Microsoft patents method to hide sensitive words in voice data
Microsoft describes a system that takes a voice recording and its text transcript to identify and mask sensitive information. It creates a new, synthetic voice clip that keeps the original speaker's tone and acoustic qualities but replaces the sensitive words with obscured versions.
In the filing’s own words
A method, computer program product, and computing system for receiving an input speech signal. A transcription of the input speech signal may be received. A speaker embedding may be extracted from the input speech signal. Acoustic properties from the input speech signal may be extracted. An obscured transcription may be generated from the transcription, where the obscured transcription includes obscured representations of sensitive content from the transcription. An obscured speech signal may be generated based upon, at least in part, the extracted speaker embedding and the obscured transcription, where the obscured speech signal includes obscured representations of sensitive content from the input speech signal. The obscured speech signal may be augmented based upon, at least in part, the extracted acoustic properties.
What exactly they claim (claim 1)
1. A method comprising: receiving an input speech signal; receiving a transcription of the input speech signal; extracting a speaker embedding from the input speech signal; extracting acoustic properties from the input speech signal; generating an obscured transcription from the transcription, wherein the obscured transcription includes obscured representations of sensitive content from the transcription; generating an obscured speech signal based upon, at least in part, the extracted speaker embedding and the obscured transcription, wherein the obscured speech signal includes obscured representations of sensitive content from the input speech signal; generating a synthetic speech signal from the obscured speech signal using a synthetic speaker embedding; and augmenting the synthetic speech signal based upon, at least in part, the extracted acoustic properties.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- System and method for secure data augmentation for speech processing systems
- Patent number
- US12763065B2
- Application number
- 18766142
- Filed
- Jul 8, 2024
- Granted
- Oct 13, 2026
- Inventors
- 3
- Claims
- 20
Classified under
G10L 13/08 Physics & computingG06F 21/6245 Physics & computingG06F 40/166 Physics & computingG10L 13/033 Physics & computingG10L 17/02 Physics & computingMore from Microsoft in Security & privacy
- Microsoft patents system to call 911 for others during video calls Sep 22, 2026
- Microsoft patents system to block fake code suggested by AI Sep 15, 2026
- Microsoft patents one-way data flow to block network attacks Sep 10, 2026
- Microsoft patents voice coding that hides speaker identity for secure calls Sep 17, 2026
- Microsoft patents security checks for AI chats using user and model profiles Oct 1, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.