Audio signal de-identification

• US 7,502,741 B2
• Filed: 02/23/2005
• Issued: 03/10/2009
• Est. Priority Date: 02/23/2005
• Status: Active Grant

• Current Assignee: Multimodal Technologies Incorporated (3M Company)
• Original Assignee: Multimodal Technologies Incorporated (3M Company)
• Inventors: Koll, Detlef, Finke, Michael
• Primary Examiner(s): Lerner; Martin
• Application Number:
  US11/064,343
• Publication Number:
  US 20060190263A1
• Time in Patent Office: 1,476 Days
• Field of Search: 704/231, 704/251, 704/273, 704/270, 705/1, 705/2, 705/3
• US Class Current: 704/270
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof

Abstract

Techniques are disclosed for automatically de-identifying spoken audio signals. In particular, techniques are disclosed for automatically removing personally identifying information from spoken audio signals and replacing such information with non-personally identifying information. De-identification of a spoken audio signal may be performed by automatically generating a report based on the spoken audio signal. The report may include concept content (e.g., text) corresponding to one or more concepts represented by the spoken audio signal. The report may also include timestamps indicating temporal positions of speech in the spoken audio signal that corresponds to the concept content. Concept content that represents personally identifying information is identified. Audio corresponding to the personally identifying concept content is removed from the spoken audio signal. The removed audio may be replaced with non-personally identifying audio.

Claims

1. A computer-implemented method, tangibly embodied as a computer program recorded in a computer-readable medium, the method comprising:

(A) identifying a first portion of an original audio signal, the first portion representing sensitive content, comprising;

(A)(1) generating a report, the report comprising;

(a) content representing information in the original audio signal, and (b) a timestamp indicating a temporal position of the first portion of the original audio signal;

(A)(2) identifying a first personally identifying concept in the report;

(A)(3) identifying a first timestamp in the report corresponding to the first personally identifying concept; and

(A)(4) identifying a portion of the original audio signal corresponding to the first personally identifying concept by using the first timestamp; and

(B) producing a modified audio signal in which the first portion is protected against unauthorized disclosure.

2. The method of claim 1, further comprising a step of:

(C) removing the first personally identifying concept from the report to produce a de-identified report.

3. The method of claim 2, further comprising a step of:

(C)transcribing the modified audio signal based on the modified audio signal and the de-identified report.

4. A system comprising:

sensitive content identification means comprising;

means for identifying a first portion of an original audio signal, the first portion representing sensitive content;

means for generating a report, the report comprising;

(a) content representing information in the original audio signal, and (b) at least one timestamp indicating at least one temporal position of at least one portion of the original audio signal corresponding to the content;

means for identifying a first personally identifying concept in the report;

means for identifying a first timestamp in the report corresponding to the first personally identifying concept; and

means for identifying a portion of the original audio signal corresponding to the first personally identifying concept by using the first timestamp; and

modified audio signal production means for producing a modified audio signal in which the identified first portion is protected against unauthorized disclosure.