Method for processing the output of a speech recognizer

A method, comprising:

• hosting, in an automated data processing system, at least one virtual workspace configured to support instances of a virtual processing environment;
• processing the received input within alternate concurrent instances of the virtual processing environment executing on at least one automated data processing system;
• automatically communicating, between respective alternate instances of the virtual processing environment, at least one status message to coordinate a reduction in a number of the alternate instances of the virtual processing environment;
• analyzing a completeness and unambiguity of the received input with respect to an ability to at least partially process a human-initiated command;
• if the received input is complete and unambiguous with respect to the ability to at least partially process the human initiated command, commencing processing;
• if the received input is incomplete or ambiguous with respect to the ability to at least partially process the human initiated command, prompting for additional input, by formulating a question to prompt the user, the answer to which is predicted to increase a statistical reliability of a correspondence to the at least one predetermined grammar, wherein the determination of the statistical reliability of the correspondence of the received input to the at least one predetermined grammar comprises a determination of a statistical reliability of a correspondence of the received input to each of a plurality of grammars corresponding to a predetermined plurality of available commands, and a determination of whether a single unambiguous predetermined available is indicated by the received input;
• and
• analyze the received input for presence of a human-initiated abort command, and cease the analysis upon recognition of the abort command.

A method for processing speech, comprising:

• receiving speech as an input;
• processing the received speech within alternate concurrent instances of a virtual processing environment executing on at least one automated data processing system;
• automatically communicating, between respective alternate instances of the virtual processing environment, at least one status message to coordinate a reduction in a number of the alternate instances of the virtual processing environment;
• analyzing:
• (1) the received speech to determine a command;
• (2) the received speech to determine data associated with the command;
• (3) a completeness and unambiguity of the received speech with respect to an ability to execute the command;
• and
• if the received speech is complete and unambiguous with respect to the ability to execute the command, executing the command, within at least one virtual processing environment, in conjunction with data associated with the command, and
• if the received speech is incomplete or ambiguous with respect to the ability to execute the command, prompting for additional input.