Abstract: A system and method are presented for acoustic data selection of a particular quality for training the parameters of an acoustic model, such as a Hidden Markov Model and Gaussian Mixture Model, for example, in automatic speech recognition systems in the speech analytics field. A raw acoustic model may be trained using a given speech corpus and maximum likelihood criteria. A series of operations are performed, such as a forced Viterbi-alignment, calculations of likelihood scores, and phoneme recognition, for example, to form a subset corpus of training data. During the process, audio files of a quality that does not meet a criterion, such as poor quality audio files, may be automatically rejected from the corpus. The subset may then be used to train a new acoustic model.

Abstract: A system and method are presented for real-time speech analytics in the speech analytics field. Real time audio is fed along with a keyword model, into a recognition engine. The recognition engine computes the probability of the audio stream data matching keywords in the keyword model. The probability is compared to a threshold where the system determines if the probability is indicative of whether or not the keyword has been spotted. Empirical metrics are computed and any false alarms are identified and rejected. The keyword may be reported as found when it is deemed not to be a false alarm and passes the threshold for detection.

Abstract: A system and method are presented for negative example based performance improvements for speech recognition. The presently disclosed embodiments address identified false positives and the identification of negative examples of keywords in an Automatic Speech Recognition (ASR) system. Various methods may be used to identify negative examples of keywords. Such methods may include, for example, human listening and learning possible negative examples from a large domain specific text source. In at least one embodiment, negative examples of keywords may be used to improve the performance of an ASR system by reducing false positives.

Abstract: Various technologies and techniques are disclosed for automating the activation of agents in particular workgroups. A call queue server receives incoming communications. A scheduling server is coupled to the call center server over a network and analyzes historical communication data to calculate a forecasted load for a particular time period. The system uses the forecasted load to create agent schedules for the workgroups for the particular time period. The system programmatically activates and deactivates the agents into and out of the workgroups at scheduled points in time based on the calculated schedules. The call center server routes each of the queued communications to a particular agent that is activated on a particular one of the workgroup.

Abstract: A communication system including a media server through which communication packets are exchanged for recording and monitoring purposes is disclosed. A tap is associated with each communication endpoint allowing for cradle to grave recording of communications despite their subsequent routing or branching. An incoming communication is routed to a first tap and upon selection of a receiving party; the first tap is routed to a second tap which forwards communication packets on to the receiving party. The taps may be used to forward communication packets to any number of other taps or destinations, such as a recording device, monitoring user, or other user in the form of a conference.

Abstract: A communication system including a media server through which communication packets are exchanged for recording and monitoring purposes is disclosed. A tap is associated with each communication endpoint allowing for cradle to grave recording of communications despite their subsequent routing or branching. An incoming communication is routed to a first tap and upon selection of a receiving party; the first tap is routed to a second tap which forwards communication packets on to the receiving party. The taps may be used to forward communication packets to any number of other taps or destinations, such as a recording device, monitoring user, or other user in the form of a conference.

Abstract: A computer system and method is disclosed for automatically establishing a screen sharing session between a first party and a second party based upon device associations. A computer telephony system establishes a telecommunication session between at least a first and second party. The computer telephony system receives a request for a screen sharing session from one party to the telecommunication session. Using a configuration plan, the computer telephony system is able to determine the proper computing devices between which to establish the screen sharing session absent user entry. A screen sharing session is created between the parties of the telecommunication session and optionally tied thereto.

Abstract: A computer-implemented system and method for assisting managers of a contact center is provided. The monitoring of agent communications is performed automatically and the communications are assigned to a group of supervisors for scoring. The scores assigned to the communications are then received and programmatically evaluated against predetermined criteria to determine the quality of the supervisors' performance. If the quality of performance is below an acceptable threshold, then the need for supervisor performance improvement is indicated. In one embodiment, the system automatically schedules a session for establishing/reinforcing a set of scoring guidelines in response to the indication.

Abstract: A computer system and method is disclosed that includes a telephony server that receives a spoken dialing command, sends the command to a speech recognition server, and dials a command based on the result. A computer system and method is disclosed that improves audio message delivery reliability. A computer system and method is disclosed that improves audio message manipulation. A computer system and method is disclosed that manages memory when audio messages are received. A system and method is disclosed that supports multiple speech recognition engines.

Abstract: A system of networked computers is disclosed having a number of servers and a number of clients. The clients are each provided with access to server selector service and the servers are each provided with access to a server reporter service. The server selector service is operable to obtain server processing load information from the server reporter service. The server selector service is responsive to a client activation request for a software task designated for server execution to select two or more servers to interrogate for server processing load information and designate one of the servers to execute the software task based on the server processing load information obtained by this interrogation.

Abstract: A computer system and method is disclosed that includes a call queue server that receives incoming calls and routes the calls to a telephone at the agent's workstation only after the agent accepts the request to take the call. A system and method is disclosed that includes a plurality of call queue servers, a queue monitor server, and a plurality of agent workstations, for distributing calls across multiple call center locations. Each call queue server receiving an incoming call sends a notification to the queue monitor server that in turn notifies each of the remaining call queue servers about the call. Each call queue server is thus able to maintain a current view of all activity across multiple call centers.

Abstract: A unified messaging system is configured to store and retrieve email, facsimile, pager, and voicemail messages. A telephone operated by a person is operatively coupled over a public switched telephone network to the unified messaging system. The system receives over the public switch telephone network a signal from the telephone corresponding to an administer multiple messages command for multiple messages having a common trait. In one form, the multiple messages having the common trait are then deleted from the database in response to this command. In another form, the multiple messages are filed into a folder specified by the person.

Abstract: A system for implementing a technique for operatively integrating an automatic call distributor and an interactive voice response unit is disclosed. Upon receiving and storing an interaction input from a caller seeking information, the automatic call distributor determines the availability of an agent workstation to respond to the interaction input. The interactive voice response unit provides the caller with access to the information when the automatic call distributor determines an agent workstation is unavailable to respond to the interaction input. The automatic call distributor transmits the interaction input to an appropriate agent workstation whenever that particular agent workstation becomes available to respond to the interaction input.

Abstract: A method, apparatus, and system places outbound calls using a predictive dialer at a call center and, optionally, receives inbound calls. The predictive dialing components use information about the substantive stage of the active calls at a given point in time to decide whether to begin to dial another outbound call. The calls that are considered may be inbound or outbound. In one form of the invention, statistics are maintained regarding each agent's passage through the various stages of an active call, then the statistics are used to control the predictive dialer.

Abstract: A novel customer interaction center server, and a novel method of operating a customer interaction center server, are disclosed. In one embodiment, a network of nodes (each representing one or more subsystem processes) and dependency relationships (indicating which processes depend on what other processes) is used to start the server, and the processes are monitored. In some of these embodiments, a failure of a particular process in the set of target processes is detected and logged and/or handled by implementing a selective shutdown and restart of only a subset of the processes represented in the network, based on the dependency information therein.

Abstract: A system for notifying and updating status of selected customer agent includes a customer computer, a computer network, and a customer contact processing computer. The customer contact processing computer is coupled to the customer computer by the computer network. The customer contact processing computer includes a storage unit to store a status indication for each agent. The customer contact processing computer is responsive to an input from the customer computer over the computer network, which corresponds to a selection of at least one of the agents by a customer computer. The customer contact processing computer transmits over the computer network the status indication for the selected agents from the storage unit to the customer computer. The customer contact processing computer updates the status indication transmitted to the customer computer for the agents from time to time.

Abstract: A novel communication distribution system is provided. In one form, an automatic communication distributor manages multiple queues of calls waiting to be handled by agents. When a call is transferred to an agent's workstation, the workstation provides different ringing signals to the agent based on the automatic communication distributor queue from which the call is coming. In another form, a computer-readable medium is encoded with programming instructions that are executable by a processor to differentiate between calls coming from different ACD queues, and to provide different ringing signals to a user based on that differentiation.

Abstract: A system for implementing a telecommunication number processing technique is disclosed. The deployed system, e.g. a call center, comprises a CT server and a telecommunication switch. The deployed system can further comprise a computer network. The CT server receives a telecommunication number input from a telecommunication switch or the computer network. The telecommunication number input represents a telecommunication number to dial a telecommunication call to a telecommunication subscriber located within the system, or an external telephone. In response to the telecommunication number input, the CT server provides a standardized number corresponding to the telecommunication number input. The CT server subsequently provides a dial plan corresponding to the standardized number. The dial plan includes a dial string, a dial group, and a dialing classification.

Abstract: A system of networked computers is disclosed having a number of servers and a number of clients. The clients are each provided with a server selector routine and the servers are each provided with a server reporter routine. The server selector routine of any of the clients is operable to obtain server processing load information from the server reporter routine of any of the servers. The server selector routine is responsive to a client activation request for a software task designated for server execution to select two or more servers to interrogate for server processing load information and designate one of the servers to execute the software task based on the server processing load information obtained by this interrogation.