Abstract: A method of selecting a language model for decoding received user spoken utterances in a speech recognition system can include a series of steps. The steps can include computing confidence scores for identified closed-class words and computing a running average of the confidence scores for a predetermined number of decoded closed-class words. Additionally, based upon the running average, telegraphic decoding can be selectively enabled.

Abstract: In a speech recognition session, a method of speech processing utilizing a plurality of grammars can include a series of steps. The method can include spawning a separate thread of execution corresponding to each one of a plurality grammars and allocating a post-processing recognition task to each separate thread of execution. Each post-processing recognition task can produce a possible recognition result using the corresponding grammar. A possible recognition result produced by one of the post-processing recognition tasks can be identified.

Abstract: A method of generating language model statistics for a new word added to a language model incorporating at least one class file containing contextually related words. The method can include the following steps: First, language model statistics can be computed based on references to at least one incorporated class file. Second, a new word can be substituted for each reference to a selected class file. Additionally, the language model statistics can be re-computed based on the new word having been substituted for the reference. Third, the re-computed language model statistics can be displayed in a user interface and modifications can be accepted to the re-computed language model statistics through the user interface. Fourth, the language model statistics can be further re-computed based on the modifications. In consequence, the language model statistics are re-computed for the new word without introducing contextual inaccuracies in the language model.

Abstract: A method for enrolling a user in a speech recognition system, without requiring reading, comprises the steps of: generating an audio user interface having an audible output and an audio input; audibly playing a text phrase; audibly prompting the user to speak the played phrase; repeating the steps of audibly prompting the user not to speak, audibly playing the phrase and audibly prompting the user to speak, for a plurality of further phrases; and, processing enrollment of the user based on the audibly prompted and subsequently spoken phrases. A graphical user interface can also be generated for: displaying text corresponding to the phrases and to the audible prompts; displaying a plurality of icons for user activation; and, selectively distinguishing different ones of the icons at different times by at least one of: color; shape; and, animation.

Abstract: A method and system for use with a computer based system having a touchscreen for distinguishing between a finger and a stylus. The method involves a series of steps including detecting contact with the touchscreen. Also, the method can include generating contact information for the detected contact with the touchscreen. The method includes comparing contact information corresponding to the detected contact with contact criteria, and, based on the comparison of the contact information, determining whether the contact was initiated by a finger or a stylus.

Abstract: A method for adjusting a speech menu interface in a speech recognition system. The method can include a series of steps which can include identifying one or more menu items from a data structure in memory for presentation using the speech menu interface. The step of retrieving the one or more menu items from the data structure can be included. Also, the step of reading at least one attribute corresponding to the one or more menu items with menu item criteria can be included. Based on the comparing step, the method can include selecting a presentation style for presentation of the one or more menu items using the speech menu interface.

Abstract: A data recognition system and method which allows a user to select between a “default recognition” mode and a “constrained recognition” mode via a user interface. In the default recognition mode, a recognition engine utilizes predetermined default recognition parameters to decode data (e.g., handwriting and speech). In the constrained recognition mode, the user can select one or more of a plurality of recognition constraints which temporarily modify the default recognition parameters to decode uncharacteristic and/or special data. The recognition parameters associated with the selected constraint enable the recognition engine to utilize specific information to decode the special data, thereby providing increased recognition accuracy.

Abstract: A method and system uses a finite state command grammar coordinated with application scripting to recognize voice command structures for performing an event from an initial location to a new location. The method involves a series of steps, including: recognizing an enabling voice command specifying the event to be performed from the initial location; determining a functional expression for the enabling voice command defined by one or more actions and objects; storing the action and object in a memory location; receiving input specifying the new location; recognizing an activating voice command for performing the event up to the new location; retrieving the stored action and object from the memory location; and performing the event from the initial location to the new location according to the retrieved action and object. Preferably, the enabling-activating command is phrased as “from here . . . to here”.

Abstract: A transcription system (100) includes a computer (102), a monitor (104), and a microphone (110). Via the microphone, a user of the system provides input speech that is received and transcribed (204) by the system. The system monitors (205) the accuracy of the transcribed speech during transcription. The system also determines (210) whether the accuracy of the transcribed speech is sufficient and, if not, automatically activates (214) a speech recognition improvement tool and alerts (212) the user that the tool has been activated. This tool could also be manually activated (206) by the user. The type of recognition problem is identified (216) by the user or automatically by the system, and the system provides (218) possible solution steps for enabling the user to adjust (219) system parameters or modify user behavior in order to alleviate the recognition problem.

Abstract: A dictation system (100) performs a method of dictating speech which automatically activates (502) and deactivates (306, 408, 510) auxiliary topic libraries based on the input speech. After receiving (206) input speech, the method searches (208, 214) a general library and topic libraries that are currently active, if any. The method also searches (220, 226) all or portions of inactive topic libraries. If the spoken word is recognized in a particular inactive topic library, the method automatically activates (502) that topic library. In a preferred embodiment, the method maintains an adjustable “score” for each active topic library. An active library's score is increased (402) each time a word is recognized in the library, and decreased (302, 404, 506) when a word is recognized in another library. If the score falls below a certain threshold, the active topic library is automatically deactivated (306, 408, 510).

Abstract: A method and system for improving the speech command recognition accuracy of a computer speech recognition system uses event-based constraints to recognize a spoken command. The constraints are system states and events, which include system activities, active applications, prior commands and an event queue. The method and system is performed by monitoring events and states of the computer system and receiving a processed command corresponding to the spoken command. The processed command is statistically analyzed in light of the system events and states as well as according to an acoustic model. The system then identifies a recognized command corresponding to the spoken command.

Abstract: A transcription system (100) includes a computer (102), a monitor (104), and a microphone (110). Via the microphone, a user of the system provides input speech that is received and transcribed (204) by the system. The system monitors (205) the accuracy of the transcribed speech during transcription. The system also determines (210) whether the accuracy of the transcribed speech is sufficient and, if not, automatically activates (214) a speech recognition improvement tool and alerts (212) the user that the tool has been activated.

Abstract: A method of proofreading and correcting dictated text contained in an electronic document comprises the steps of: selecting proofreading criteria for identifying textual errors contained in the electronic document; playing back each word contained in the electronic document; and, marking as a textual error each played back word in nonconformity with at least one of the proofreading criteria. The method can further comprise the step of editing each the marked textual error identified in the marking step. In particular, the editing step can include reviewing each the marked textual error identified in the marking step; accepting user specified changes to each marked textual error reviewed in the reviewing step; and, unmarking each marked textual error corrected by the user in the accepting step.

Abstract: A method and a system for use in a computer speech recognition system for adding new vocabulary by using language model statistics corresponding to an existing vocabulary word. The method involves a series of steps including receiving a user input identifying a first word for which no language model statistics exist in the speech recognition system. The first word is for inclusion within the existing vocabulary of the speech recognition system. In response to a second user input identifying a second word for which language model statistics exist in the speech recognition system, recalling from a computer memory the language model statistics for the second word. The speech recognition system then automatically creates language model statistics for the first word by duplicating the language model statistics of the second word and replacing each occurrence of the second word in the duplicated language model statistics with the first word.

Abstract: A data recognition system and method which allows a user to select between a “default recognition” mode and a “constrained recognition” mode via a user interface. In the default recognition mode, a recognition engine utilizes predetermined default recognition parameters to decode data (e.g., handwriting and speech). In the constrained recognition mode, the user can select one or more of a plurality of recognition constraints which temporarily modify the default recognition parameters to decode uncharacteristic and/or special data. The recognition parameters associated with the selected constraint enable the recognition engine to utilize specific information to decode the special data, thereby providing increased recognition accuracy.

Abstract: A method and apparatus for transcribing text from multiple speakers in a computer system having a speech recognition application. The system receives speech from one of a plurality of speakers through a single channel, assigns a speaker ID to the speaker, transcribes the speech into text, and associates the speaker ID with the speech and text. In order to detect a speaker change, the system monitors the speech input through the channel for a speaker change.

Abstract: An efficient method and system, particularly well-suited for correcting natural language understanding (NLU) commands, corrects spoken commands misinterpreted by a speech recognition system. The method involves a series of steps, including: receiving the spoken command from a user; parsing the command to identify a paraphrased command; displaying the paraphrased command; and accepting corrections of the paraphrased command from the user. The paraphrased command is segmented according to command language categories, which include a command action category, an action object category, and an action and/or object modifying category. The paraphrased command is displayed in a user interface window segmented into these command language categories. The user interface window also contains alternative commands for each segment of the paraphrased command.

Abstract: A method for enrolling a user in a speech recognition system, without requiring reading, comprises the steps of: generating an audio user interface having an audible output and an audio input; audibly playing a text phrase; audibly prompting the user to speak the played phrase; repeating the steps of audibly prompting the user not to speak, audibly playing the phrase and audibly prompting the user to speak, for a plurality of further phrases; and, processing enrollment of the user based on the audibly prompted and subsequently spoken phrases. A graphical user interface can also be generated for: displaying text corresponding to the phrases and to the audible prompts; displaying a plurality of icons for user activation; and, selectively distinguishing different ones of the icons at different times by at least one of: color; shape; and, animation.

Abstract: A method and system for responding to randomly occurring noise in a voice recognition application program. The system receives an audio signal representative of sound in an audio environment and processes the audio signal to identify certain non-speech sounds. A pre-defined action is performed in response to the non-speech sound which has been identified. The pre-defined action is selected from the group consisting of disabling a microphone source of the audio signal, suspending further processing of the audio signal by the speech recognition system, executing a user-defined macro, and ignoring the sound. The system may perform additional steps including recording a sound which is to be identified as a non-speech sound and assigning one of the pre-defined actions to be performed in response when the non-speech sound has been identified.

Abstract: In a computer system having a word processing application adapted for speech recognition, a method and system to propagate corrections in dictated text. in response to a first user command, a first error word is selected to be corrected from a word processing file containing dictated text. The error word is replaced by a correct word selected by a user. The system subsequently searches the dictated text contained in the document fie in response to another user command to locate a second or subsequent error word that is a close acoustic match to the first error word. The second or subsequent error word may then be replaced using a word selected from an alternate word list.