The Distributions of Uncalibrated Speaker Verification Scores: A Generative Model for Domain Mismatch and Trial-Dependent Calibration-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

The Distributions of Uncalibrated Speaker Verification Scores: A Generative Model for Domain Mismatch and Trial-Dependent Calibration

Published:2023 Issue: Volume:31 Page:2204-2219
ISSN:2329-9290
Container-title:IEEE/ACM Transactions on Audio, Speech, and Language Processing
language:
Short-container-title:IEEE/ACM Trans. Audio Speech Lang. Process.

Author:

Cumani Sandro¹^ORCID,Sarni Salvatore¹^ORCID

Affiliation:

1. Dipartimento di Automatica e Informatica, Politecnico di Torino, Torino, Italy

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Acoustics and Ultrasonics,Computer Science (miscellaneous),Computational Mathematics

Link

http://xplorestaging.ieee.org/ielx7/6570655/9970249/10141873.pdf?arnumber=10141873

Reference63 articles.

1. A comparison of linear and nonlinear calibrations for speaker recognition;brümmer;Proc Speaker Lang Recognit Workshop,0

2. Deep Neural Networks for extracting Baum-Welch statistics for Speaker Recognition

3. Generative modelling for unsupervised score calibration

4. A Novel Scheme for Speaker Recognition Using a Phonetically-Aware Deep Neural Network

5. Tied Normal Variance–Mean Mixtures for Linear Score Calibration

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370

www.globalauthorid.com

TOP