A call analytics system and associated methods that can be used to rapidly analyze call data and provide conversational insights. The call analytics system receives audio call data of a phone call between a customer and an agent of a business, and converts the call data into one or more messages for handling by a distributed stream-processing platform. In some embodiments, the stream-processing platform is the Apache Kafka platform. The distributed platform processes the messages and communicates with various software modules to generate a variety of conversational insights. When processed by a stream-processing platform, certain analyses can occur in parallel which allows conversational insights to be provided to the businesses shortly (e.g., within seconds) after the call data is received.

Embodiments disclosed are directed to a computing system that performs steps to automatically generate fine-grained call reasons from customer service call transcripts. The computing system extracts, using a natural language processing (NLP) technique, a set of events from a set of text strings of speaker turns. The computing system then identifies a set of clusters of events based on the set of events and labels each cluster of events in the set of clusters of events to generate a set of labeled clusters of events. Subsequently, the computing system assigns each event in the set of events to a respective labeled cluster of events in the set of labeled clusters of events.

Methods and systems for replaying buffered audio of a telephone call are provided herein. In some embodiments, a method for replaying buffered audio of a telephone call, comprises buffering audio data associated with a telephone call when a quality of an established data connection decreases below a first threshold quality measure; playing the buffered audio data from the buffer; determining the quality of the established data connection exceeds a second threshold quality measure; and replaying the audio data from the buffer, wherein replaying the audio comprises modifying the playback rate of the buffered audio data during playback.

Methods and systems are disclosed herein for improving the quality of audio for use in a biometric. A biometric system may use machine learning to determine whether audio or a portion of the audio should be used as a biometric for a user. A sample of the user's voice may be used to generate a voice signature of the user. Portions of the audio that do not meet a similarity threshold when compared with the voice signature may be removed from the audio. Additionally or alternatively, interfering noises may be detected and removed from the audio to improve the quality of a voice biometric generated from the audio.

Methods and systems are disclosed herein for improving the quality of audio for use in a biometric. A biometric system may use machine learning to determine whether audio or a portion of the audio should be used as a biometric for a user. A sample of the user's voice may be used to generate a voice signature of the user. Portions of the audio that do not meet a similarity threshold when compared with the voice signature may be removed from the audio. Additionally or alternatively, interfering noises may be detected and removed from the audio to improve the quality of a voice biometric generated from the audio.

There is disclosed in one example a mobile telephone, including: a hardware platform including a processor and a memory; a telecommunication transceiver; and instructions encoded within the memory to instruct the processor to: identify a call made via the telecommunication transceiver; analyze the call and assign the call a predicted local reputation according to the analysis, including a legitimacy confidence score; if the legitimacy confidence score is less than a first threshold, terminate the call; if the legitimacy confidence score is greater than a second threshold, cease analysis of the call; and if the legitimacy confidence score is between the first and second thresholds, continue analysis of the call.

A system and method may identify a fraud ring based on call or interaction data by analyzing by a computer processor interaction data including audio recordings to identify clusters of interactions which are suspected of involving fraud each cluster including the same speaker; analyzing by the computer processor the clusters, in combination with metadata associated with the interaction data, to identify fraud rings, each fraud ring describing a plurality of different speakers, each fraud ring defined by a set of speakers and a set of metadata corresponding to interactions including that speaker; and for each fraud ring, creating a relevance value defining the relative relevance of the fraud ring.

There is provided a method, and application server for enabling recording of communications transmitted via an Internet Protocol Multimedia Subsystem Network. A call request is received from a first party to call a second party and a database, comprising a plurality of subscriber profiles, is queried to obtain subscriber configuration data relating to at least one of the first party and the second party. Based on the subscriber configuration data, media streams are caused to be transmitted between the first party and a Media Resource Function, between the second party and the Media Resource Function, and from the Media Resource Function to a recording device to record at least part of a call between the first and second party. A communications network and a user device are also provided.

A method is disclosed for forking call audio channels. The method includes, during an active call, receiving a first audio stream of first call audio that originates from a far-end telephony device, and receiving a second audio stream of second call audio that originates from a microphone of a near-end headset. Further, the method includes generating, during the active call, a third audio stream containing the first call audio by processing the first audio stream, and generating a fourth audio stream containing the second call audio by processing the second audio stream. Still yet, the method includes, during the active call, generating a fifth audio stream containing the first call audio, and generating a sixth audio stream containing the second call audio.

A computerized-method for providing real-time lockless parallel screen recording compliance enforcement to omni-channel cloud systems, is provided herein. In a processor of a client computer configured to execute code for recording events of one or more voice or digital interactions, on one or more screens associated to the client computer, the computerized-method maintains a cache for storing a masked state. Each interaction is having an associated interaction identifier and upon receiving a screen event from a server of a cloud-based video recording that is communicating with the client computer over a communication network, operating a compliance-enforcement module. The compliance-enforcement module includes updating the cache; and operating a module of recording of screen events for the screen events of the one or more voice or digital interactions. Thus, by updating in real-time the cache on the client computer refraining from database locks in the server of the cloud-based video recording.