Methods and systems are disclosed for detecting threats in voice communications such as telephone calls. Various voice phishing (vishing) detectors detect respective type of threats and can be used or activated individually or in various combinations. A tampering detector utilizes deep scattering spectra and shifted delta cepstra features to detect tampering in the form of voice conversion, speech synthesis, or splicing. A content detector predicts a likelihood that word patterns on an incoming voice signal are indicative of a vishing threat. A spoofing detector authenticates or repudiates a purported speaker based on comparison of voice profiles. The vishing detectors can be provided as an authentication service or embedded in communication equipment. Machine learning and signal processing aspects are disclosed, along with applications to mobile telephony and call centers.

An apparatus including an interface and a processor. The interface may be configured to receive video frames corresponding to an interior of a vehicle. The processor may be configured to perform video operations on the video frames to detect objects in the video frames, detect one or more passengers based on the objects detected in the video frames, determine a location of each of the passengers detected, determine which of the passengers may be an audio source and generate a control signal in response to the audio source. The control signal may be configured to adjust an input of a microphone towards the audio source. The video operations may be used to determine the location and the audio source.

The exemplary embodiments disclose a system and method, a computer program product, and a computer system for determining the context of calls and providing a user interface to a user. The exemplary embodiments may include collecting data from the call, extracting one or more features from the collected data, determining a context of the call based on applying one or more models to the extracted one or more features, and providing a user with a user interface.

A system includes one or more memory devices storing instructions, and one or more processors configured to execute the instructions to perform steps of a method for detecting harassment. The system may receive communication data from a first customer service representative terminal or a customer communication device and may determine, based at least in part on the communication data and stored communication data, that the communication data comprises harassing content. The system may, responsive to determining that the communication data comprises harassing content, transmit to a second customer service representative terminal, a notification indicating that the communication data comprises harassing content.

Provided are a call deflection and response system and method, wherein a voice call from a caller device is received, a skill group is determined to resolve an issue associated with the call, and a text response to the issue is sent to the caller device, providing a context-based personalized response. A caller leaves a detailed voicemail explaining an issue needing resolution, which is electronically transcribed and then run through a classifier to determine concepts and intents associated with the call. Based on the concepts and intents, responsibility for the call and associated files are transferred to a particular skill group on a chat platform for resolution. A chat entity from the appropriate skill group determines and provides an issue response via text message to the caller device, e.g., to the caller's mobile phone.

An information processing device includes an image acquirer that acquires a captured image captured by an imager, an utterer identifier that identifies an utterer, a display target identifier that identifies a display target corresponding to the utterer identified by the utterer identifier from the captured image acquired by the image acquirer, and a display processor that displays display information corresponding to the display target identified by the display target identifier, on a first display.

A fraud analysis computing system is provided. The system includes a network interface configured to communicate data over a network and a processing circuit including one or more processors coupled to non-transitory memory. The processing circuit is configured to monitor incoming call data generated during an incoming call between a user and an incoming caller, detect a fraud trigger within the incoming call data, and complete a fraud interception activity in response to detection of the fraud trigger.

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.

A cloud-based communication system for monitoring a collaboration session. Based on the monitoring, the system identifies a collaboration event that indicates desirability of a break or that a digression from a session topic has or is occurring. When a collaboration event is identified, a prompt is communicated to the facilitator of the collaboration session. The collaboration event may be defined in a variety of ways such as participant fatigue, participant distraction, or the like. The system provides the facilitator with actions to be initiated by the system (automatically or in response to facilitator/user input) to respond to an identified communication event. The actions include initiating a break, acting to avoid or reduce session digressions, and creating a highlight reel of the collaboration session, including a number of unique features enabling more efficient retrieval and/or review of data. A distracted or fatigued participant can be directed to access the highlight reel.

An apparatus including an interface and a processor. The interface may be configured to receive video frames corresponding to an interior of a vehicle. The processor may be configured to perform video operations on the video frames to detect objects in the video frames, detect one or more passengers based on the objects detected in the video frames, determine a location of each of the passengers detected, determine which of the passengers may be an audio source and generate a control signal in response to the audio source. The control signal may be configured to adjust an input of a microphone towards the audio source. The video operations may be used to determine the location and the audio source.