Method of and system for transcribing dictations in text files and for revising the text

• US 7,184,956 B2
• Filed: 10/28/2002
• Issued: 02/27/2007
• Est. Priority Date: 10/31/2001
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Frimpong-Ansah, Kwaku
• Primary Examiner(s): {hacek over (S)}mits; Talivaldis Ivars
• Assistant Examiner(s): Ng; Eunice
• Application Number:
  US10/281,694
• Publication Number:
  US 20030083885A1
• Time in Patent Office: 1,583 Days
• Field of Search: 704/235
• US Class Current: 704/235
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/0631 Creating reference templates; Clustering

Abstract

The invention relates to a method and a transcription system (T) for transcribing dictations, in which a dictation file (5) is converted into a text file (8), and subsequently the text file (8) is compared with the dictation file (5). To increase the speed for the subsequent correction, provision is made that during transcription of the dictation file (5) a confidence value is generated for a transcribed text passage of the text file (8), and a comparison of the text file (8) with the dictation file (5) takes place only in respect of those text passages for which the confidence value of the text passage is below a confidence limit, i.e. a text passage recognized as possibly defective is present.

Claims

1. A method for transcribing dictations comprising the steps of:

converting a dictation file (5) into a text file (8) with text passages (W(n)),

generating a respective confidence value during the conversion to converted text passages (W(n)),

comparing the text file (8) with the dictation file (5) only in the case of those text passages (W(n)) for which the confidence value is below a confidence limit (C_G) , i.e. where possibly defective text passages (W(n)) are present; and

altering a playback speed for the dictation file (5) during comparison of the text file (8) with the dictation file (5) as a function of the confidence value of the relevant text passage (W(n)).

2. The method as claimed in claim 1, further comprising the step of:

marking the text passages (W(n)) for which the confidence value is below a confidence limit (C_G) .

3. A method as claimed in claim 1, in which the dictation file (5) is converted into a text file (8) automatically using a speech recognition device (7).

4. The method as claimed in claim 1, further comprising the step of:

equipping the text passages (W(n)) for which the confidence value is below the confidence limit (C_G) with a weighting factor.

5. The method as claimed in claim 1, wherein the confidence limit (C_G) is adjustable.

6. The method as claimed in claim 1, further comprising the step of:

repeating the comparison of the text file (8) with the dictation file (5) with an increased confidence limit (C_G) .

7. A transcription system (T) for transcribing dictations comprising

conversion means (7) for converting a dictation file (5) into a text file (8) with text passages (W(n));

confidence-value generation means (25) by which a confidence value is generated for each converted text passage (W(n)),

comparison means (24) for comparing the confidence value with a confidence limit (C_G) only in the case of those text passages (Wn)) for which the confidence value is below a confidence limit (C_G) ; and

playback speed alteration means for altering the playback speed for the dictation file (5) during comparison of the text file (8) with the dictation file (5) as a function of the confidence value of the relevant text passage (W(n)).

8. The transcription system (T) as claimed in claim 7, further comprising:

means (23) for marking the text passages (W(n)) for which the confidence value is below the confidence limit (C_G) .

9. The transcription system (T) as claimed in claim 7, in which the conversion means (7) for converting the dictation file (5) into a text file (8) is in the form of a speech recognition device.

10. The transcription system (T) as claimed in claim 7, further comprising:

means (21) are provided for weighing the text passages (W(n)) of the text file (8).

11. The transcription system (T) as claimed in claim 7, further comprising:

means (19) are provided for inputting the confidence limit (C_G) .