Abstract: Generally discussed herein are devices, systems, and methods for speech recognition. Processing circuitry can implement a connectionist temporal classification (CTC) neural network (NN) including an encode NN to receive an audio frame and generate a current encoded hidden feature vector, an attend NN to generate, based on a current encoded hidden feature vector and a first context vector from a previous time slice, a weight vector indicating an amount the current encoded hidden feature vector, a previous encoded hidden feature vector, and a future encoded hidden feature vector from a future time slice contribute to a current, second context vector, an annotate NN to generate the current, second context vector based on the weight vector, the current encoded hidden feature vector, the previous encoded hidden feature vector, and the future encoded hidden feature vector, and a normal NN to generate a normalized output vector based on the context vector.

Abstract: A system herein provides automated call-back of customers who have terminated an inbound call by exercising a call-back option of an interactive voice response unit or by abandoning the inbound call, using predictive modeling of caller value to prioritize call-backs. The call management system monitors the inbound customer call and detects any termination of the customer call. A call-back module opens a call-back record for the terminated customer call and associates that call-back record with an identified customer. The call-back module retrieves customer demographic data and other data associated with the identified customer. A predictive module determines a value prediction signal for the identified customer by modeling purchase and lapse behaviors and classifies each identified customer for either priority call-back or subordinate call-back treatment.

Abstract: Placing calls in a non-disturbing manner that includes receiving, by a communication server from a caller endpoint device, a request to place a call to a called endpoint device, wherein the request comprises an indication that the called endpoint device is to be notified about the call in a non-disturbing manner. The communication server also receives from the caller endpoint device, a time period for which a user of the caller endpoint device is available to receive a callback from the called endpoint device, a context associated with the call. Then, the communication server can forward to the called endpoint device, the call, wherein the call includes the time period and the context associated with the call.

Abstract: A system and method for dynamically updating a service level agreement during a communication with a contact center are disclosed. The system and method are configured to display an initial time associated with a predetermine SLA path and then update the displayed time based on a communication between an agent and a customer.

Abstract: Provided is a method, a system, an apparatus, and/or a non-transitory computer readable medium for providing a ringback tone and a ringtone using a Voice over Internet Protocol (VoIP) call service. A call method may provide sound sources directly edited by users as a ringtone or a ringback tone in a VoIP call service.

Abstract: Systems and methods directed to discovery by a user equipment (UE) of a bot functionality available from an entity during a call set up between the UE and the entity are provided. The UE may initiate call the entity, for example a business, using a session initiation protocol (SIP) in a communication network, and, as a part of SIP signaling, an operator of the communication network may add to a SIP header a profile of the bot functionality offered by the business, which is forwarded to the UE. Once the UE processes the information included in the profile, the UE and the business may communicate using the bot functionality.

Abstract: A method of smart coding mode switching includes receiving a first data including a primary copy and a partial copy. The method includes determining if switching a coding mode from channel aware mode to non-channel aware mode may be advantageous. The method further includes transmitting a request to another device for coding mode switch in response to determination result. The method includes receiving and decoding of a second data that includes a primary copy.

Abstract: A method includes decoding a low-band portion of an encoded mid channel to generate a decoded low-band mid channel. The method also includes filtering the decoded low-band mid channel according to one or more filter coefficients to generate a low-band filtered mid channel. The method also includes generating an inter-channel predicted signal based on the low-band filtered mid channel and the inter-channel prediction gain. The method further includes generating a low-band left channel and a low-band right channel based on an up-mix factor, the decoded low-band mid channel, and the inter-channel predicted signal.

Abstract: As “call centers” continue to be replaced with omnichannel contact centers, managing a plurality of simultaneous media channels becomes more important. Contacting a customer on one channel and, at the customer or agent's request, initiating a second channel that delays the interaction will having limited acceptance and, in some jurisdictions, may be illegal. By nailing-up an agent half-communication with a number of channels, agents maintain a perpetual connection comprising an agent half-communication to a server, such as one serving as a media anchor point, share point, etc. The customer half-connection is established to a server and the agent, already connected, is joined. As a result, the customer experiences a greatly reduced delay between the time they answer and being greeted by an agent, regardless of the media type or types utilized.

Abstract: In various embodiments, a predictive dialer in a contact center is managed by a Communication Attempt Management System (“CAMS”) that manages the total number of communications attempts, including voice calls, originated to an individual associated with an account within a period of time. In particular embodiments, a list comprising account data of a plurality individuals may be processed by the CAMS to identify those accounts which have exceeded a weekly limit on the number of allowable communication attempts and are not authorized to receive further communications in that period of time. The list is modified to reflect those accounts which have not exceeded their corresponding limit and are authorized to be contacted. The modified list is provided to the predictive dialer, which then originates a call to each account. The CAMS may then update each account to reflect each communication attempt made by the predictive dialer.

Abstract: Traditional audio feedback elimination systems may attempt to reduce the effect of the audio feedback by simply scaling down the audio volume of the signal frequencies that are prone to howling. Other traditional feedback elimination systems may also employ adaptive notch filtering to detect and “notch” the so-called “singing” or “howling” frequencies as they occur in real-time. Such devices may typically have several knobs and buttons needing tuning, for example: the number of adaptive parametric equalizers (PEQs) versus fixed PEQs; attack and decay timers; and/or PEQ bandwidth. Rather than removing the singing frequencies with PEQs, the devices described herein attempt to holistically model the feedback audio and then remove the entire feedback signal. Two advantages of the devices described herein are: 1.) the system can operate at a much larger loop-gain (and hence with a much higher loudspeaker volume); and 2) setup is greatly simplified (i.e., no tuning knobs or buttons).

Abstract: A system and method for establishing contact between a customer contact center agent and a customer based on customer availability information. A plurality of communication channels that may be used to communicate with the customer is monitored by the contact center. The availability of the customer is identified for each of the plurality of communication channels and user availability data is dynamically adjusted for each of the plurality of communication channels. The user availability data is provided to a contact center agent handling, for example, an offline task involving the customer. The contact center agent may use the availability data to establish contact with the customer to better handle the offline task.

Abstract: Cognitive routing of an incoming call includes analyzing respective captured audio and video data related to each of a plurality of agents of an enterprise, each agent associated with a respective mobile device; and determining a respective current activity in which each agent is engaged based on the agent's related captured audio and video data. Such routing also includes selecting one of the plurality of agents to receive an incoming call based at least in part on the determined respective current activity in which each agent is engaged; and routing an incoming call to the mobile device associated with the selected one agent.

Abstract: The disclosed system and methods provide real-time information about how agents and customers sound as they are speaking, allowing a supervisor to continuously monitor how agents are doing. The system allows agents to visualize their own speech behavior performance during and after a conversation while viewing important comparative information about prior conversations, and gamifies conversations in real-time by providing visual comparison between the live conversations and various target metrics. The visualization in-turn enhances agent interactive skills such as active listening and mirroring, as well as decision-making skills based on observations of customer engagement and distress levels.

Abstract: An example method of assigning a telephone number to a user account in a communications system is provided. The method includes obtaining a mnemonic seed and obtaining a subset of telephone numbers filtered from a global telephone number pool based on the mnemonic seed. The alphanumeric representation of each telephone number in the subset is within a threshold Hamming distance of the mnemonic seed. The method further includes receiving an indication of a selected telephone number from the subset and assigning the selected telephone number to the user account.

Abstract: A system for managing resource commitment in a contact center includes: a processor; and a memory, wherein the memory stores instructions that cause the processor to: receive over a shared data communications channel a request for contact center resources, wherein the request is for handling activities for the contact center. having an activity type; transmit a signal to initiate a raise round according to the request over the data communications channel to a pool of resources registered to communicate on the data communications channel; receive a plurality of volunteer signals from a plurality of volunteering resources from the pool of resources; select one or more of the plurality of the volunteering resources for fulfilling the request; and transmit a message to the selected volunteering resources for committing the selected volunteering resources to the request, wherein the committed resources are selected for routing an activity having the activity type.

Abstract: A system, computer program product, and method are provided to automate a framework for knowledge graph based persistence of data, and to resolve temporal changes and uncertainties in the knowledge graph. Natural language understanding, together with one or more machine learning models (MLMs), is used to extract data from unstructured information, including entities and entity relationships. The extracted data is populated into a knowledge graph. As the KG is subject to change, the KG is used to create new and retrain existing machine learning models (MLMs). Weighting is applied to the populated data in the form of veracity value. Blockchain technology is applied to the populated data to ensure reliability of the data and to provide auditability to assess changes to the data.

Abstract: Devices, computer-readable media and methods for delivering customer service content associated with a reason code are disclosed. Examples of the present disclosure may include a processor of a telecommunication network identifying a reason code associated with calls from customers to a customer call center and determining a set of shared traits among the customers. The shared traits may be based upon first network event data and first customer account data associated with the customers. The processor may further determine a customer with a propensity to call score that exceeds a threshold and with a customer profile that matches the set of shared traits. The customer profile may be based upon second network event data and second customer account data associated with the customer. The processor may further deliver a customer service content associated with the reason code to the customer via a communication modality that is determined for the customer.

Abstract: A telecommunications method for call forwarding including storing information regarding a called party in at least one local database, where the information regarding the called party is stored in a user account and making a telephone call by dialing a telephone number with a telephone, where the telephone is contained in a telephone management system. The method also includes determining whether the telephone number is associated with the user account and transferring, via the switchboard, the call to the called party if the telephone number is associated with the user account, where the telephone management system is in communication with a revenue management system, and also where the revenue management system contains at least one local database.

Abstract: A method of configuring a network element, for example an amplifier in a VDSL network. Configuration is transmitted to the amplifier using a common mode voltage signal so that there is no interference with the telephony or DSL signals.