Systems and methods for analyzing speech data to remove sensitive data
US12229313B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 19, 2024 |
| Grant date | Feb 18, 2025 |
| Priority date | — |
| Expiry date | Jul 19, 2044 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L17/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
According to an embodiment, a method includes receiving audio data and providing the audio data as input to a first machine learning model to produce transcription data. The audio data is provided as input to a second machine learning model to produce speaker separation data, and the transcription data is segmented based on the speaker separation data to produce speaker separated transcription data. A portion of the speaker separated transcription data is provided as input to a third machine learning model to identify personal identifiable information (PII) text in the portion of the speaker separated transcription data, the portion being associated with a speaker from a plurality of speakers. The method also includes replacing the PII text with redaction text in the portion of the speaker separated transcription data and causing display of the transcription data including the redaction text at a user compute device.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.