An AI based moderator system for an electronic conference. The moderator scores users based on ratings and diversity, and attempts to keep a high rating person talking while maintaining diversity.

An AI based moderator system for an electronic conference. The moderator scores users based on ratings and diversity, and attempts to keep a high rating person talking while maintaining diversity.

In one embodiment, a device obtains audio data from one or more past conferences. A prediction model that predicts when participants of a conference will speak is generated based on the audio data from the one or more past conferences. The device uses the prediction model to predict a speech distribution for participants of a particular conference. Then, the device proactively optimizes audio parameters of the particular conference based on its predicted speech distribution.

A system, method, and computer readable medium that facilitate user authentication via voice biometrics in a network system featuring interactive voice response system access is provided. The voice biometric authentication mechanisms alleviate identity theft occurring via specific interactive voice response transactions. A voice biometrics authentication system interfaces with an interactive network platform and may be hosted by a third party provider of voice biometric technologies.

Systems and methods are provided for identifying and displaying whiteboard text and/or an active speaker in a video-based presentation, e.g., a video conference. Video images of an environment including a whiteboard may be captured by a video camera system. The video images may be analyzed to detect at least one text-containing area in the environment. Each text-containing area may be analyzed to determine whether it is an area of a whiteboard. When a text-containing area is identified as a whiteboard area, an area of view including the text-containing whiteboard area may be selected for display, e.g., a subset of the full frame captured by the video system. A video feed from the video camera system may be controlled to display the selected area of view at a client device, to provide a useful view of the whiteboard text and/or a speaking person located near the whiteboard text.

A method for providing data produced in a conference, in which voice signals from participants in the conference are mixed in a conference bridge, can include provision of a time base that runs concurrently over the duration of the conference and setup of automatic identification of each participant when this participant speaks in the conference. The method also comprises capture of conversation contribution by each speaking participant to a conversation by the participants which is conducted during the conference as speaking time associated with each speaking participant at the conference, association of a time stamp with the speaking time, and production of statistical data by virtue of statistical evaluation of the speaking times of the participants.

Systems and methods for identifying a participant providing audible information during a communication session are disclosed. More particularly, speech localization is utilized to determine a location of the participant providing audible information. An identification device determined to be at a location corresponding to the location of the participant providing audible information is identified. The identity of the participant providing the audible information is then obtained by mapping the identification device to the participant. The information identifying the participant providing audible information can be provided to other endpoints of the communication session.

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. In another aspect, the invention automatically tags audio data retrieved from a database, by steganographically encoding into the audio data the identity of the official retrieving the audio data.

Prompt snippets (typically 800 ms long) that are used to detect voice prompts within a call waveform may be divided into smaller sniplet portions (approx. 100 ms) long. The presence of a prompt in a call waveform may be detected by detecting the sniplets and determining if a sufficient number of the sniplets of a snippet were detected in sequence and within allowable time constraints. The use of sniplets improves accuracy of prompt detection in call waveforms in lower quality transmissions.

A method of accessing a wireless communication network using secure voice print authentication. The method includes receiving a request from a mobile device at a gateway of the wireless communication network for service on the wireless communication network. A voice print is obtained at the gateway from a user using the mobile device. The voice print is compared by the gateway with a primary voice print, wherein the primary voice print is associated with a voicemail account at the wireless communication network, and wherein the voicemail account is associated with a primary user of the mobile device. Based upon comparing the voice print with the primary voice print, the service may be provided to the mobile device on the wireless communication network.