user-friendly fashion, without having to depend on an internet connection.

Abstract: A method and an apparatus for training a voiceprint recognition system are provided. The method includes obtaining a voice training data set comprising voice segments of users; determining identity vectors of all the voice segments; identifying identity vectors of voice segments of a same user in the determined identity vectors; placing the recognized identity vectors of the same user in the users into one of user categories; and determining an identity vector in the user category as a first identity vector. The method further includes normalizing the first identity vector by using a normalization matrix, a first value being a sum of similarity degrees between the first identity vector in the corresponding category and other identity vectors in the corresponding category; training the normalization matrix, and outputting a training value of the normalization matrix when the normalization matrix maximizes a sum of first values of all the user categories.

Abstract: Techniques (300, 400, 500) and apparatuses (100, 200, 700) for recognizing accented speech are described. In some embodiments, an accent module recognizes accented speech using an accent library based on device data, uses different speech recognition correction levels based on an application field into which recognized words are set to be provided, or updates an accent library based on corrections made to incorrectly recognized speech.

Abstract: Methods and systems are provided for optimizing call quality and improving network efficiency by reducing bandwidth requirements at the individual-voice-call level. Embodiments provided herein build vocal fingerprints that correspond to the frequency range of the human voice, as well as the frequency range of the voice of individual users. The vocal fingerprints are used minimize and reduce the transmission of background noise and ambient sound captured using HD voice while retaining the frequency range of a user's voice in HD voice. This filtered HD voice frequency range is then transmitted to recipients over the network. The reduced frequency range lowers bandwidth usage and conserves network resources, all while optimizing the call quality for individual users.

Abstract: A method and an apparatus for processing voice data. A specific implementation of the method includes: receiving voice data sent by a user terminal; extracting a voiceprint characteristic vector in the voice data; matching the voiceprint characteristic vector with a registered voiceprint vector prestored by the user, and generating a matching degree between the voiceprint characteristic vector and the registered voiceprint vector; determining whether the matching degree is greater than or equal to a preset update threshold; and updating the registered voiceprint vector by using the voiceprint characteristic vector and the voice data in response to determining that the matching degree is greater than or equal to the preset update threshold. This implementation enhances accuracy of a registered voiceprint vector of a user.

Abstract: A system is provided for interpreting real-time voice communications and generating action plan queues to assist a sales representative during a call. The system includes an analytics module configured to identify voice call data between the sales representative and the other party and select voice impressions in the call for analysis. The analytics module further receives the voice impressions and interpret the impressions, associates at least one attribute and at least one value with each voice impression, and creates a conversation profile based on the at least one attribute and the at least one value associated with the voice impressions. The analytics module further determines action plan queues according to the conversation profile and render the action plan queues to the sales representative during the call.

Abstract: The present disclosure discloses a method and apparatus for verifying information. The method includes: acquiring a target combination of question and answer, the target combination of question and answer comprising a question and an answer to the question; sending the question in the target combination of question and answer to a terminal device; receiving to-be-confirmed voice information sent by the terminal device, and recognizing the to-be-confirmed voice information to generate a to-be-confirmed answer; and determining that the to-be-confirmed voice information is verified, if the to-be-confirmed answer matches the answer in the target combination of question and answer.

Abstract: Methods, systems, and computer-readable media for device monitoring for conference reservation cancellation are disclosed. A location value is associated with a reservation for a scheduled conference associated with a scheduled starting time and a scheduled ending time. A voice-capturing device is associated with the location value, and the voice-capturing device is configured to send voice input to a service provider environment over a network. Voice input is not received from the voice-capturing device within a duration of time between the scheduled starting time and the scheduled ending time. The reservation is canceled based on determining that the voice input is not received from the voice-capturing device within the duration of time between the scheduled starting time and the scheduled ending time.

Abstract: A system and method for generating a range image using sparse depth data is disclosed. The method includes receiving, by a controller, image data of a scene. The image data includes a first set of pixels. The method also includes receiving, by the controller, a sparse depth data of the scene. The sparse depth data includes a second set of pixels, and the number of the second set of pixels is less than the number of first set of pixels. The method also includes combining the image data and the sparse depth data into a combined data. The method also includes generating a range image using the combined data.

Abstract: A service monitoring system includes a voice collector that collects a voice of an employee in a predetermined voice collection region, a storage unit that stores service event data including determination conditions for each predetermined service event, terminal operation history data indicating an operation history of an employee on a predetermined business terminal and voice data of the employee in correlation with each other, a detector that detects the service event of the employee based on the service event data and the terminal operation history data, a calculator that calculates a service speech evaluation value corresponding to a predetermined speech keyword on the basis of the voice data of the employee during the service event, and an output that stores the service speech evaluation value in correlation with identification information of the employee, and voice data of the employee specified by a service position and time point of the employee.

Abstract: An identity authentication method, comprising: at an electronic device having one or more processors and memory, the electronic device coupled with a display and one or more input devices: receiving an identity authentication request; in response to receiving the identity authentication request, performing an interactive authentication information exchange between the electronic device and a user, including: displaying, on the display, first visual information in a first manner; displaying, on the display, the first visual information in a second manner that is distinct from the first manner, wherein the first visual information displayed in the second manner includes a timing characteristic that is absent from the first visual information displayed in the first manner; receiving user input entered in accordance with the first visual information displayed in the second manner; and verifying that the user input conforms to the timing characteristic in the first visual information displayed in the second manner

Abstract: The present disclosure provides a method and a device for processing voiceprint authentication. The method includes: extracting a first feature vector for each first speech segment of a training set by a gender-mixed voiceprint baseline system based on Deep Neural Network; training a gender classifier according to the first feature vector for each first speech segment and a pre-labeled first gender label of each first speech segment; training Deep Neural Network models for different genders respectively according to speech data of different genders of the training set; and training uniform background models, feature vector extracting models and linear probability discriminant analysis models for different genders respectively according to the Deep Neural Network models for different genders and the speech data of different genders of the training set. A voiceprint authentication processing model for gender distinguishing is built, thus improving the efficiency and accuracy of voiceprint authentication.

Abstract: A score indicating a likelihood that a first subject is the same as a second subject may be calibrated to compensate for aging of the first subject between samples of age-sensitive biometric characteristics. Age of the first subject obtained at a first sample time and age of the second subject obtained at a second sample time may be averaged, and an age approximation may be generated based on at least the age average and an interval between the first and second samples. The age approximation, the interval between the first and second sample times, and an obtained gender of the subject are used to calibrate the likelihood score.

Abstract: Updating a voice template for recognizing a speaker on the basis of a voice uttered by the speaker is disclosed. Stored voice templates indicate distinctive characteristics of utterances from speakers. Distinctive characteristics are extracted for a specific speaker based on a voice message utterance received from that speaker. The distinctive characteristics are compared to the characteristics indicated by the stored voice templates to selected a template that matches within a predetermined threshold. The selected template is updated on the basis of the extracted characteristics.

Abstract: Techniques are disclosed for responding to a pre-recorded inbound voice message in a communication system that includes communication devices and a communication server. In a first communication device, a pre-recorded inbound voice message is received from a sender communication device via a communication server. A reply mode is set for a response voice message from a plurality of reply modes. The response voice message is recorded and a reply mode flag is inserted into a message header. The response voice message is then sent to the communication server where it determines the reply mode. When the reply mode is reply to all, the response voice message is sent to the sender communication device and other recipient communication devices. When the reply mode is reply to sender, a direct channel communication link is established between the first communication device and the sender communication device and the response voice message is sent directly to the sender communication device.

Abstract: Disclosed are techniques for capturing and classification of digital data and providing recommendations in real-time or nearly real-time. These techniques identify a plurality of agent computing or communication devices in communication with a server and identify a plurality of communications between the plurality of agent computing or communication devices and a plurality of user communication or computing devices of a plurality of users into real-time service data. One or more actions are determined for a communication of the plurality of communications based in part or in whole upon at least one communication class into which the communication is classified. One or more post-classification tasks are performed based in part or in whole upon the one or more actions determined at the recommendation module.

Abstract: Techniques are disclosed for managing outbound voice messages in a communication system that includes communication devices and a communication server. A temporal mode of either live mode or message mode and a recipient mode of either group mode or direct mode are selected and set for an outbound voice message. Based on the selected settings for temporal mode and recipient mode the originating communication device records a voice message that is relayed to the communication server where it is distributed to other communication devices according to the rules or parameters associated with the temporal and recipient mode selected.

Abstract: An approach includes contacting a predefined contact information when a mobile device, which is password protected, is lost and subsequently found. The approach includes receiving an activation event predefined for a specified password protected mobile device, and receiving predefined contact information stored in the mobile device while the mobile device remains password protected, upon the receipt of the activation event.

Abstract: A system and method for facilitating user interaction with a voice application. A VoiceXML browser runs locally on a mobile device. Supporting components, such as a Resource Manager, a Call Data Manager, and a MRCP Gateway Client support operation of the VoiceXML browser. The Resource Manager servers either those files stored locally on the mobile device, or files accessible via a network connection using the wireless or mobile broadband capabilities of the mobile device. The Call Data Manager communicates call-specific data back to the application's system of origin or another configured target system. The MRCP Gateway Client provides the VoiceXML browser with access to media resources via a MRCP Gateway Client.

Abstract: Apparatuses, methods and storage media associated with multiple multi-drop buses in a switch are provided herein. In some embodiments, the switch may include a multi-drop row bus to transmit a plurality of frames in a row dimension of the matrix switch and a multi-drop column bus to transmit the plurality of frames in a column dimension of the matrix switch. The switch may further include an input port to receive the plurality of frames and an output port to output the plurality of frames from the matrix switch. Other embodiments may be described and/or claimed.

Abstract: Methods, apparatuses, and techniques for security and/or automation systems are described. In one embodiment, the method may include receiving a call initiation instruction at a video monitoring component of a home automation system. The method may further include analyzing the call initiation instruction, and communicating a call request from the video monitoring component of the home automation system to a first remote user based at least in part on the received call initiation instruction.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving audio data corresponding to an utterance, determining that the audio data corresponds to a hotword, generating a hotword audio fingerprint of the audio data that is determined to correspond to the hotword, comparing the hotword audio fingerprint to one or more stored audio fingerprints of audio data that was previously determined to correspond to the hotword, detecting whether the hotword audio fingerprint matches a stored audio fingerprint of audio data that was previously determined to correspond to the hotword based on whether the comparison indicates a similarity between the hotword audio fingerprint and one of the one or more stored audio fingerprints that satisfies a predetermined threshold, and in response to detecting that the hotword audio fingerprint matches a stored audio fingerprint, disabling access to a computing device into which the utterance was spoken.

Abstract: A secure telephone call management system is provided for authenticating users of a telephone system in an institutional facility. Authentication of the users of the telephone call management system is accomplished by using a personal identification number, biometric means, and/or radio frequency means. The secure telephone call management system includes accounting software capable of limiting access to the system based on funds in a user's account, and includes management software capable of implementing widespread or local changes to the system. The system monitors a conversation in the telephone call to detect a presence of a first characteristic in audio of the conversation, and terminates the telephone call if the first characteristic does not match a second characteristic of biometric information of a user or a called party.

Abstract: Method of filtering undesirable incoming telephone calls, in which a decision to block a call or to transmit it is based both on the caller's number and on analysis of the caller's voice.

Abstract: A residential gateway has a first, wired data connection and a second, wireless data connection. At least the second data connection connects to a network node which at least temporarily maintains simultaneous connections to at least one residential gateway and at least one mobile station. The residential gateway is communicatively connected to a load balancing controller. A method of operating the residential gateway for controlling load balancing comprises the residential gateway sending a registration request to the load balancing controller. The registration request comprises an identification of the residential gateway and an identification of the network node to which the residential gateway is communicatively connected. The residential gateway receives a listening address from which it receives load balancing control messages, and listens for load balancing control messages from the listening address.

Abstract: A method and an apparatus for processing voice data. A specific implementation of the method includes: receiving voice data sent by a user terminal; extracting a voiceprint characteristic vector in the voice data; matching the voiceprint characteristic vector with a registered voiceprint vector prestored by the user, and generating a matching degree between the voiceprint characteristic vector and the registered voiceprint vector; determining whether the matching degree is greater than or equal to a preset update threshold; and updating the registered voiceprint vector by using the voiceprint characteristic vector and the voice data in response to determining that the matching degree is greater than or equal to the preset update threshold. This implementation enhances accuracy of a registered voiceprint vector of a user.

Abstract: The disclosure discloses a user biological feature authentication method and system. The method includes the following: a client sends an authentication request to a server; the client receives a speech password; acquires speech information and a face image of a user to be authenticated; the client judges whether the speech information is the same as the speech password, and judges whether the face image is valid; the client associates a speech information fragment to the face image under the condition that a judgment result is YES; the client calculates a digest value of the speech password, the speech information, a target image, associated information and a first moment; and the client sends an authentication content to the server. By the disclosure, the effect of improving ID authentication security in a biological feature recognition process is further achieved.

Abstract: Approaches for recording and playing back a portion of a telephone call are provided. An approach includes establishing a subscriber of a recording and play back service. The approach includes recording, by a computing device, a portion of a conversation of the subscriber that occurs in a call between a first telephone and a second telephone. The approach additionally includes storing, by the computing device, the portion of the conversation when the call ends. The approach further includes analyzing, by the computing device, the stored portion of the conversation to detect predefined keywords. The approach also includes automatically providing the subscriber with an option to play back the stored portion of the conversation when at least one of the predefined keywords is detected during the analyzing.

Abstract: Embodiments are provided for the automatic real-time recording and processing of media in a communications network based on the context of the media. In one embodiment, a media stream is received in an analysis module in a service platform in the communications network. The media stream may represent a communication session between a calling party and a call center in the network. The incoming media steam is analyzed to identify words comprising a context of the communication session. A determination is then made as to whether the context of the communication session is related to a set of business rules associated with the service platform which may automatically trigger the retention of a recording of the communication session. If the context of the communication session is related to the set of business rules, the retention of the communication session is automatically triggered in real-time at a recording module.

Abstract: Analog signals are received from a sound transducer. The analog signals are converted into digitized data. A determination is made as to whether voice activity exists within the digitized signal. Upon the detection of voice activity, an indication of voice activity is sent to a processing device. The indication is sent across a standard interface, and the standard interface is configured to be compatible to be coupled with a plurality of devices from potentially different manufacturers.

Abstract: A user seeking information relevant to the purchase of a home improvement product or other product submits a query to an automated system. The system transforms the user's voice query into a text statement and searches a knowledge base for candidate responses. Quality scores for the candidate responses are determined. If no candidate response having at least a minimum quality score is identified, the query is sent to a second device associated with an agent. The agent response is provided to the user and stored in the knowledge base for future use.

Abstract: Click logs are automatically mined to assist in discovering candidate variations for named entities. The named entities may be obtained from one or more sources and include an initial list of named entities. A search may be performed within one or more search engines to determine common phrases that are used to identify the named entity in addition to the named entity initially included in the named entity list. Click logs associated with results of past searches are automatically mined to discover what phrases determined from the searches are candidate variations for the named entity. The candidate variations are scored to assist in determining the variations to include within an understanding model. The variations may also be used when delivering responses and displayed output in the SLU system. For example, instead of using the listed named entity, a popular and/or shortened name may be used by the system.

Abstract: The speaker identification system has a voice acquisition unit that acquires voice information of a speaker, and a database management unit that determines whether or not the speaker corresponding to the acquired voice information matches a speaker corresponding to registered voice information in connection with content information on a content, that acquires content information on the content displayed on a device at the time of acquisition of the voice information and stores the acquired content information in connection with the registered voice information in a case where it is determined that the speaker corresponding to the acquired voice information matches the speaker corresponding to the registered voice information, and that stores the acquired voice information in the database as registered voice information in a case where it is determined that the speaker corresponding to the acquired voice information does not match the speaker corresponding to the registered voice information.

Abstract: A method and system for using conversational biometrics and speaker identification and/or verification to filter voice streams during mixed mode communication. The method includes receiving an audio stream of a communication between participants. Additionally, the method includes filtering the audio stream of the communication into separate audio streams, one for each of the participants. Each of the separate audio streams contains portions of the communication attributable to a respective participant. Furthermore, the method includes outputting the separate audio streams to a storage system.

Abstract: Systems and methods for analyzing digital recordings of the human voice in order to find characteristics unique to an individual. A biometrics engine may use an analytics service in a contact center to supply audio streams based on configured rules and providers for biometric detection. The analytics service may provide call audio data and attributes to connected engines based on a provider-set of selection rules. The connected providers send call audio data and attributes through the analytics service. The engines are notified when a new call is available for processing and can then retrieve chunks of audio data and call attributes by polling an analytics service interface. A mathematical model of the human vocal tract in the call audio data is created and/or matched against existing models. The result is analogous to a fingerprint, i.e., a pattern unique to an individual to within some level of probability.

Abstract: A third-party profile service based on a proxy server model is described, where a user's profile service resides at a URL, in contrast to a profile service that requires federation identity. A profile service is provided that augments location-based services offered by service providers targeting mobile users via, for example, wireless and Wifi Networks. Additional personalization is driven by identity/profile services. Participants in the scenario are not required to share an identity or profile (i.e., static federation is not required). The user establishes a single profile with a trusted provider, hands-off solicitations to a profile agent that operates on behalf of the user to apply policies and preferences. The agent also provides privacy and anonymity (opaqueness).

Abstract: In one example, documents that are examined by a search process may be scored in a manner that is specific to a domain. A domain may be a substantive area, such as medicine, sports, etc. Different scoring approaches that take aspects of the domain into account may be applied to the documents, thereby producing different scores than might have been produced by a simple comparison of the terms in the query with the terms in the documents. These domain-based approaches may take a query into account in scoring the documents, or may be query-independent. Each approach may be implemented by a scorer. The combined output of the scorers may be used to generate a score for each document. Documents then may be ranked based on the scores, and search results may be provided.

Abstract: In one aspect, the present invention facilitates the investigation of networks of criminals, by gathering associations between phone numbers, the names of persons reached at those phone numbers, and voice print data. In another aspect the invention automatically detects phone calls from a prison where the voiceprint of the person called matches the voiceprint of a past inmate. In another aspect the invention detects identity scams in prisons, by monitoring for known voice characteristics of likely imposters on phone calls made by prisoners. In another aspect, the invention automatically does speech-to-text conversion of phone numbers spoken within a predetermined time of detecting data indicative of a three-way call event while monitoring a phone call from a prison inmate. In another aspect, the invention automatically thwarts attempts of prison inmates to use re-dialing services.

Abstract: A method for speaker verification is disclosed. The method comprises using at least one hardware processor for: providing a development set comprising multiple voice samples of multiple speakers uttering a predefined development text, prompting a test text to a target speaker, wherein the test text is different from the development text, and recording a test sample of the target speaker uttering the test text, synthesizing a set of artificial voice samples based on the multiple voice samples, wherein each of the artificial voice samples simulates a different speaker of the multiple speakers uttering the test text, and verifying an identity of the target speaker based on the set of artificial voice samples and on the test sample of the target speaker.

Abstract: Techniques (300, 400, 500) and apparatuses (100, 200, 700) for recognizing accented speech are described. In some embodiments, an accent module recognizes accented speech using an accent library based on device data, uses different speech recognition correction levels based on an application field into which recognized words are set to be provided, or updates an accent library based on corrections made to incorrectly recognized speech.

Abstract: Methods, systems, computer-readable media, and apparatuses for utilizing voice biometrics to prevent unauthorized access are presented. In some embodiments, a computing device may receive a voice sample. Subsequently, the computing device may determine a voice biometric confidence score based on the voice sample. The computing device then may evaluate the voice biometric confidence score in combination with one or more other factors to identify an attempt to access an account without authorization.

Abstract: A third party verification system, method, and computer readable medium comprising a response unit in communication with at least a first party, said response unit configured to automatically elicit information in the form of a dual tone multi-frequency (DTMF) response from the at least first party providing evidence of consent granted by the at least first party to enter into at least one transaction with at least a second party, and a print server in communication with said response unit, said print server configured to receive and store said information to provide a record for third party verification that the at least first party consented to enter into the at least one transaction with the at least one second party.

Abstract: An interactive presentation environment for eMeetings or the like that provides participants with more control over what they see and hear. The interactive presentation environment may comprise a meeting recorder adapted to create a recording of a live meeting and a navigation control for selecting a portion of the recording to view during the live meeting. The interactive presentation environment may further comprise a timeline control containing a first graphical indicator associated with a live position and a second graphical indicator associated with a current position, a bookmark control adapted to mark a portion of the recording for archiving, and a display operatively connected to the meeting recorder and the navigation control.

Abstract: Systems and methods are provided for scoring non-native, spontaneous speech. A spontaneous speech sample is received, where the sample is of spontaneous speech spoken by a non-native speaker. Automatic speech recognition is performed on the sample using an automatic speech recognition system to generate a transcript of the sample, where a speech recognizer metric is determined by the automatic speech recognition system. A word accuracy rate estimate is determined for the transcript of the sample generated by the automatic speech recognition system based on the speech recognizer metric. The spontaneous speech sample is scored using a preferred scoring model when the word accuracy rate estimate satisfies a threshold, and the spontaneous speech sample is scored using an alternate scoring model when the word accuracy rate estimate fails to satisfy the threshold.

Abstract: Approaches for recording and playing back a portion of a telephone call are provided. An approach includes establishing a subscriber of a recording and play back service. The approach includes recording, by a computing device, a portion of a conversation of the subscriber that occurs in a call between a first telephone and a second telephone. The approach additionally includes storing, by the computing device, the portion of the conversation when the call ends. The approach further includes analyzing, by the computing device, the stored portion of the conversation to detect predefined keywords. The approach also includes automatically providing the subscriber with an option to play back the stored portion of the conversation when at least one of the predefined keywords is detected during the analyzing.

Abstract: The invention refers to a method of generating a means and/or status which is temporarily limited and/or usage limited and allows access to a service which has access restrictions, the method being carried out in a computing system and comprising the steps of establishing a telecommunications connection such that an audio call as for example a telephone call, within the telecommunications connection is preferably initiated by a person; determining biometric data of a specific person such as for example voice information; receiving data such as a voice utterance from the person which is connected by the telecommunications connection; verifying that the received data and the determined biometric data fit; and generating the means and/or status which is temporarily limited and/or usage limited after the verifying step.

Abstract: Methods, systems, computer-readable media, and apparatuses for handling calls based on a voice biometric confidence score are presented. In some embodiments, a computing device may receive a voice sample associated with a telephone call. Subsequently, the computing device may determine a voice biometric confidence score based on the voice sample. The computing device then may determine to route the telephone call to a certain endpoint based on the voice biometric confidence score.

Abstract: Embodiments of techniques or systems for fraud detection are provided herein. A communication may be received where the communication includes one or more voice signals from an individual. Frequency responses associated with these voice signals may be determined and analyzed and utilized to determine whether or not potential fraudulent activity is occurring. For example, if a frequency response is greater than a frequency threshold, potential fraudulent activity may be determined. Further, frequency responses may be cross referenced with voice biometrics, voice printing, or fraud pathway detection results. In this way, voice stress or frequency responses may be utilized to build other databases related to other types of fraud detection, thereby enhancing one or more aspects of fraud detection. For example, a database may include a voice library, a pathway library, or a frequency library which include characteristics associated with fraudulent activity, thereby facilitating identification of such activity.

Abstract: A telecommunications system for use in a secure facility such as a jail, prison or the like. The systems, devices and methods disclosed provide telecommunications, email, other messaging, financial services, vending, and commissary or canteen services for inmates of a secure facility with respect to family, friends and others. The system includes a phone server adapted to be communicatively connected to an external service provider; a monitoring station communicatively connected to the phone server; an account manager server communicatively connected to the phone server, and at least one telecommunications device disposed at the secure facility for use by the inmate and which is communicatively connected to the phone server. A method of telecommunicating, including receiving incomming calls at the secure facility, via the system is also disclosed.

Abstract: Features are disclosed for automatically identifying a speaker. Artifacts of automatic speech recognition (“ASR”) and/or other automatically determined information may be processed against individual user profiles or models. Scores may be determined reflecting the likelihood that individual users made an utterance. The scores can be based on, e.g., individual components of Gaussian mixture models (“GMMs”) that score best for frames of audio data of an utterance. A user associated with the highest likelihood score for a particular utterance can be identified as the speaker of the utterance. Information regarding the identified user can be provided to components of a spoken language processing system, separate applications, etc.