About: An Improved Deep Embedding Learning Method for Short Duration Speaker Verification

Not logged in : Login

(Sponging disallowed)

Facets (new session)
Description
Metadata
Settings
- Rule:
- Inverse Functional Properties:
- "Same As":

About: An Improved Deep Embedding Learning Method for Short Duration Speaker Verification Goto Sponge NotDistinct Permalink

An Entity of Type : bibo:AcademicArticle, within Data Space : demo.openlinksw.com associated with source document(s)

Attributes	Values
type	http://eprints.org/ontology/ConferenceItemEPrint http://eprints.org/ontology/EPrint Article Academic Article
seeAlso	HTML Summary of #67451 An Improved Deep Embedding Learning Method for Short Duration Speaker Verification
sameAs	An Improved Deep Embedding Learning Method for Short Duration Speaker Verification
http://eprints.org/ontology/hasAccepted	An Improved Deep Embedding Learning Method for Short Duration Speaker Verification (PDF)
http://eprints.org/ontology/hasDocument	An Improved Deep Embedding Learning Method for Short Duration Speaker Verification (PDF) An Improved Deep Embedding Learning Method for Short Duration Speaker Verification (Other) An Improved Deep Embedding Learning Method for Short Duration Speaker Verification (Other) An Improved Deep Embedding Learning Method for Short Duration Speaker Verification (Other) An Improved Deep Embedding Learning Method for Short Duration Speaker Verification (Other) An Improved Deep Embedding Learning Method for Short Duration Speaker Verification (Other)
dc:hasVersion	An Improved Deep Embedding Learning Method for Short Duration Speaker Verification (PDF)
Title	An Improved Deep Embedding Learning Method for Short Duration Speaker Verification
described by	https://demo.openlinksw.com/about/id/entity/https/raw.githubusercontent.com/annajordanous/CO644Files/main/export_kar_RDFN3.n3
Date	2018-09-06
Creator	Zhifu Gao Yan Song Li-Rong Dai Wu Guo I. McLoughlin
status	peer reviewed published
Publisher	International Speech Communication Association
abstract	This paper presents an improved deep embedding learning method based on convolutional neural networks (CNN) for short-duration speaker verification (SV). Existing deep learning-based SV methods generally extract frontend embeddings from a feed-forward deep neural network, in which the long-term speaker characteristics are captured via a pooling operation over the input speech. The extracted embeddings are then scored via a backend model, such as Probabilistic Linear Discriminative Analysis (PLDA). Two improvements are proposed for frontend embedding learning based on the CNN structure: (1) Motivated by the WaveNet for speech synthesis, dilated filters are designed to achieve a tradeoff between computational efficiency and receptive-filter size; and (2) A novel cross-convolutional-layer pooling method is exploited to capture $1^{st}$-order statistics for modelling long-term speaker characteristics. Specifically, the activations of one convolutional layer are aggregated with the guidance of the feature maps from the successive layer. To evaluate the effectiveness of our proposed methods, extensive experiments are conducted on the modified female portion of NIST SRE 2010 evaluations, with conditions ranging from 10s-10s to 5s-4s. Excellent performance has been achieved on each evaluation condition, significantly outperforming existing SV systems using i-vector and d-vector embeddings.
Is Part Of	https://kar.kent.ac.uk/id/repository
Subject	T Technology
list of authors	https://kar.kent.ac.uk/id/eprint/67451#authors
presented at	Interspeech 2018
is topic of	https://raw.githubusercontent.com/annajordanous/CO644Files/main/export_kar_RDFN3.n3
is primary topic of	HTML Summary of #67451 An Improved Deep Embedding Learning Method for Short Duration Speaker Verification

Faceted Search & Find service v1.17_git144 as of Jul 26 2024

Alternative Linked Data Documents: iSPARQL | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 08.03.3331 as of Aug 25 2024, on Linux (x86_64-ubuntu_noble-linux-glibc2.38-64), Single-Server Edition (378 GB total memory, 52 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software