Speaker attributed transcript generation
US12243534B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 4, 2022 |
| Grant date | Mar 4, 2025 |
| Priority date | — |
| Expiry date | Sep 24, 2042 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04M2201/41
- WIPO fieldDigital communication
- WIPO sectorElectrical engineering
Abstract
A computer implemented method processes audio streams recorded during a meeting by a plurality of distributed devices. Operations include performing speech recognition on each audio stream by a corresponding speech recognition system to generate utterance-level posterior probabilities as hypotheses for each audio stream, aligning the hypotheses and formatting them as word confusion networks with associated word-level posteriors probabilities, performing speaker recognition on each audio stream by a speaker identification algorithm that generates a stream of speaker-attributed word hypotheses, formatting speaker hypotheses with associated speaker label posterior probabilities and speaker-attributed hypotheses for each audio stream as a speaker confusion network, aligning the word and speaker confusion networks from all audio streams to each other to merge the posterior probabilities and align word and speaker labels, and creating a best speaker-attributed word transcript by selecting the sequence of word and speaker labels with the highest posterior probabilities.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.