Patent · US Active

System and method for speaker change detection

US10535000B2 · kind B2 · utility

0Cited by

4References

8Claims

0Family size

Inventors

Zhenhao Ge · Indianapolis, US
Ananth Nagaraja Iyer · Carmel, US
Srinath Cheluvaraja · Carmel, US
Aravind Ganapathiraju · Hyderabad, IN

Key dates

Filing date	Oct 6, 2017
Grant date	Jan 14, 2020
Priority date	—
Expiry date	Nov 22, 2037

Classification

Technology area (CPC G)Physics
CPC primaryG10L15/02
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A method for training a neural network of a neural network based speaker classifier for use in speaker change detection. The method comprises: a) preprocessing input speech data; b) extracting a plurality of feature frames from the preprocessed input speech data; c) normalizing the extracted feature frames of each speaker within the preprocessed input speech data with each speaker's mean and variance; d) concatenating the normalized feature frames to form overlapped longer frames having a frame length and a hop size; e) inputting the overlapped longer frames to the neural network based speaker classifier; and f) training the neural network through forward-backward propagation.

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