Abstract: In a text-to-speech system, a method of converting text-to-speech can include receiving a text input and comparing the received text input to at least one entry in a text-to-speech cache memory. Each entry in the text-to-speech cache memory can specify a corresponding spoken output. If the text input matches one of the entries in the text-to-speech cache memory, the cached speech output specified by the matching entry can be provided.

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 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 method and system for correcting misrecognized phrases in a computer speech recognition system prevents prior misrecognized text phrases from reoccurring during re-dictation. In particular, the present invention provides a method for correcting a user identified misrecognized text at a location in a dictated electronic document. The method includes: receiving dictation from a user; processing the user input to identify a plurality of alternate text selections; excluding the misrecognized text from the plurality of alternate text selections; and replacing it with a replacement text. These steps are repeated each time the user selects and re-dictates text at the location of the misrecognized text.

Abstract: A method for automatically analyzing a document in a speech recognition system having a vocabulary and language model can include the steps of: determining whether the document has undergone previous analysis; undoing the previous analysis; and, analyzing the document. More specifically, the determining step comprises the steps of: comparing trigrams in the document with trigrams in the language model; and, setting a reference point containing document data for undoing a previous analysis in the undoing step if the compared language model contains all the document trigrams. Moreover, the undoing step comprises the step of removing from the language model each trigram contained in the document data in the reference point.

Abstract: A method for supporting customized tokenization of domain-specific text acomprises the steps of: loading domain-specific tokenization rules corresponding to the customized tokenization of the domain-specific text; tokenizing the domain-specific text using the loaded domain-specific tokenization rules; and, further tokenizing the domain-specific text using general purpose tokenization rules. The loading step of the inventive method can comprise: loading a speech recognition vocabulary; and, loading domain-specific tokenization rules corresponding to the speech recognition vocabulary. In addition, the tokenizing step can comprise identifying each substring in the domain-specific text matching a regular expression having a corresponding replacement pattern in the loaded domain-specific tokenization rules, and replacing each substring identified in the identifying step with the replacement pattern corresponding to the matched regular expression.

Abstract: A system and method is delineated for dictating a body of text in response to an available body of text. In the preferred embodiment, the available body of text comprises only the textual body in plain format from a received E-mail message, while the responsive body of text preferably comprises a dictated E-mail response. Each word from the selected text of the received E-mail message is compared against the speech recognition system's vocabulary to determine whether any words are out-of-vocabulary. Out-of-vocabulary words and their pronunciations are added to the system vocabulary. Similarly, new context information is extracted from the selected text of the received E-mail message, and used to update the system's language model. Thereafter, the user more accurately and efficiently dictates the responsive E-mail, and the system removes the updates to the system vocabulary and language model.