Abstract: The present disclosure provides, among other things, a method of managing a wrap-up time in a contact center, the method including: receiving, by an agent of the contact center, a communication having a variable associated with the communication; receiving an input from a source external to the contact center; determining that the variable is related to the input; based on the relation of the variable to the input, determining an updated wrap-up time; storing the updated wrap-up time and the input in a database including timing variables; enabling a machine learning process to analyze the database; providing the updated wrap-up time to the agent as an amount of time rendered on a display to the agent; and updating a data model used to automatically determine wrap-up times based on the analysis of the machine learning process.

Abstract: A caller queue system and process for a video call-in system. The system includes a waiting room server that connects to a plurality of caller devices over a network. The waiting room server may provide content to the plurality of video caller devices and collects input received from the plurality of video caller devices. A queue managing module connected to the waiting room server prioritizes or sorts the plurality of video caller devices in a queue based on the input received from the plurality of video caller devices. The system allows a user or producer to prescreen and determine the priority of the callers and accept a higher number callers to be connected to the caller queue system.

Abstract: Machine translation is used to leverage the semantic properties (e.g., intent) already known for one natural language for use in another natural language. In a first embodiment, the corpus of a first language is translated to each other language of interest using machine translation, and the corresponding semantic properties are transferred to the translated corpuses. Semantic models can then be generated from the translated corpuses and the transferred semantic properties. In a second embodiment, given a first language for which there is a semantic model, if a query is received in a second, different language lacking its own semantic model, machine translation is used to translate the query into the first language. Then, the semantic model for the first language is applied to the translated query, thereby obtaining the semantic properties for the query, even though no semantic model existed for the language in which the query was specified.

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: A method includes receiving, at an audio encoder, multiple streams of audio data. The method includes assigning a priority to each stream of the multiple streams and determining, based on the priority of each stream of the multiple streams, a permutation sequence for encoding of the multiple streams. The method also includes encoding at least a portion of each stream of the multiple streams according to the permutation sequence.

Abstract: The present disclosure relates to speech recognition systems and methods that enable personalized vocal user interfaces. More specifically, the present disclosure relates to combining a self-learning speech recognition system based on semantics with a speech-to-text system optionally integrated with a natural language processing system. The combined system has the advantage of automatically and continually training the semantics-based speech recognition system and increasing recognition accuracy.

Abstract: Techniques for workforce management in a contact center system are disclosed. In one particular embodiment, the techniques may be realized as a method for workforce management in a contact center system comprising generating historical workforce data regarding an agent workforce capacity of the contact center system, and initiating an increase or decrease to an agent workforce of the contact center system based at least in part on the historical workforce data to increase an amount of choice among available agents or waiting contacts.

Abstract: A processor-implemented machine translation method includes generating a target sentence by translating a source sentence expressed in a source language into a target language; and determining a reliability of the target sentence based on one or more generated third sentences generated by translating either one or both of the source sentence and the target sentence into a third language.

Abstract: A computer system is described that is configured to enable customers of an organization to self-monitor account activity and modify account access settings via a contact center of the organization. The contact center control system is configured to provide an interactive call history associated with the customer's accounts with the organization. Using the call history, the customer may perform self-monitoring of calls into the contact center that access the customer's accounts, and notify the organization if any of the calls appear suspicious. The contact center control system is configured provide a user interface through which the customer may modify account access settings including changing which types of authentication methods are enabled to access the customer's accounts, and blocking account access by callers from certain phone numbers. The contact center control system may allow the customer to turn off all access to the customer's accounts via the contact center.

Abstract: A speaker recognition system includes a non-transitory computer readable medium configured to store instructions. The speaker recognition system further includes a processor connected to the non-transitory computer readable medium. The processor is configured to execute the instructions for extracting acoustic features from each frame of a plurality of frames in input speech data. The processor is configured to execute the instructions for calculating a saliency value for each frame of the plurality of frames using a first neural network (NN) based on the extracted acoustic features, wherein the first NN is a trained NN using speaker posteriors. The processor is configured to execute the instructions for extracting a speaker feature using the saliency value for each frame of the plurality of frames.

Abstract: Techniques for conducting a support session and determine suitable instructions for resolving a certain technical mal-function in a device/equipment of a user. Imagery data associated the technical mal-function is received from a user's device and used for determining at least one improperly setup property associated with the mal-function in the mal-functioning device/equipment based on a comparison of the received imagery data with reference data. Instructions comprising augmented imagery for resolving the mal-function can be then generated, or fetched form a database, based on the determined at least one improperly setup property. A new database record can be generated comprising the augmented imagery data for use in future support sessions associated with the mal-function.

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: 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: A method for providing a vehicle AI service is provided. The method includes steps of: an AI service providing device (a) supporting an AI server to extract from a voice of a user (i) at least one of skill candidates including service categories and (ii) at least one of command candidates, to create voice analysis data, and receiving it from the AI server; and (b) (I) analyzing at least one of (i) the voice analysis data, (ii) second data created by analyzing voices of other users within a certain time, (iii) third data created by analyzing voices of the user within a particular time, and (iv) fourth data having information on context of the user, and (II) recognizing an intention included in the voice and determining a final skill and a final command matching the intention; wherein each of the data includes the skill candidates and the command candidates.

Abstract: Certain aspects of the disclosure are directed to apparatuses and methods involving a data-communication apparatus that includes a data-communications server and processing circuitry in communication therewith. The data-communication server interfaces with a plurality of remotely-situated client entities for providing data communication services. The processing circuitry accesses an archive of digital voice data indicative of transcribed audio conversations for at least one of the plurality of remotely-situated client entities, calendar information, and a client data-communications server for geographic information of the agents and system parameters. The processing circuitry analyzes the digital voice data associated with the agents, the calendar information, and the system parameters to predict a call answer rate for agents of a geographic region of the at least one remotely-situated client entity for a period of time and reroutes incoming calls based on the predicted call answer rate.

Abstract: Contact centers strive to match the best resource, commonly an agent, with a customer for an interaction, such as telephone call, text exchange, or email exchange. Often the initial best match is not the best match upon a different agent being identified and/or new information being gathered. Therefore, it is often beneficial to take a call routed to an agent, who may or may not have answered the call, and reroute it to a different agent. If the agent has already answered the call, the benefits need to at least exceed the costs associated with the transfer. To avoid creating an unstable or unending re-assessment, if the cost-benefit for a particular routing (or rerouting) calls between agents has reached a Nash Equilibrium, the system is stable and, absent new information, re-evaluation unnecessary.

Abstract: Techniques for providing a standardized voice user interface (VUI) that enables voice to voice natural language understanding (NLU) processing are described. The standardized VUI may be added to speechlets to enable a customer to interact with a business via server(s) using NLU processing. For example, a first user may initiate a first voice interaction using NLU processing with the server(s) and the system may initiate a second voice interaction using NLU processing between the server(s) and a second user. This enables a customer to initiate a transaction (e.g., request information, place an order, make a reservation, etc.) with the business using the speechlet. Thus, the business may use the speechlet to offer services without requiring additional infrastructure or complicated programming to implement.

Abstract: An apparatus, system and method for call notifications to active communication devices are provided. At an apparatus comprising a processor and a communication interface, a call for a first device is received via the communication interface. When is determined that a second device is active, a notification of the call is transmitted to the second device.

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: 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.