Abstract: A method for providing streaming audio over a network from a client to a server associated with a third-party service. The method includes receiving configuration data from a tenant regarding the server. The method may further include establishing a connection with the server via a connection process. The connection process includes sending a connection request that includes: a bidirectional communication protocol configured to transmit data from the client to the server and from the server to the client by reusing an established connection channel; a tenant-Id parameter; and a session-Id parameter. The method may further include implementing an open transaction for initiating the streaming of the audio of the ongoing conversation to the server. The open transaction includes transmitting participant parameters identifying the customer and at least one choice regarding an audio format for the audio streaming.

Abstract: A method of dynamic prioritization of collaboration between human and virtual agents according to an embodiment includes generating a priority score for a conversation between a human user and a chat bot, wherein the priority score is based on at least a sentiment of the human user and a temporal aspect of the conversation, providing the priority score to a human agent via an interface for monitoring the priority score, transferring control of the conversation from the chat bot to the human agent based on an interaction of the human agent with the interface, and yielding control of the conversation from the human agent back to the chat bot in response to another interaction of the human agent with the interface.

Abstract: A method for deriving a model for a chatbot for predicting entities in a sentence. The sentence is input into a named-entity recognition module and features obtained. A LSTM RNN forward pass and backward pass is performed on the features to obtain a first and second set of results, respectively. A first concatenating is performed on the first set of results and the second set of results. A second concatenation is performed on the first concatenation using output target entities. A connected set of neurons from the second concatenation is obtained. An output is obtained, and a prediction is collected on a next output by summing the outputs previous to that output. The prediction is input into the performing of the second concatenation step, wherein the method is performed cyclically until all outputs have been processed with input predictions.

Abstract: A system and method are presented for model derivation for entity prediction. An LSTM with 100 memory cells is used in the system architecture. Sentences are truncated and provided with feature information to a named-entity recognition model. A forward and a backward pass of the LSTM are performed, and each pass is concatenated. The concatenated bi-directional LSTM encodings are obtained for the various features for each word. A fully connected set of neurons shared across all encoded words is obtained and the final encoded outputs with dimensions equal to the number of entities is determined.

Abstract: A system and method are presented for the correction of packet loss in audio in automatic speech recognition (ASR) systems. Packet loss correction, as presented herein, occurs at the recognition stage without modifying any of the acoustic models generated during training. The behavior of the ASR engine in the absence of packet loss is thus not altered. To accomplish this, the actual input signal may be rectified, the recognition scores may be normalized to account for signal errors, and a best-estimate method using information from previous frames and acoustic models may be used to replace the noisy signal.

Abstract: A method facilitating a cross-channel interaction between a customer and a contact center. The method includes: receiving and conducting a first interaction with the customer; determining a first identifier related to the first interaction; storing, in a database, the first identifier and associating the first identifier with the first interaction; receiving a second interaction from the customer; determining a second identifier related to the second interaction; using the second identifier to check the database to determine if the second interaction is associated with the first interaction; determining, based on the check of the database, that the second interaction is contextually related with the first interaction; and modifying, in response to determining that the second interaction is contextually related to the first interaction, at least one way in which the second interaction is handled by the contact center.

Abstract: A method facilitating a cross-channel interaction between a customer and a contact center. The method includes: receiving and conducting a first interaction with the customer; determining a first identifier related to the first interaction; storing, in a database, the first identifier and associating the first identifier with the first interaction; receiving a second interaction from the customer; determining a second identifier related to the second interaction; using the second identifier to check the database to determine if the second interaction is associated with the first interaction; determining, based on the check of the database, that the second interaction is contextually related with the first interaction; and modifying, in response to determining that the second interaction is contextually related to the first interaction, at least one way in which the second interaction is handled by the contact center.

Abstract: A system and method are presented for the correction of packet loss in audio in automatic speech recognition (ASR) systems. Packet loss correction, as presented herein, occurs at the recognition stage without modifying any of the acoustic models generated during training. The behavior of the ASR engine in the absence of packet loss is thus not altered. To accomplish this, the actual input signal may be rectified, the recognition scores may be normalized to account for signal errors, and a best-estimate method using information from previous frames and acoustic models may be used to replace the noisy signal.

Abstract: A system and method are presented for customer journey event representation learning and outcome prediction using neural sequence models. A plurality of events are input into a module where each event has a schema comprising characteristics of the events and their modalities (web clicks, calls, emails, chats, etc.). The events of different modalities can be captured using different schemas and therefore embodiments described herein are schema-agnostic. Each event is represented as a vector of some number of numbers by the module with a plurality of vectors being generated in total for each customer visit. The vectors are then used in sequence learning to predict real-time next best actions or outcome probabilities in a customer journey using machine learning algorithms such as recurrent neural networks.

Abstract: A method of dynamic prioritization of collaboration between human and virtual agents according to an embodiment includes generating a priority score for a conversation between a human user and a chat bot, wherein the priority score is based on at least a sentiment of the human user and a temporal aspect of the conversation, providing the priority score to a human agent via an interface for monitoring the priority score, transferring control of the conversation from the chat bot to the human agent based on an interaction of the human agent with the interface, and yielding control of the conversation from the human agent back to the chat bot in response to another interaction of the human agent with the interface.

Abstract: A method for selectively transcribing voice communications that includes: receiving keywords; receiving an audio stream of audio data of speech; searching the audio stream to detect keywords or keyword detections and recording parameter data for each that includes a location of the keyword within the audio stream; generating one or more cumulative datasets for one or more portions of the audio stream that each includes parameter data for the keyword detections occurring therein; for each of the one or more portions of the audio stream, calculating a transcription favorableness score via inputting the corresponding one of the one or more cumulative datasets into an algorithm; and determining whether to transcribe each of the one or more portions of the audio stream by comparing the corresponding transcription favorableness score against a predetermined threshold.

Abstract: A method for conducting an automated dialogue between an inbound automated voice resource and an outbound automated voice resource during a voice communication session according to one embodiment includes receiving at the inbound automated voice resource an initiation of the voice communication session from the outbound automated voice resource; transmitting, by the inbound automated voice resource, a speech communication to the outbound automated voice resource during the voice communication session, wherein a digital watermark is embedded in the speech communication; identifying, by the outbound automated voice resource, the digital watermark in response to analyzing the speech communication; converting, by the outbound automated voice resource, an outbound automated voice resource communication language from speech to machine language in response to determining that the inbound automated voice resource interprets machine language based on the digital watermark; transmitting, by the outbound automated voice

Abstract: A system is presented for load balancing across media server instances. In an embodiment, media is broken out into a multi-tenanted service allowing the media to be scaled independently of the number of organizations supported on a cloud-based collaboration platform. Scaling may occur in a scaling-out or a scaling-in operation. States for a media service may comprise in-service, quiescing, quiesced, failed, etc. The states may be used to monitor sessions associated with an instance and determine which media instances to terminate during a scaling-in operation. In an embodiment, new instances may be added to a collection of media instances in response to an increased workload in a scaling-out operation.

Abstract: A system and method are presented for optimization of audio fingerprint search. In an embodiment, the audio fingerprints are organized into a recursive tree with different branches containing fingerprint sets that are dissimilar to each other. The tree is constructed using a clustering algorithm based on a similarity measure. The similarity measure may comprise a Hamming distance for a binary fingerprint or a Euclidean distance for continuous valued fingerprints. In another embodiment, each fingerprint is stored at a plurality of resolutions and clustering is performed hierarchically. The recognition of an incoming fingerprint begins from the root of the tree and proceeds down its branches until a match or mismatch is declared. In yet another embodiment, a fingerprint definition is generalized to include more detailed audio information than in the previous definition.

Abstract: A computer-implemented method for managing a dialog between a contact center system and a user thereof, comprising the steps of: hosting a dialog over a communication channel between an automated dialog engine of said contact center and said user thereof, said dialog comprising messages sent between said automated dialog engine and said user in both directions; said automated dialog engine receiving input messages from said user, and determining response messages in response to said inputs; detecting from said messages of said dialog a trigger event matching a rule; in response to detection of said trigger event: providing said agent station with a summary of said dialog; and providing control of said automated dialog engine to said agent station.

Abstract: A method for selectively transcribing voice communications that includes: receiving keywords; receiving an audio stream of audio data of speech; searching the audio stream to detect keywords or keyword detections and recording parameter data for each that includes a location of the keyword within the audio stream; generating one or more cumulative datasets for one or more portions of the audio stream that each includes parameter data for the keyword detections occurring therein; for each of the one or more portions of the audio stream, calculating a transcription favorableness score via inputting the corresponding one of the one or more cumulative datasets into an algorithm; and determining whether to transcribe each of the one or more portions of the audio stream by comparing the corresponding transcription favorableness score against a predetermined threshold.

Abstract: A method for automated generation of contact center system embeddings according to one embodiment includes determining, by a computing system, contact center system agents, contact center system agent skills, and/or contact center system virtual queue experiences; generating, by the computing system, a matrix representation based on the contact center system agents, the contact center system agent skills, and/or the contact center system virtual queue experiences; generating, by the computing system and based on the matrix representation, contact center system agent identifiers, contact center system agent skills identifiers, and/or contact center system virtual queue identifiers; transforming, by the computing system, the contact center system agent identifiers, the contact center system agent skills identifiers, and/or the contact center system virtual queue identifiers into the contact center system agent embeddings, contact center system agent skills embeddings, and/or contact center system virtual queue

Abstract: A root behavior tree is stored with a flow control node and a plurality of child nodes. The flow control node may determine a sequence of execution of child nodes. A first-level behavior tree is stored and executed to accomplish a task with associated intent. The first-level tree comprises a child node of the root tree and nodes defining actions. A dialog between contact center and user is hosted over a communication channel and a processor receives inputs from the dialog and executes the root tree and the first-level tree as a child node of the root tree in response. Upon detecting a match between an input and a data pattern, the execution sequence within the root tree or a further tree is altered. Responsive to the altered sequence, an output is provided to cause an action.

Abstract: A processor receives inputs from a dialog between an agent and a user performed over a communication channel A knowledge base is stored, comprising entries with a subset of said entries defined as higher priority. A match is detected between an input from said dialog and a plurality of said knowledge base entries. At least one of said plurality of entries is retrieved corresponding to said match. The at least one of said plurality of entries is pushed as an output to one or more of a device operated by said user and at least one device operated by one of said user and said agent. A further match is detected between an input from said dialog and a higher priority entry in said knowledge base and pushed to said at least one device while the dialog is ongoing.

Abstract: A method is presented for executing a dialog turn in a conversation by a dialog manager comprising: receiving an input associated with a task from a user; passing the input to an NLU engine on a first task path; receiving a list of possible intents associated with the task, wherein the list of possible intents comprises an associated confidence for each of the possible intents; applying context-aware re-scoring of the confidences from the NLU engine with weight applied to one or more tasks currently active with the user; selecting an intent based on the re-scored confidences; determining a new task path in a hierarchy of intents based on the confirmed intent; confirming the selected intent and associated slots; and selecting a response flow for the new task path in the hierarchy of intents and executing the response flow.