Patent · US Active

Maintainable and scalable pipeline for automatic speech recognition language modeling

US11410658B1 · kind B1 · utility

0Cited by
6References
22Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 29, 2019
Grant dateAug 9, 2022
Priority date
Expiry dateJun 17, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L15/30
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Audio data saved at the end of client interactions are sampled, analyzed for pauses in speech, and sliced into stretches of acoustic data containing human speech between those pauses. The acoustic data are accompanied by machine transcripts made by VoiceAI. A suitable distribution of data useful for training and testing are stipulated during data sampling by applying certain filtering criteria. The resulting datasets are sent for transcription by a human transcriber team. The human transcripts are retrieved, some post-transcription processing and cleaning are performed, and the results are added to datastores for training and testing an acoustic model.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.