Method and system for performing text edits during audio recording playback

• US 6,360,237 B1
• Filed: 10/05/1998
• Issued: 03/19/2002
• Est. Priority Date: 10/05/1998
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Lernout & Hauspie Speech Products NV (Intel Corporation)
• Inventors: Crovitz, Michael D., Schulz, David E., Wightman, Colin W.
• Primary Examiner(s): Hong, Stephen S.
• Assistant Examiner(s): HUYNH, CONG LAC T
• Application Number:
  US09/166,363
• Time in Patent Office: 1,261 Days
• Field of Search: 707/531, 707/530, 704/231, 704/246
• US Class Current: 715/255
• CPC Class Codes: G06F 40/166 Editing, e.g. inserting or deleting
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/225 Feedback of the input speech

Abstract

A method for editing written text in a text editor which automatically aligns a cursor in the written text on a screen with a particular spoken word during playback of an audio recording. The method may comprise aligning the cursor in a targeted insertion point in response to a user'"'"'s input, performing one or more editing functions at the targeted insertion point, and realigning the cursor with the spoken words.

Claims

1. A method for editing written text in a text editor which automatically aligns a cursor in the written text on a screen with a particular spoken word during playback of an audio recording, the method comprising:

(a) aligning the cursor to a targeted insertion point in response to a user'"'"'s input and a reaction time variable so that the insertion point lags behind the playback by a reaction time that allows the user to respond to the spoken word and input an editing function instruction for the text word that corresponds to the spoken word;

(b) performing the input editing function at the targeted insertion point; and

(c) realigning the cursor with the spoken words, delaying by the reaction time variable so that the insertion point lags behind the playback by the reaction time.

2. The method of claim 1 wherein the act of aligning further comprises:

(i) determining whether the targeted insertion point is an appropriate insertion point for one or more text edits, and

(ii) adjusting the cursor location to an appropriate insertion point if the targeted insertion point is inappropriate.

3. The method of claim 2 further comprising refreshing the screen after the act of performing.

4. The method of claim 1 wherein the act of adjusting further comprises computing the reaction time variable as a function of a rate of speech in the audio recording.

5. The method of claim 1 further comprising performing full word-level speech recognition to produce a draft of the written text prior to steps (a) through (c).

6. The method of claim 1 further comprising stopping playback of the audio recording in response to a quit command from a user.

7. The method of claim 6 further comprising reverting to a standard text editor.

8. The method of claim 1 further comprising determining whether one or more edits are appropriate and performing one or more edits only if appropriate.

9. The method of claim 8 wherein the act of determining further comprises evaluating the context of words to determine whether one or more edits are appropriate.

10. The method of claim 9 wherein the act of evaluating comprises ensuring that one or more words that are at the targeted insertion point that are a preposition, article, or conjunction are not a final word in a sentence.

11. An apparatus for editing written text comprising:

(a) a text editor that automatically aligns a cursor in the written text with a particular spoken word during playback of an audio recording; and

(b) software containing instructions to;

(i) align the cursor to a targeted insertion point in response to a user'"'"'s input and a reaction time variable so that the insertion point lags behind the playback by a reaction time that allows the user to respond to the spoken word and input an editing function instruction for the text word that corresponds to the spoken word,

(ii) perform the input editing function at the targeted insertion point, and

(iii) realign the cursor with the spoken words, delaying by the reaction time variable so that the insertion point lags behind the playback by the reaction time.

12. The apparatus of claim 11 wherein the software further contains instructions to determine whether the targeted insertion point is an appropriate insertion point for one or more text edits and to adjust the cursor location to an appropriate insertion point if the targeted insertion point is inappropriate.

13. The apparatus of claim 12 further comprising a speech recognition unit to perform full word-level recognition and produce a draft of the written text.