Abstract: A computer-implemented method is described for optimizing prompts for a speech-enabled application. The speech-enabled application is operable to receive communications from a number of users and communicate one or more prompts to each user to elicit a response from the user that indicates the purpose of the user's communication. The method includes determining a number of prompt alternatives (each including one or more prompts) to evaluate and determining an evaluation period for each prompt alternative. The method also includes automatically presenting each prompt alternative to users during the associated evaluation period and automatically recording the results of user responses to each prompt alternative. Furthermore, the method includes automatically analyzing the recorded results for each prompt alternative based on one or more performance criteria and automatically implementing one of the prompt alternatives based on the analysis of the recorded results.

Abstract: A method and system for an automated departure strategy from an automated system includes a track engine and an error engine. The track engine allows for the tracking and storing of one or more utterances spoken by a caller in response to one or more prompts. In addition, the track engine classifies each of the utterances with a confidence level. The error engine determines when one of the utterances initiates an error condition and transfers the caller to an operator on the occurrence of the error condition. In addition to transferring the caller to the operator, the error engine plays to the operator an error utterance, causing the error condition, and a preceding utterance, preceding the error utterance. Furthermore, the error engine populates an operator screen with information provided by the caller in the utterances for utterances classified with a high level of confidence.

Abstract: A method and system for automating customer slamming and cramming complaints includes an automated reporting system having one or more receiving devices and a complaint module. Customers who want to report a slam or cram access the automated reporting system and report the complaint without having to speak with a customer service representative. The complaint module obtains the customer telephone number and retrieves customer account information using the customer telephone number. Using the customer account information, the complaint module extrapolates a type of complaint for the customer complaint and prompts the customer for information regarding the customer complaint and the type of the complaint. The customer provides customer responses to the prompts and the complaint module provides an indication to the customer regarding each customer response.

Abstract: A method of providing a caller with a directory assistance dialog. The dialog is configurable, at any level of the dialog, from an automated speech recognition (ASR) dialog to an operator-assisted (OP) dialog. The dialog is handed off to an operator if any level of the speech recognition dialog fails. Also, a configuration switch may be set to cause the dialog to be handed off to an operator even if a response at some level of the ASR dialog is successfully recognized.

Abstract: A method of designing an interface system that allows users to map the representation of their task directly to the interface. There are three major phases to the Customer-Centric Approach to Interface Design (C-CAID). End-users' tasks are categorized to determine the frequency of reasons or tasks of why users interact with a particular system. These reasons and their relative frequencies are used to design interface options that emphasize the user's task categories. Finally, the customer-centric interface designs are evaluated and compared with existing system interfaces using usability tests with actual users performing the tasks. The results from usability tests are used to pinpoint the task-option combinations that do not work well and which should be revised. Benefits of this customer-centric design are improved systems performance and increased user satisfaction.

Abstract: Systems and methods for processing speech are provided. A system may include an acoustic model to transform speech input into one or more word strings. The system may also include a semantic model to convert each of the one or more word strings into a detected object and a detected action. The system may also include a synonym table to determine a preferred object based on the detected object and to determine a preferred action based on the detected action.

Abstract: A computer-implemented method is described for optimizing prompts for a speech-enabled application. The speech-enabled application is operable to receive communications from a number of users and communicate one or more prompts to each user to illicit a response from the user that indicates the purpose of the user's communication. The method includes determining a number of prompt alternatives (each including one or more prompts) to evaluate and determining an evaluation period for each prompt alternative. The method also includes automatically presenting each prompt alternative to users during the associated evaluation period and automatically recording the results of user responses to each prompt alternative. Furthermore, the method includes automatically analyzing the recorded results for each prompt alternative based on one or more performance criteria and automatically implementing one of the prompt alternatives based on the analysis of the recorded results.

Abstract: A computer-implemented method is described for optimizing prompts for a speech-enabled application. The speech-enabled application is operable to receive communications from a number of users and communicate one or more prompts to each user to illicit a response from the user that indicates the purpose of the user's communication. The method includes determining a number of prompt alternatives (each including one or more prompts) to evaluate and determining an evaluation period for each prompt alternative. The method also includes automatically presenting each prompt alternative to users during the associated evaluation period and automatically recording the results of user responses to each prompt alternative. Furthermore, the method includes automatically analyzing the recorded results for each prompt alternative based on one or more performance criteria and automatically implementing one of the prompt alternatives based on the analysis of the recorded results.

Abstract: A method and system for automating the analysis of performance data includes an analysis system automatically analyzing a plurality of performance data sets, a task engine, and a score engine. The task engine allows for the matching of each performance data set with an assigned task for each performance data set and the retrieval of a correct key sequence for each performance data set. The score engine compares the correct key sequence with a recorded key sequence of the performance data set to determine if the assigned task is successfully accomplished. The score engine further calculates one or more response times for each performance data set. The automated analysis of performance data allows for a cost savings, more efficient use of time, and more reliable and consistent performance data analysis results.

Abstract: A method, software and system of developing personalities for interactive and/or automated call center applications are provided. According to teachings of the present invention, sample population questionnaires and interviews may be used to identify key personality traits. The impact of the identified key personality traits are then empirically determined. Based on the empirical determination of the key personality traits' impact on customer satisfaction, a plurality of personality profiles may be generated for evaluation. A plurality of application types and voice talents may then be employed to evaluate the impact of each personality profile on customer satisfaction, for different user populations and different types of automated systems. The personality traits for each automated system are preferably rated and reviewed to ensure a system accurately represents the identified key personality traits.

Abstract: A method, software and system of developing personalities for interactive and/or automated call center applications are provided. According to teachings of the present invention, sample population questionnaires and interviews may be used to identify key personality traits. The impact of the identified key personality traits are then empirically determined. Based on the empirical determination of the key personality traits' impact on customer satisfaction, a plurality of personality profiles may be generated for evaluation. A plurality of application types and voice talents may then be employed to evaluate the impact of each personality profile on customer satisfaction, for different user populations and different types of automated systems. The personality traits for each automated system are preferably rated and reviewed to ensure a system accurately represents the identified key personality traits.

Abstract: A method of designing a customer interface for a service center, such as an automated speech recognition (ASR) self-service center. Customer activity to an existing service center is monitored, providing customer model, which includes a collection of customer tasks. These tasks are assigned to action-object pairs, which are further assigned to routing destinations. Dialog modules are designed, based on the customer model data, including disambiguation dialogs.

Abstract: A method and system for an automated departure strategy from an automated system includes a track engine and an error engine. The track engine allows for the tracking and storing of one or more utterances spoken by a caller in response to one or more prompts. In addition, the track engine classifies each of the utterances with a confidence level. The error engine determines when one of the utterances initiates an error condition and transfers the caller to an operator on the occurrence of the error condition. In addition to transferring the caller to the operator, the error engine plays to the operator an error utterance, causing the error condition, and a preceding utterance, preceding the error utterance. Furthermore, the error engine populates an operator screen with information provided by the caller in the utterances for utterances classified with a high level of confidence.

Abstract: An interface is provided by creating prompts for the interface. The prompts represent tasks to be accomplished by a user and are obtained based on user input. The prompts are grouped according to relationships, obtained from the user input, among the tasks. The interface is updated based on user feedback. Each of the prompts is designated using user terminology obtained from the user input.

Abstract: A method of designing a customer interface for a service center, such as an automated speech recognition (ASR) self-service center. Customer activity to an existing service center is monitored, providing customer model, which includes a collection of customer tasks. These tasks are assigned to action-object pairs, which are further assigned to routing destinations. Dialog modules are designed, based on the customer model data, including disambiguation dialogs.

Abstract: A system and method for providing customer activities while in queue allows for one or more customers to interact with one or more customer activities while waiting to speak with a live agent. The customers engage the customer activities while holding in a queue where the customer activities reduce the boredom, frustration, and perceived hold duration associated with holding to speak to a live agent. The customers are offered one or more options of the customer activities to interact with and the system and method monitors the customers' selections and interaction with the customer activities. As agents become available, each customer is transferred to an agent along with information regarding the customer's interaction with a selected customer activity. Upon completion of the interaction between the agent and the customer, the customer has the option to return to the selected customer activity and continue interacting with the selected customer activity.

Abstract: A system, method and software for facilitating a speech-enabled call routing application using an action-object matrix is disclosed. In operation, a natural language user utterance may be evaluated to identify an action and object available in an action-object matrix indicating transactions or operations available to a user. Depending upon the contents of the natural language user utterance, additional prompts and/or a disambiguation dialogue may be effected to elicit an available action-object combination selection from the user. Following identification of an action-object combination from the natural language user utterance, the action-object matrix may cooperate with a look-up table to identify an appropriate use routing destination. Following identification of an appropriate routing destination, the user connection may be routed to a service agent or module configured to facilitate the user selected transaction as indicated by the action-object combination.

Abstract: A method and system for an automated departure strategy from an automated system includes a track engine and an error engine. The track engine allows for the tracking and storing of one or more utterances spoken by a caller in response to one or more prompts. In addition, the track engine classifies each of the utterances with a confidence level. The error engine determines when one of the utterances initiates an error condition and transfers the caller to an operator on the occurrence of the error condition. In addition to transferring the caller to the operator, the error engine plays to the operator an error utterance, causing the error condition, and a preceding utterance, preceding the error utterance. Furthermore, the error engine populates an operator screen with information provided by the caller in the utterances for utterances classified with a high level of confidence.

Abstract: In a disclosed method for interpreting automatic speech recognition (ASR) performance data, a data processing system may receive user input that selects a log file to be processed. The log file may contain log records produced by an ASR system as a result of verbal interaction between an individual and the ASR system. In response to receiving the user input, the data processing system may automatically interpret data in the log records and generate interpretation results. The interpretation results may include a duration for a system prompt communicated to the individual by the ASR system, a user response to the system prompt, and a duration for the user response. The user response may include a textual representation of a verbal response from the individual, obtained through ASR. The interpretation results may also include an overall duration for the telephone call.

Abstract: A system and method for providing customer activities while in queue allows for one or more customers to interact with one or more customer activities while waiting to speak with a live agent. The customers engage the customer activities while holding in a queue where the customer activities reduce the boredom, frustration, and perceived hold duration associated with holding to speak to a live agent. The customers are offered one or more options of the customer activities to interact with and the system and method monitors the customers' selections and interaction with the customer activities. As agents become available, each customer is transferred to an agent along with information regarding the customer's interaction with a selected customer activity. Upon completion of the interaction between the agent and the customer, the customer has the option to return to the selected customer activity and continue interacting with the selected customer activity.