Method and system for processing a telephone call comprising initiating a telephone call. Taking a first action if the telephone call is answered before a call alert is initiated. Taking a second action if the telephone call is answered after the call alert is initiated. Furthermore, a first action may be taken if the telephone call is answered before a call alert is initiated or if the telephone call is answered within a time period following the call alert being initiated. The second action may be taken if the telephone call is answered after expiry of the time period following the call alert being initiated.

Implementations described herein relate to methods, systems, and computer-readable media to label incoming phone calls. A method to label an incoming phone call includes detecting the incoming phone call associated with a caller identifier (ID), determining a location associated with the call, and analyzing a call header of the call to determine one or more call characteristics. The method further includes determining, based on the location and the call characteristics, if the location is spoofed and determining, based on the caller ID and the call characteristics, if an access network associated with the call is spoofed. The method further includes applying a trained machine learning model to determine whether the call is a robocall. The method further includes assigning a label to the call that indicates whether the call is a spoofed call or is the robocall and sending the label to a callee device associated with the call.

A method and apparatus for identifying a faked video is provided herein. During operation, when a video, or video call is received from a device, a simultaneous audio call is placed to the device (i.e., the video call and audio call take place simultaneously in time). The audio streams on both the video and audio call are compared, and a difference between the audio streams is identified. The video is deemed a potential fake if the difference between the audio streams is above a particular threshold.

A method and system for automatically detecting and blocking robocalls. A robocall application on a server network device detects whether incoming calls from a first network device requesting a connection to a second network device are live voice calls are robocalls including natural synthesized voice data or artificial synthesized voice data. The robocall application on a server network device also detects whether incoming or outgoing calls from a third-party network device used to connect the first network device to the second network device are live voice calls or are robocalls including natural synthesized voice data or artificial synthesized voice data. Robocalls are automatically detected and blocked.

A method of recorded message detection is provided. In this an audio restream is received and a set of landmark features is identified in a section of the audio stream. From these landmark features an audio finger print for the section of the audio stream is determined. This audio finger print is compared with at least one of the plurality of stored audio finger prints, each derived from a respective audio stream. It is determined that the received audio stream is a recorded message if a derived audio finger print is substantially equivalent to one of the plurality of stored audio finger prints representing a recorded message.

A method of operating a telephony system for determining whether a telephone call made to a call destination terminal is a live call which is answered by a live person and not by an answering machine, the system performing steps comprising detecting that the telephone call has been answered and that the call is in progress transmitting one or more voice messages in a transmitted signal to the call destination terminal analyzing a received signal from the call destination terminal to detect voice signals, and determining whether or not the telephone call is a live call by applying test criteria to relative timing of events in the received signal and transmitted signal, the test criteria being based on an expected pattern of speech and silence representative of normal conversation.

Various embodiments of the invention provide methods, systems, and computer program products for determining whether a call has reached a live party or a machine. Specifically, a call handler that is handling the call analyzes a cadence of the audio of the call while a speech analytics system analyzes the audio of the call to detect one or more keywords over a call leg established between the call handler and speech analytics system. Accordingly, in particular embodiments, the call handler may make a first determination that the call has reached a live party or a machine based on the cadence of the audio and may make a second determination that the call has reached a live party or a machine based on an event received from the speech analytics system as a result of the speech analytics system detecting a particular keyword in the audio of the call.

An apparatus provides a method for analyzing a situation of a called terminal based on a sound source provided by a telecommunication service provider. The method includes storing feature inforamtions of situation guidance sound sources provided by telecommunication service providers according to the situation of the called terminal; after a call connection request to a called terminal, receiving a sound source provided by a telecommunication service provider according to a situation of the called terminal; extracting at least one analysis duration of the received sound source with reference to a beep/tone of the received sound source, corresponding to feature inforamtions of at least one candidate sound source among the situation guidance sound sources; and determining a situation of the called terminal based on a matching degree of the received sound source and the candidate sound source relating to a corresponding analysis duration, for respective analysis durations.

A contact center system for performing call progress analysis including tone and speech classification according to an embodiment includes at least one processor and at least one memory comprising a plurality of instructions stored thereon that, in response to execution by the at least one processor, causes the contact center system to determine a cumulative average of an entropy of an audio signal received by the contact center system, determine a cumulative average power spectral amplitude and a cumulative average spectral entropy of the audio signal, calculate a difference measure of the audio signal as a difference between the cumulative average of the entropy and the cumulative average spectral entropy, distinguish tones from speech of the audio signal based on the difference measure, and process one or more tones of the audio signal in response to identification of the one or more tones in the audio signal.

A call challenger can receive a user input from a called party identity to opt-in to a call challenge service, and a second user input of a keyword. When the call challenger receives a call directed to a user equipment of the called party identity, the call challenger can prompt the calling party to provide an audible response. In response to a receipt of the audible response, the call challenger can convert the audible response to a text. The call challenger can compare the text with the keyword to determine if there is a sufficient match. In response to the determining the output of the comparing does not satisfy a threshold match score, the call challenger can prevent the call from connecting with the user equipment.