In one embodiment, the techniques herein are directed to receiving a reason for a call from a user device. For instance, an illustrative method herein may comprise: receiving, by a particular device, an indication from an intermediate service that a user device requested that the particular device participate in a call with a user of the user device, the indication also including a reason for the call; determining, by the particular device, when the particular device is able to initiate the call; and initiating, by the particular device and in response to being able to initiate the call, the call to the user device, wherein the particular device is aware of the user and the reason for the call prior to initiating the call.

A method, system, and computer program product for managing communication privacy in a conversation system are provided. The method detects an utterance on a public channel by a user of a computing device. A privacy nature of the utterance is determined. Based on the privacy nature, a classification confidence is determined for the utterance. The method generates a privacy question to be presented to the user based on the privacy nature and the classification confidence. In response to a confirmation response, a privacy channel is established. The method switches from the public channel to the privacy channel.

Systems and methods for managing data transfers between a secure location and a less secure location. A data transfer checker operating on a mobile device determines whether an attempted data transfer between two locations is permitted. If it is not permitted, then the data transfer is prevented and the user may be notified of the data transfer prevention.

A system, method and non-transitory computer readable medium for generating a voiceprint for a call participant are disclosed, wherein an audio recording or communication session is received, the quality of the audio recording is analyzed, and if determined to be of sufficient quality, the audio recording is separated into speech for each call participant, which may be further analyzed to generate a voiceprint for each participant. The voiceprint that is generated may be used to identify the participant in other historical recordings or in an active communications session, and upon such an identification, one or more compliance or data protection policies may be applied.

Systems and methods for utilizing a mnemonic to communicate sensitive data to an agent are disclosed. In aspects, a computer-implemented method comprises: establishing a telephone connection between a caller and an agent; entering an encryption key received from the agent into a mnemonic application of the computer device to permute an algorithm of the mnemonic application; receiving sensitive data in the form of one or more alphabetic, numeric or alpha-numeric sequence; initiating the mnemonic application to generate a mnemonic of the sensitive data using the encryption key, wherein the mnemonic is a sequence of words representing the sensitive data; displaying the mnemonic to the caller; and conveying audio communication of the mnemonic to the agent through the telephone connection to enable remote decoding of the mnemonic back into the at least one sensitive number sequence.

A system, method and non-transitory computer readable medium for generating a voiceprint for a call participant are disclosed, wherein an audio recording or communication session is received, the quality of the audio recording is analyzed, and if determined to be of sufficient quality, the audio recording is separated into speech for each call participant, which may be further analyzed to generate a voiceprint for each participant. The voiceprint that is generated may be used to identify the participant in other historical recordings or in an active communications session, and upon such an identification, one or more compliance or data protection policies may be applied.

Apparatus for the transfer of sensitive information between two parties facilitated by an intermediary, the apparatus adapted to: receive from the first party voice signals and data signals; determine a parameter relating to an estimate of the time required for sensitive information to be determined from the data signals received from the first party; transmit to the intermediary the received voice signals and the parameter; determine sensitive information from the received data signals; and transmit the sensitive information to the second party. A corresponding method is also provided.

Systems and methods for utilizing a mnemonic to communicate sensitive data to an agent are disclosed. In aspects, a computer-implemented method comprises: establishing a telephone connection between a caller and an agent; entering an encryption key received from the agent into a mnemonic application of the computer device to permute an algorithm of the mnemonic application; receiving sensitive data in the form of one or more alphabetic, numeric or alpha-numeric sequence; initiating the mnemonic application to generate a mnemonic of the sensitive data using the encryption key, wherein the mnemonic is a sequence of words representing the sensitive data; displaying the mnemonic to the caller; and conveying audio communication of the mnemonic to the agent through the telephone connection to enable remote decoding of the mnemonic back into the at least one sensitive number sequence.

Provided are techniques for sharing confidential information with privacy using a mobile phone. A voice preference and language preferences are received for an information provider profile of an information provider, where the language preferences include a first language for typing text and a second language for speaking the text. During an on-going live phone call between the information provider and an information requester, selection of a text to talk feature is received. Text is received in the first language, where the text includes confidential information. The text is converted from the first language to text in the second language. The text in the second language is converted to a voice message that is spoken in a voice identified by the voice preference through the on-going live phone call to provide the confidential information with privacy. Then, control is returned to the on-going live phone call.

System and method for a secure interactive voice response (IVR) includes: receiving a communication from a first party regarding a transaction, over a communication network; connecting the second party with the communication to service the communication; creating an anonymous order entry for the transaction; detecting sensitive information in the communication; isolating the sensitive information in the communication from the second party; route the communication to a secure system for processing of the sensitive information; and reconnecting the communication to complete the transaction.