Speaker segment analysis for conferences
US11863711B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 10, 2022 |
| Grant date | Jan 2, 2024 |
| Priority date | — |
| Expiry date | Oct 10, 2042 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04N7/147
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
A transcript of a conference is processed to extract a conference summary. The transcript includes strings that are associated with respective timestamps and respective speaker identifiers. Speaker segments—sequences of consecutive strings attributed to the same speaker—are identified in the transcript. A speaker segment is selected based on its duration in time and one or more strings are selected from with the selected speaker segment for inclusion in the conference summary. A short video conference summary or a short audio conference summary is then generated using timestamps from the transcript associated with strings that have been selected for inclusion in the conference summary. The short video or audio summary may be presented to users to enable efficient storage and transmission of information from the conference within a unified communications system.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.