Abstract: In one embodiment, the invention provides a method for a speech recognition system to select a return value corresponding to a spoken input. The method comprises generating a dictionary comprising return values associated with data provisioned in the speech recognition system; generating a grammar for each return value in the dictionary; analyzing the grammar to determine a subset of return values from the dictionary that are likely alternatives for each return value in the dictionary, based on the grammar; selecting a return value corresponding to the spoken input based on the grammar; and if the selected return value is not confirmed by a user, then presenting the likely alternative for the selected return value to the user.

Abstract: In one embodiment, the invention provides a method for personalizing a response to an incoming customer communication. The method includes identifying a customer based on an incoming customer communication; selecting a rule applicable to the incoming customer communication, the rule having a destination associated therewith; preparing data to facilitate processing of the incoming customer communication; and routing the call to the destination associated with the selected rule and sending the prepared data to the destination.

Abstract: In one embodiment, the invention provides a method for creating a voice application, the method being implemented by a computer system and comprising generating a graphical user interface comprising a text-to-topic button; receiving first input identifying a location of a text file; receiving second input selecting the text-to-topic button; partitioning content associated with the text file into subjects in response to receiving the second input; and storing information on the partitioning.

Abstract: A method and system for generating a finite state grammar is provided. The method comprises receiving user input of at least two sample phrases; analyzing the sample phrases to determine common words that occur in each of the sample phrases and optional words that occur in only some of the sample phrases; creating a mathematical expression representing the sample phrases, the expression including each word found in the sample phrases and an indication of whether a word is a common word or an optional word; displaying the mathematical expression to a user; allowing the user to alter the mathematical expression; generating a finite state grammar corresponding to the altered mathematical expression; and displaying the finite state grammar to the user.

Abstract: In accordance with one embodiment, a method for operating a telephonic voice content system is provided. The method, comprises in a non-live agent mode, interacting with a caller by receiving an utterance from the caller, performing a machine selection of voice content to play to the caller based on the utterance, and playing the machine-selected voice content to the caller; and upon receiving a request to speak to a live agent from the caller, switching to a live agent mode wherein a live agent holds a conversation with the caller, and selects voice content to play to the caller based on the conversation; and switching to the non-live agent mode and playing the live agent-selected voice content to the caller.

Abstract: In one aspect, the invention provides a method for generating a sales lead for the sale of a CVR system. The method comprises initiating a call in which a human calls an organization and interacts with an interactive voice response (IVR) system that defines an interface to a database for an organization in order to obtain information from the database; generating a first audio file comprising a recording of the interaction; generating a second audio file comprising a recording of an interaction of the caller with a CVR system in order to obtain the same information from the database; presenting the first and second audio files to a decision maker in the organization who has some influence on a decision to purchase the CVR system; tracking when the decision maker accesses the audio files; and initiating contact with the decision maker once access of the audio files is established.

Abstract: In one embodiment, the invention provides a method for a speech recognition system to select a return value corresponding to a spoken input. The method comprises generating a dictionary comprising return values associated with data provisioned in the speech recognition system; generating a grammar for each return value in the dictionary; analyzing the grammar to determine a subset of return values from the dictionary that are likely alternatives for each return value in the dictionary, based on the grammar; selecting a return value corresponding to the spoken input based on the grammar; and if the selected return value is not confirmed by a user, then presenting the likely alternative for the selected return value to the user.