International Business Machines Corporation

Nuance Communications, Inc.

Jeffrey S Kobal

Girish Dhanakshirur

David E Reich

Bruce D Lucas

Jeffrey Allen Jones

Maximilian Bisani

Dwayne Dames

Olivier Divay

A computer implemented method and system of formatting text output from a speech recognition system is provided. The method includes determining if a user correction to a text output from a speech recognition system can be accomplished by changing a formatting setting associated with the speech recognition system. The formatting setting is changed based on an inferential indication that the change to the formatting setting is acceptable to the user and/or an explicit confirmation from the user that the change to the formatting setting is acceptable.

Text formatter with intuitive customization

A system () for previewing changes to a structured flow diagram is provided. The system includes a user interface () that displays a structured flow diagram according to a predetermined visual format. The system () further includes a preview module () for generating a modified display of a portion of the structured flow diagram displayable with the user interface (). The modified display shows a user-directed modification to the structured flow diagram by displaying the user-directed modification in a different visual format juxtaposed with portions of the structured flow diagram that remain unchanged by the user-directed modification. The modification to the structured flow diagram can thus be previewed prior to determining whether to incorporate the modification into the structured flow diagram if the system user elects to do so.

System and methods for previewing alternative compositions and arrangements when composing a strictly-structured flow diagram

A visual toolkit for prioritizing speech transcription is provided. The toolkit can include a logger () for capturing information from a speech recognition system, a processor () for determining an accuracy rating of the information, and a visual display () for categorizing the information and prioritizing a transcription of the information based on the accuracy rating. The prioritizing identifies spoken utterances having a transcription priority in view of the recognized result. The visual display can include a transcription category () having a modifiable textbox entry with a text entry initially corresponding to a text of the recognized result, and an accept button () for validating a transcription of the recognized result. The categories can be automatically ranked by the accuracy rating in an ordered priority for increasing an efficiency of transcription.

Method and system for automatic transcription prioritization

A visual toolkit for prioritizing speech transcription from a plurality of speech recognition tasks is provided. The toolkit can include a logger () for capturing information from a speech recognition system, a processor () for determining an accuracy rating based at least in part on information that is independent of a confidence score associated with a recognized phrase and independent of confidence scores associated with a plurality of phrases in an N-best match, and a visual display () for categorizing the information and prioritizing a transcription of the information based on the accuracy rating. The prioritizing identifies spoken utterances having a transcription priority in view of the recognized result. The visual display can include a transcription category () having a modifiable textbox entry with a text entry initially corresponding to a text of the recognized result, and an accept button () for validating a transcription of the recognized result. The categories can be automatically ranked by the accuracy rating in an ordered priority for increasing an efficiency of transcription.

A method of verifying a speech input can include determining pronunciation data for a received user spoken utterance specifying a word and speech recognizing further user spoken utterances specifying individual characters of the word. An N-best list can be generated for each received user spoken utterance specifying a character. A grammar can be automatically generated that includes word candidates using the N-best list for each user spoken utterance specifying a character. Pronunciation data for each word in the grammar can be generated automatically. The pronunciation data from the user spoken utterance specifying the word can be compared with pronunciation data for the word candidates of the grammar to determine at least one match.

Using a spoken utterance for disambiguation of spelling inputs into a speech recognition system

A method of generating pronunciation information can include graphically presenting at least one activatable visual identifier corresponding to individual ones of a plurality of phonemes. Responsive to a selection of one of the visual identifiers, pronunciation information can be generated in accordance with the selected visual identifier. The pronunciation information can be compiled responsive to a selection of one of the plurality of visual identifiers.

Method and apparatus for word pronunciation composition

The present system and method improves the way of forwarding a reference from an importing module to an exporting module. The present system and method allow forwarding of a reference(s) through a forwarder exporting module for a specified export(s) when an explicit entrypoint(s) does/do not exist for the specified export(s) in the forwarder exporting module and still allow correlation from the importing module to the exporting module when the loader is loading the importing module during a load time. One or more implicit forwarder record(s) is stored in the exporting module by a linker. Each implicit forwarder record designates a respective target module. The loader determines whether an explicit entrypoint exists in the exporting module for the reference of the specified export. The loader resolves the reference by using the explicit entrypoint to determine a location of the specified export if the explicit entrypoint exists. The loader searches in a defined sequential order for the location of the specified export in a target module designated by a respective implicit forwarder record if the explicit entrypoint does not exist. The loader resolves the reference by using the implicit forwarder record if the specified export is found in a target module.

Growing community of inventors

Lake Worth, FL, United States of America

Jeffrey S Kobal