Video conferencing in a controlled environment facility entails significant security concerns. These concerns are even more prevalent in a system that permits residents of such facilities to communicate via their own personal devices. Therefore, in order to alleviate these concerns and provide a secure system in which a resident is able to make video calls using their personal device, a kiosk unit is provided to which the personal device must be linked for completing a video call. When making the video call, the camera and display on the personal device are disabled, and all video data is captured and displayed by the kiosk unit. The link between the kiosk unit and the personal device facilitates the exchange of the image information for transmission to the outside party, or display to the user. By providing a fixed camera, and disabling the personal device camera, security can be maintained while permitting video calling services.

A computerized system comprising: (a) a compliance server adapted to receive an audio feed of a telephone conversation; (b) an identification module adapted to compare said audio feed to a database of voice prints and identify participants in said telephone conversation; and (c) an analysis module adapted to ascertain a subject of said telephone conversation.

A method for splitting a digital signal using prosodic features included in the signal is provided that includes calculating onset value locations in the signal. The onset values correspond to stress accents in the signal. Moreover, the method includes splitting, using a processor, the signal into a prosodic unit candidate sequence by superimposing the stress accent locations on the signal, and processing the sequence to include only true prosodic units.

A method of controlling free phone calls places from within a secured premises through an institutional phone system generally includes assigning a unique access identifier to an individual caller upon entry into the secured premises; receiving a destination number front the individual caller within the secured premises, the destination number being associated with a telephone located outside the secured premises; determining if the destination number is a per se free number, and, if the destination number is not determined to be a per se free number: receiving the unique access identifier from the individual caller; validating the unique access identifier; and, if the unique access identifier is valid, processing a telephone call to the destination number.

Disclosed is a secure telephone call management system for authenticating users of a telephone system in an institutional facility. Authentication of the users is accomplished by using a personal identification number, preferably in conjunction with speaker independent voice recognition and speaker dependent voice identification. When a user first enters the system, the user speaks his or her name which is used as a sample voice print. During each subsequent use of the system, the user is required to speak his or her name. Voice identification software is used to verify that the provided speech matches the sample voice print. The secure system includes accounting software to limit access based on funds in a user's account or other related limitations. Management software implements widespread or local changes to the system and can modify or set any number of user account parameters.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a dynamic threshold for speaker verification are disclosed. In one aspect, a method includes the actions of receiving, for each of multiple utterances of a hotword, a data set including at least a speaker verification confidence score, and environmental context data. The actions further include selecting from among the data sets, a subset of the data sets that are associated with a particular environmental context. The actions further include selecting a particular data set from among the subset of data sets based on one or more selection criteria. The actions further include selecting, as a speaker verification threshold for the particular environmental context, the speaker verification confidence score. The actions further include providing the speaker verification threshold for use in performing speaker verification of utterances that are associated with the particular environmental context.

An automated calling system authenticates and subsequently communicates via a telephone network with a person such as a current or prospective customer. The communication may be in regards to an account having an adverse account status (e.g. a payment delinquency, an overdrawn checking account, being over the credit limit on a credit card, excessive transactions on one account, suspicious or fraudulent transactions on an account, and so on).

Disclosed embodiments may include a method for dynamically detecting disabilities. The method may include receiving image data and sensory data from an imaging device and one or more sensors of a user interacting with a machine, determining, using a machine learning model, whether the user interacting with the machine is impaired based on the image data or the sensory data, or combinations thereof, and in response to determining that the user is impaired: causing the machine to output a sound or one or more vibration sequences within a predetermined distance from a reader of the machine, initiating a phone call to a user device associated with the user using a phone number associated with the data, initiate a machine process, receiving, from the user device, a command to terminate the machine process, and transmitting a termination instruction to the machine.

Disclosed is a secure telephone call management system for authenticating users of a telephone system in an institutional facility. Authentication of the users is accomplished by using a personal identification number, preferably in conjunction with speaker independent voice recognition and speaker dependent voice identification. When a user first enters the system, the user speaks his or her name which is used as a sample voice print. During each subsequent use of the system, the user is required to speak his or her name. Voice identification software is used to verify that the provided speech matches the sample voice print. The secure system includes accounting software to limit access based on funds in a user's account or other related limitations. Management software implements widespread or local changes to the system and can modify or set any number of user account parameters.

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.