Method and apparatus for improving speech recognition accuracy

• US 6,370,503 B1
• Filed: 06/30/1999
• Issued: 04/09/2002
• Est. Priority Date: 06/30/1999
• Status: Expired due to Term

• Current Assignee: X Corp. (f/k/a Twitter, Inc.) (X Holdings Corp.)
• Original Assignee: International Business Machines Corporation
• Inventors: Lewis, James R., Egger, Hans, Ortega, Kerry A., Wang, Huifang, Keller, Arthur, Vanbuskirk, Ronald E.
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US09/345,071
• Time in Patent Office: 1,014 Days
• Field of Search: 704/231, 704/235, 704/246, 704/251, 704/256, 704/276
• US Class Current: 704/235
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/0638 Interactive procedures

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. The system also provides the user the ability to test (222) the transcription process in order to determine whether the solution has improved the recognition accuracy.

Claims

1. A method for transcribing speech performed by a transcription system, the method comprising the steps of:

a) receiving input speech;

b) transcribing the input speech into transcribed speech that includes a sequential listing of words in text format;

c) monitoring speech recognition accuracy of the transcribed speech by keeping track of a number of words that fall below a recognition threshold;

d) determining whether the accuracy of the transcribed speech is sufficient;

e) automatically activating a speech recognition improvement tool upon a determination that the accuracy of the transcribed speech is not sufficient; and

f) improving the accuracy of the transcribing step using the speech recognition improvement tool.

2. The method as claimed in claim 1, wherein the step of determining comprises the step of determining that the accuracy is not sufficient if the number of words that fall below the recognition threshold is higher than a pre-defined number.

3. The method as claimed in claim 1, wherein the step of determining comprises the step of determining that the accuracy is not sufficient if the number of words that fall below the recognition threshold is higher than a pre-defined percentage.

4. A method for transcribing speech performed by a transcription system, the method comprising the steps of:

a) receiving input speech;

b) transcribing the input speech into transcribed speech that includes a sequential listing of words in text format;

c) monitoring speech recognition accuracy of the transcribed speech by keeping track of a number of words that are corrected by a user of the transcription system;

d) determining whether the accuracy of the transcribed speech is sufficient;

e) automatically activating a speech recognition improvement tool upon a determination that the accuracy of the transcribed speech is not sufficient; and

f) improving the accuracy of the transcribing step using the speech recognition improvement tool.

5. The method as claimed in claim 4, wherein the step of determining comprises the step of determining that the accuracy is not sufficient if the number of words that are corrected by the user is higher than a pre-defined number.

6. The method as claimed in claim 4, wherein the step of determining comprises the step of determining that the accuracy is not sufficient if the number of words that are corrected by the user is higher than a pre-defined percentage.