Method and apparatus for improving speech recognition accuracy

• US 6,675,142 B2
• Filed: 09/21/2001
• Issued: 01/06/2004
• Est. Priority Date: 06/30/1999
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Egger, Hans, Ortega, Kerry A., Keller, Arthur, VanBuskirk, Ronald E., Lewis, James R., Wang, Huifang
• Primary Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US09/960,826
• Publication Number:
  US 20020013709A1
• Time in Patent Office: 837 Days
• Field of Search: 704/231, 704/235, 704/246, 704/251, 704/256, 704/270, 704/272, 704/277, 704/278
• 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.

Claims

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

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

monitoring an accuracy of the transcribed speech to determine whether the accuracy of the transcribed speech is sufficient;

automatically activating an interactive speech recognition improvement tool during a dictation session upon determining that the accuracy of the transcribed speech is not sufficient; and

during the dictation session, improving the accuracy of the transcribing step for subsequent transcriptions using the speech recognition improvement tool.

2. The method of claim 1, wherein the step of improving the accuracy of the transcribing step comprises:

identifying a recognition problem type; and

providing, to a user of the speech recognition improvement tool, possible solution steps to resolve the recognition problem type.

3. The method of claim 2, wherein the step of identifying a recognition problem type comprises:

displaying a number of possible recognition problem types to the user; and

receiving input from the user indicating which of the possible recognition problem types the user identifies as the recognition problem type.

4. The method of claim 2, wherein the step of identifying a recognition problem type comprises the step of automatically identifying, by the speech recognition improvement tool, a most likely recognition problem type as the recognition problem type.

5. The method as claimed in claim 2, further comprising:

receiving input from the user that enables the interactive speech recognition improvement tool to adjust parameters in order to improve the accuracy of the transcribing step.

6. The method of claim 2, further comprising:

providing the user with a mini-tutorial in order to help the user solve the recognition problem type.

7. The method of claim 1, further comprising:

alerting a user of the interactive speech recognition improvement tool when the speech recognition improvement tool is automatically activated.

8. The method as claimed in claim 1, further comprising:

determining whether the user would like the transcription system to test the accuracy of the transcribing step; and

if the user would like the transcription system to test the accuracy, receiving and transcribing test input speech from the user.

9. The method of claim 1, further comprising:

determining whether the step of automatically activating the interactive speech recognition improvement tool is disabled; and

if the step of automatically activating the interactive speech recognition improvement tool is disabled, not performing the step of automatically activating.

10. A transcription apparatus for transcribing input speech into text format, the apparatus comprising:

a computer that transcribes a received input speech into transcribed speech and monitors an accuracy of the transcribed speech to determine whether the accuracy of the transcribed speech is sufficient, and that automatically activates an interactive speech recognition improvement tool during a dictation session when the accuracy is not sufficient, and which, during the dictation session, improves the accuracy of the transcribing step for subsequent transcriptions using the interactive speech recognition improvement tool;

a display monitor, coupled to the computer, that displays the transcribed speech; and

a microphone, coupled to the computer, that receives the input speech.

11. A machine-readable storage, having stored thereon a computer program having a plurality of code sections executable by a machine for causing the machine to perform the steps of:

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

monitoring an accuracy of the transcribed speech to determine whether the accuracy of the transcribed speech is sufficient;

automatically activating an interactive speech recognition improvement tool during a dictation session upon a determination that the accuracy of the transcribed speech is not sufficient; and

during the dictation session, improving the accuracy of the transcribing step for subsequent transcriptions using the speech recognition improvement tool.