Kernel eigenvoice

id: kernel-eigenvoice-241-946508
title: Kernel eigenvoice
text: Speaker adaptation is an important technology to fine-tune either features or speech models for mis-match due to inter-speaker variation. In the last decade, eigenvoice (EV) speaker adaptation has been developed. It makes use of the prior knowledge of training speakers to provide a fast adaptation algorithm. Inspired by the kernel eigenface idea in face recognition, kernel eigenvoice (KEV) is proposed. KEV is a non-linear generalization to EV. This incorporates Kernel principal component analysi
brand slug: wiki
category slug: encyclopedia
description:
original url: https://en.wikipedia.org/wiki/Kernel_eigenvoice
date created:
date modified: 2021-05-28T13:17:17Z
main entity: {"identifier":"Q6394193","url":"https://www.wikidata.org/entity/Q6394193"}
image:
fields total: 13
integrity: 13

Related Entries

Explore Next Part