Apparatuses and method for training and operating speech recognition systems

• US 6,092,043 A
• Filed: 06/26/1997
• Issued: 07/18/2000
• Est. Priority Date: 11/13/1992
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Dragon Systems, Inc. (Microsoft Corporation)
• Inventors: Heitman, Peter S., McGrath, Frank J., Parke, Joel W., Squires, Steven D.
• Primary Examiner(s): Dorvil, Richemond
• Application Number:
  US08/882,920
• Time in Patent Office: 1,118 Days
• Field of Search: 704/251, 704/252, 704/253, 704/231, 704/270, 704/275, 704/243, 704/244, 704/255
• US Class Current: 704/251
• CPC Class Codes: G09B 19/04 Speaking with audible presentation of the material to be studied G09B5/04
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/0631 Creating reference templates; Clustering
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A word recognition system can: respond to the input of a character string from a user by limiting the words it will recognize to words having a related, but not necessarily the same, string, score signals generated after a user has been prompted to generate a given word against words other than the prompted word to determine if the signal should be used to train the prompted word; vary the number of signals a user is prompted to generate to train a given word as a function of how well the training signals score against each other or prior models for the prompted word; create a new acoustic model of a phrase by concatenating prior acoustic models of the words in the phrase; obtain information from another program running on the same computer, such as its commands or the context of text being entered into it, and use that information to vary which words it can recognize; determine which program unit, such as an application program or dialog box, currently has input focus on its computer and create a vocabulary state associated with that program unit into which vocabulary words which will be made active when that program group has the focus can be put; detect the available computational resources and alter the instructions it executes in response; test if its ability to respond to voice input has been shut off without user confirmation, and, if so, turn that ability back on and prompt the user to confirm if that ability is to be turned off; store both a first and a second set of models for individual vocabulary words and enable a user to selectively cause the recognizer to disregard the second set of models for a selected word; and/or score a signal representing a given word against models for that word from different word model sets to select which model should be used for future recognition.

Claims

1. A computerized method of performing word recognition designed to operate on a computer system which can run multiple program units at one time and which can selectively give one of those program units an input focus, that is, the ability to receive certain user input, said computerized method comprising the steps of:

receiving user generated word signals representing words to be recognized;

storing a plurality of vocabulary words, and storing a plurality of vocabulary states with which one or more vocabulary words can be associated;

enabling a user to selectively add one or more vocabulary words to a vocabulary state;

defining a set of one or more vocabulary states which are active at a given time;

associating each of one or more of said vocabulary states with a corresponding ones of said program unit;

performing pattern matching upon the word signals to select which one or more of a plurality of vocabulary words associated with the set of currently active vocabulary states most probably correspond to each such word signal;

determining which program unit, if any, running on said computer system currently has the input focus; and

determining whether or not the program unit having the input focus has a vocabulary state associated with it, and if so adding that vocabulary state to the set of active vocabulary states, and if not creating a new vocabulary state and associating it with the program unit which has the input focus.

2. A computerized method as in claim 1 wherein:

said receiving of user generated word signals includes receiving acoustic word signals representing the sounds of spoken words; and

said pattern matching performs speech recognition upon such acoustic word signals.

3. A computerized method as in claim 1 wherein said step of determining which program unit, if any, has the input focus includes determining which application program, if any, has the input focus.

4. A computerized method as in claim 1 wherein said step of determining which program unit, if any, has the input focus includes determining which dialog box, if any, has the input focus.

5. A computerized method as in claim 1 further including the step of determining whether or not to stop storaging a vocabulary state created for a program unit which has had the input focus as a function of whether or not the user has added a vocabulary word to that state.