Speaker attributed transcript generation

US11322148B2 · kind B2 · utility

Assignee

• MICROSOFT TECHNOLOGY LICENSING, LLC · US

Inventors

• Takuya Yoshioka · Bellevue, US
• Andreas Stolcke · Berkeley, US
• Zhuo Chen · Markham, CA
• Dimitrios Dimitriadis · Rutherford, US
• Nanshan Zeng · Bellevue, US
• Lijuan Qin · Redmond, US
• William Isaac Hinthorn · Seattle, US
• Xuedong Huang · Bellevue, US

Key dates

• Filing date: Apr 30, 2019
• Grant date: May 3, 2022
• Expiry date: Dec 5, 2039

Classification

• Technology area (CPC H): Electricity
• CPC primary: H04M2201/41
• WIPO field: Digital communication
• WIPO sector: Electrical 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.