A device configured to obtain at least a portion of a phone call and to identify a voice signal associated with a person on the phone call. The device is further configured to generate metadata for the phone call and a transcript for the phone call. The device is further configured to input the transcript and the metadata into a machine learning model and to receive a call profile from the machine learning model. The call profile includes a first call classification for the phone call. The device is further configured to identify a call log associated with the phone call that includes a second call classification for the phone call. The device is further configured to determine that the first call classification does not match the second call classification, to generate a feedback report that identifies the first call classification, and to output the feedback report.

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.

Methods to reduce agent effort and improve customer experience quality through artificial intelligence. The Agent Assist tool provides contact centers with an innovative tool designed to reduce agent effort, improve quality and reduce costs by minimizing search and data entry tasks The Agent Assist tool is natively built and fully unified within the agent interface while keeping all data internally protected from third-party sharing.

A method of verifying a user identity using a Web-based multimodal interface can include sending, to a remote computing device, a multimodal markup language document that, when rendered by the remote computing device, queries a user for a user identifier and causes audio of the user's voice to be sent to a multimodal, Web-based application. The user identifier and the audio can be received at about a same time from the client device. The audio can be compared with a voice print associated with the user identifier. The user at the remote computing device can be selectively granted access to the system according to a result obtained from the comparing step.

For validating information provided in a conversation, apparatus, methods, and program products are disclosed. The apparatus includes an association module that associates a plurality of items of caller identification data with a caller, an information module that identifies, using a speech recognition application, caller information from speech of the caller during a telephonic conversation with a call recipient, a comparison module that compares the plurality of items of caller identification data with the caller information, and a validation module that calculates a confidence score based on the comparison of the plurality of items of caller identification data with the caller information and presents, to the call recipient, the confidence score.

Controlled-environment communication systems are increasingly using voice over internet protocol (VoIP) to serve their users. VoIP allows voice to be sent in packetized form, where audio is encoded using one of several codecs. Because of bandwidth constraints, particularly during peak call times, codecs may be used which sacrifice audio quality for bandwidth efficiency. As a result, several features of communication systems, including critical security features. The present disclosure provides details for systems and methods by which a controlled-environment communication system may shift between codecs to perform security-related features or to alleviate bandwidth considerations. This involves the special formatting of control-signaling messages, including session initiation protocol (SIP) and session description protocol (SDP) messaging.

A system is described herein that facilitates the monitoring of inmate communications. The system provides a remotely-accessible means for a reviewer to monitor a call between an inmate and another person. The system includes a monitoring server and a monitoring station. The monitoring server is configured to receive a call and call information from a communication center and process the call for monitoring, schedule a review of the call; and store the call, the call information, and scheduling data. The monitoring station is configured to receive the call and the call information from the monitoring server based on the scheduling data, and to display the identifying information and facilitate the review of the call.

A computer-implemented method for determining potentially undesirable voices, according to some embodiments, includes: receiving a plurality of audio recordings, the plurality of audio recordings comprising voices associated with undesirable activity, and determining a plurality of audio components of each of the plurality of audio recordings. The method may further comprise generating a multi-dimensional vector of audio components, from the plurality of audio components, for each of the plurality of audio recordings to generate a plurality of multi-dimensional vectors of audio components, and comparing audio components between the plurality of multi-dimensional vectors of audio components to determine a plurality of clusters of multi-dimensional vectors, each cluster of the plurality of clusters comprising two or more of the plurality of multi-dimensional vectors of audio components, wherein each cluster of the plurality of clusters corresponds to a blacklisted voice. The method may further comprise receiving an audio recording or audio stream, and determining whether the audio recording or audio stream is associated with a voice associated with undesirable activity based on a comparison to the plurality of clusters.

A method, system and computer program product for discovering social network groups of interests to attendees of a group gathering. Voice imprints of attendees of a group gathering are received during a registration process. The received voice imprints are associated with the registered attendees. A voice stream that was captured in the group gathering is then translated to a list of utterances. Each utterance is then tagged with the attendee who made the utterance based on the voice imprints provided by the attendees during registration. The utterances are parsed and analyzed to identify concepts and keywords. An attendee to the group gathering may then be associated with a social network group (either preexisting or newly created) with a mapping to concepts and keywords that have a similarity to the identified concepts and keywords that meets or exceeds a threshold.

One embodiment provides a method comprising answering one or more incoming phone calls received at one or more pre-specified phone numbers utilizing a bot. The bot is configured to engage in a conversation with a caller initiating an incoming phone call utilizing a voice recording that impersonates a human being. The method further comprises recording each conversation the bot engages in, and classifying each recorded conversation as one of poison data or truthful training data based on content of the recorded conversation and one or more learned detection models for detecting poisoned data.