公开(公告)号：DE10040214B4

公开(公告)日：2006-03-30

申请号：DE10040214

申请日：2000-08-17

Applicant: IBM

Inventor： NASSIFF AMADO ,  ORTEGA KERRY A

IPC: G10L15/00 ,  G10L15/06 ,  G10L15/18

公开(公告)号：DE10040214A1

公开(公告)日：2001-04-19

申请号：DE10040214

申请日：2000-08-17

Applicant: IBM

Inventor： NASSIFF AMADO ,  ORTEGA KERRY A

IPC: G10L15/06 ,  G10L15/18 ,  G10L15/00

Abstract: The computer speech recognition system has each spoken word compared with stored values if identified the word is passed for conversion into digital form. If not alternative word lists are accessed and depending upon the result a correction process is applied.

公开(公告)号：CA2307300C

公开(公告)日：2007-02-06

申请号：CA2307300

申请日：2000-05-01

Applicant: IBM

Inventor： ORTEGA KERRY A ,  LEWIS JAMES R ,  VANBUSKIRK RONALD E ,  KELLER ARTHUR ,  HANSON GARY R ,  BALLARD BARBARA E

IPC: G06F17/27 ,  G10L13/04 ,  G10L15/22

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 marke d 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 ea ch marked textual error reviewed in the reviewing step; and, unmarking each marked textual error corrected by the user in the accepting step. Also, the reviewing step can include highlighting each t he word in the electronic document corresponding to the marked textual error marked in the marking ste p; and, displaying an explanation for each marked textual error in a user interface. Moreover, the reviewing step can further include suggesting a recommended change to the marked textual error; displaying the recommended change in the user interface; and, accepting a user specified preference to substitute the recommended change for the marked textual error.

公开(公告)号：CA2276567C

公开(公告)日：2006-04-11

申请号：CA2276567

申请日：1999-06-29

Applicant: IBM

Inventor： ORTEGA KERRY A

IPC: G06F3/16 ,  G06F17/00 ,  G06F7/00 ,  G06F9/06 ,  G06F17/21 ,  G06F17/22 ,  G10L15/00 ,  G10L21/00

Abstract: A method for creating dictation macros, comprising the steps of: storing a selected text string; displaying a graphical user interface (GUI) for naming a dictation macro responsive to a first user command, the GUI having a section for naming the macro; creating a baseform for a macro name entered into the section of the GUI responsive to a second user command ; and, associating the macro name with the stored selected text string as a the dictation macro. A method for creating dictation macros in a speech application, comprising the steps of: creating a text string; selecting the text string; invoking a first user command for the speech application to create a dictation macro; naming the dictation macro; and, invoking a second user command for the spee ch application to create a baseform for the macro name and associate the macro name with the selected text string as the dictation macro.

公开(公告)号：GB2362745A

公开(公告)日：2001-11-28

申请号：GB0112299

申请日：2001-05-21

Applicant: IBM

Inventor： LEWIS JAMES R ,  ORTEGA KERRY A

IPC: G06F3/16 ,  G10L15/26 ,  H04M3/53 ,  H04M11/10

Abstract: A speaker identification process can identify an enrolled speaker as a source of a computer voice mail message. responsive to the identification of the enrolled speaker, the computer voice mail message can be submitted to a speech conversion process in a speech recognition system. The speech conversion process can perform speech- to-text conversion of the computer voice mail message using speaker enrolment data corresponding to the identified enrolled speaker.