The present disclosure provides methods and systems that may be used for providing quality control for audio samples. The audio samples may be speech samples of a user. The user may be participating in an audio interview.

A quality-of-service management system includes a terminal and a server (a quality-of-service management device), the terminal determines whether or not a satisfaction condition is satisfied for a predetermined terminal-side determination item in response to a start request of QoS control from an application or the terminal and transmits a condition determination request for starting QoS control to the server when it is determined that the condition is satisfied, the server determines whether or not the satisfaction condition is satisfied for a predetermined server-side determination item in response to the condition determination request for starting QoS control, and at least one of the terminal and the server starts QoS control when it is determined that the condition is satisfied.

A new audio quality assessment system includes an assessment system running in a receiver system of a VoIP communication system. The new audio quality assessment system determines an accurate MOS of a VoIP call within a time window. The audio quality assessment system determines an effective PLC counter, a PLC impact factor, an effective AS counter, an AS impact factor, a network impact factor, a codec type of the received voice packets, a bitrate of the received voice packets, an initial MOS from a configured codec-bitrate MOS table, and determines the accurate MOS based on these data. The determined MOS is more accurate and efficiently obtained since it is based on efficiently collected statistics of the receiver system's modules and a pre-configured codec-bitrate MOS table.

A conferencing system terminal device includes a display, an audio output, a user interface, a communication device, and one or more processors. The one or more processors present an audio difficulties user actuation target upon the display during an audio or video conference occurring across a network and concurrently with a presentation of conference content. Actuation of the audio difficulties user actuation target indicates that audio content associated with the audio or video conference being delivered by the audio output is impaired.

Techniques are described for training a learning machine. One of these methods includes tracking interactions between a customer and customer service agents. The method includes generating a training set based on the tracked interactions. The method also includes generating a trained learning machine comprising training a learning machine using the training set.

A method for determining the quality of a media stream transmitted via a communication network, including at least the quality of the media stream as it is transmitted via a radio access network to a receiving device, based on data which is obtained prior to that transmission via the radio access network. The method utilizes a predictive model which is developed using a machine-learning algorithm.

Embodiments of the present disclosure provide methods, apparatus, systems, computing devices, and/or computing entities for processing a call drop likelihood prediction for an interactive call data object. In accordance with one embodiment, a method is provided that includes: identifying a group of interactive call feature data objects associated with the interactive call data object that comprises an interactive call audio data object and an interactive call metadata object; processing the call feature data objects using a real-time call monitoring machine learning framework to generate the prediction by: processing the call audio data object using an audio data processing machine learning model to generate an audio-based embedding data object, processing the call audio data object using an audio transcript processing machine learning model to generate a transcript-based embedding data object, and generating the prediction based at least in part on the audio-based and transcript-based embedding data objects and the metadata object.

Present invention refers to a method and a system for intelligent routing of an incoming call over a dual telecommunication network supporting both CS and PS connections, comprising: initiating, from a call router server, a CS call establishment connection; at roughly the same time, sending, a push message over the PS connection to a callee's mobile device; as result of receiving the push message, registering said callee's mobile device into the call router server; providing the call router server with a measure of quality of a PS connection; and in the event of receiving, at the call router server, an unreachable notification from the CS connection and the measure of quality is higher than a pre-established minimum value, routing the incoming call through the PS connection.

In a voice-over-IP communications network, call data records include dynamically assigned IP signaling addresses such as IPv6 signaling addresses used in provisioning communications sessions. Those dynamically assigned IP signaling addresses are computed from customer site identification codes using a reversible algorithm. The algorithm can then be reversed to compute a customer site identification code from an IP signaling address contained in a call data record, allowing the communications network provider to perform quality monitoring and diagnostics based on call data records.

In an approach to generating a digital sentiment signature to characterize an end to a communication, one or more computer processors detect a start of a communication between at least two participants. A computer starts a digital timer of the communication. A computer identifies one or more digital marks of the communication, where the one or more digital marks are a reflection of a sentiment of at least one of the at least two participants in the communication. A computer generates a digital sentiment signature based on the digital timer and on the one or more digital marks, where the digital sentiment signature is a digital signal that can be communicated across a plurality of types of communication channels. A computer detects an end of the communication. A computer determines a reason for the end of the communication. A computer stores the reason.