Abstract: A method and system efficiently identifies voice commands for a user of a speech recognition system. The method involves a series of steps including: receiving input from a user; monitoring the computer system to log system events and ascertain a current system state; predicting a probable next event according to the current system state and logged events; and identifying acceptable voice commands to perform the next event. The system events include commands, system control activities, timed activities, and application activation. These events are statistically analyzed in light of the current system state to determine the probable next event. The voice commands for performing the probable next event are displayed to the user.

Abstract: A method for automatically generating a minimal set of test phrases for testing a natural commands grammar includes the steps of selecting a line of text in the natural commands grammar; forming a test phrase for the selected line of text; detecting a previous inclusion of the test phrase in the minimal set of test phrases; and, adding the test phrase to the minimal set of test phrases only if the test phrase has not been detected as having been previously included in the minimal set of test phrases in the detecting step.

Abstract: Sample text is evaluated to determine if it is suitable for updating a language file in a computer speech recognition system. The evaluation is performed by retrieving from a memory a sample text file containing text and a function word file containing a list of function words. The sample text file is processed to determine a total number of words it contains and a total number of function words it contains. A ratio is calculated for the total number of function words relative to the total number of words. Based upon the value of the ratio thus calculated a decision can then be made as to whether to update a language model.

Abstract: A method for correcting errors of a speech recognition application in natural speech recognition of words or phrases represented by characters can include the steps of selecting a character corresponding to an incorrectly recognized spoken word or phrase and observing a list of alternative characters. The method also can include replacing the incorrect character with one of the alternative characters, if the alternative characters correctly represent the incorrectly recognized word or phrase. If none of the alternative characters in the list correctly represents the spoken word or phrase, the step of drawing some features of a character correctly representing the incorrectly recognized word or phrase by moving a cursor can be included. Also included in the method can be the step of updating the list of alternative characters responsive to the drawing step; and, repeating the replacing, drawing and updating steps until a character correctly representing the word or phrase is selected from the updated list.

Abstract: In a computer speech dictation system, a method and system for automatically determining whether to update a language model based upon user amendments to text in a dictated word processing document. The method includes the steps of monitoring a user's text-amending input to an application program for amending the dictated text and subsequently performing processing responsive to the monitoring step to determine whether the text-amending input corrects a misrecognized word in the dictated text. If the test amending input corrects a misrecognized word, the system updates a language model based upon the text which has been amended.

Abstract: A method for managing a What Can I Say (WCIS) function in an application having a plurality of commands which can be voice activated comprises the steps of: storing a set of substantially all voice activatable commands associated with the application; identifying those of the commands in the set which are displayable by the application; and, in response to a user input, displaying in a graphical user interface (GUI) a subset of the voice activatable commands which are not displayable by the application. Moreover, the method includes displaying in the GUI, in response to a user input, a list of the stored set of substantially all voice activatable commands associated with the application; displaying in the GUI a pull down menu identifying different categories by which the commands can be viewed in the list; and, displaying the GUI with a pull down menu identifying commands that can be performed against a voice command.

Abstract: A method for updating a language model in a speech application during a correction session comprises the steps of: automatically acoustically comparing to one another audio of originally dictated text and audio for replacement text; and, automatically updating the language model with a correction if the acoustical comparison is close enough to indicate that the new audio represents correction of a misrecognition error rather than an edit, whereby the language model can be updated without user interaction. The updating step can comprise adding new words to a vocabulary in the speech application.

Abstract: A method for reconciling pronunciation differences between respective vocabularies of recognition and text to speech (TTS) engines in a speech application, first compares respective pronunciations of each word in the recognition engine's vocabulary with each word's pronunciation by the TTS engine, second, for each word for which the pronunciations are different, the recognition engine's pronunciation of the different word is added to an exception dictionary of the TTS engine. Before adding the recognition engine's pronunciation of the different word to the exception dictionary, each different word is tested for form consistent with the exception dictionary. Each different word which is not consistent in form with the exception dictionary is converted to a suitable form prior to being added to the exception dictionary. The pronunciations are compared by comparing baseforms of the pronunciations.

Abstract: A method for programming a grammar code for a speech-enabled computer program, comprising the steps of: enabling a plurality of natural command grammars containing respective representations of valid expressions for said speech-enabled computer program; providing as one of said valid expressions a plurality of ordered words virtually certain not to be uttered by someone not already aware of said plurality of ordered words; and, causing said program to automatically initiate a perceptible action in response to recognition of said plurality of ordered words. The method can further comprise the step of providing translation rules for said plurality of command grammars, wherein speech recognition of said plurality of ordered words invokes one of said translation rules, said invoked one of said translation rules initiating said perceptible action. The action can be activation of a predetermined printer function, displaying a predetermined message on a display device and printing a predetermined message.

Abstract: A method for proofreading text generated by a speech application can include the following steps beginning with the step of finding all closed-class vocabulary words in the text. Subsequently, the method can include the step of automatically highlighting at least some of the closed-class vocabulary words in the text during proofreading. Additionally, the highlighting of the closed-class vocabulary words can include either highlighting all of the closed-class vocabulary words, highlighting the closed-class vocabulary words based on a perplexity filter, or highlighting the closed-class vocabulary words based on a language model enhancement filter.

Abstract: A multiple function graphical user interface for a speech recognition application adapted for generation by a computer programmed with a routine set of instructions, the interface comprising: an activatable icon defining an elongated screen display area, the icon having separately controllable foreground and background displays substantially coextensive with the display area; the background display being substantially fully changeable in response to user speech into a microphone having at least two states; text being displayable in the foreground display across substantially all of the display area; and, activation of the icon invoking a function related to the speech recognition application. A border can be selectively displayed around the elongated screen display area for indicating whether the speech application is in a navigation mode or a dictation mode.

Abstract: The invention provides a method for a speech application to read dictated text back to the user. As playback of dictated audio runs, the application searches ahead for words unassociated with the dictated audio. When the application encounters words unassociated with the dictated audio, the application sends the words to a Text-To-Speech engine to synthesize a spoken instance of each word. This method enhance the user's review of the effectiveness of the dictated text by providing an opportunity for the user to hear the entire document played back both the text that was dictated and the text that was typed.

Abstract: A method for correcting frequently misrecognized words and commands in a speech application. According to the method, when a need for correcting a frequently misrecognized word/command spoken by a user is detected, a recording is made of the misrecognized word/command in isolation. Subsequently, an in-isolation base form for the misrecognized word/command is established from the in-isolation recording. The in-isolation base form is then saved and the misrecognized word/command in recorded in context. Next, an in-context base form is established for the misrecognized word/command from the context recording and a comparison is made between the in-isolation and in-context base forms. The in-context base form is saved only if the in-isolation and in-context base forms are markedly different from one another. A sentence is displayed using the frequently misrecognized word/command in context and the user is prompted to speak the sentence.

Abstract: An option attach connector has a first indicator bit combination that alerts the device that a public switched telephone network connection has been made to it. The presence of the first indicator bit combination is a signal to the device that telephone, FAX, and E-mail communications applications are to be conducted over a PSTN link. The presence of the first indicator bit combination invokes the stored computer program to display images of menus, keypads, and visual presentations on the LCD display that are consistent with a basic display layout for both cellular telephone network and PSTN modes, but that include customized presentation features that are unique to the PSTN mode of communications.

Abstract: A mobile, hand-held personal communicator includes a casing for housing a cellular phone, modem, and data processing system. Graphics image files are stored and can be selectively displayed on a touchscreen display. A zoom function magnifies areas of a graphics image, such as a fax image, that has been received and stored in the PC. When the zoom function is selected, the user touches the screen, and a magnification frame or window appears. When the user removes his/her finger, the area within the frame is magnified. The user can also drag the frame around the screen, while still touching the screen, to select a specific area to be magnified when the user releases the screen. A pan function allows the user to shift the image within a viewing area. The user can pan the image by touching the display at an initial touch point, and moving his/her finger keeping it in contact with the screen, to shift the touch point to a new touch point.

Abstract: An option attach connector has a first indicator bit combination that alerts the device that a public switched telephone network connection has been made to it. The presence of the first indicator bit combination is a signal to the device that telephone, FAX, and E-MAIL communications applications are to be conducted over a PSTN link. The presence of the first indicator bit combination invokes a stored computer program to provide appropriate connections between the PSTN link and the telephone, FAX, and modem hardware in the device. The connections are made by an audio multiplexer that receives control signals from the system CPU, while executing the stored computer program. The program determines the communications application selected by the user and selectively configures the PSTN link to be connected to the either the ear piece and microphone for voice communications, or to the FAX/modem for FAX communications, or to the modem alone for E-MAIL communications.

Abstract: A radio telephone which communicates via cellular telephone networks and by direct connection to a PSTN. The radio telephone includes a random access memory for storing a character string comprising dialing digits defining a calling number and DTMF digits representing signalling tones for accessing information to called equipment. The character string includes a delimiting character for separating dialed digits and DTMF digits. In a dialing sequence, the cellular radio will dial numbers defined by the dial digits and send the remaining characters as DTMF tones to connected telephone.

Abstract: A personal communicator has a touch sensitive overlay coupled with a liquid crystal display (LCD). The communicator has two external (non-screen) up/down buttons for adjusting the volume of a cellular phone speaker. These volume buttons are also used to allow the user to adjust contrast. In accordance with one operation, contrast is adjusted in response to the user touching a predetermined area of the screen at the same time as one of the up or down buttons is actuated. In accordance with another operation, contrast is adjusted in response to the user first pressing both speaker volume buttons to enter a contrast adjustment mode, and thereafter pressing one or the other of such buttons, to increase or decrease contrast as desired.

Abstract: A maintenance-free valve for impeding the flow of fibers in a high velocity air-fiber stream. The valve has a rake-like construction to impede fiber flow when in the closed position. The valve has a plurality of closely-spaced, parallel tines attached to a rotatable shaft that is perpendicular to the tines. When closed, fibers collect on the tines of the rake valve, blinding the valve to further fiber flow. When opened, the fibers are dislodged from the tines such that they re-enter the air-fiber stream.

Abstract: A portable ash auger including a heat and fire resistant housing with an attached handle and with a fireproof tube that opens into and projects from the housing while surrounding an auger having a tip end extending beyond the tube and drive means for the auger.