Patent · US Active

Voice signal component forecasting

US10224061B2 · kind B2 · utility

0Cited by
1References
9Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 15, 2017
Grant dateMar 5, 2019
Priority date
Expiry dateDec 15, 2037

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L2021/02087
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods forecast voice signal components, wherein processors are configured to translate the audio data that includes voice data and a fabricated background noise into frequency domain data; identify a threshold number of top frequencies within the frequency domain data; and generate a hash code value from the threshold number of top frequencies. Processors are configured to, in response to determining that the generated hash code value is unique from other hash code values that are indexed to each of a unique identification of the speaker and a background noise profile identification of the fabricated background noise, index a model of the threshold number of top frequencies in association with the hash code to the speaker identification and to the background noise profile.

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