On the Complementary Role of DNN Multi-Level Enhancement for Noisy Robust Speaker Recognition in an I-Vector Framework
Author:
Affiliation:
1. Lab of Intelligent Information Processing, Army Engineering University
2. College of Communication Engineering, Army Engineering University
3. Institution of Information & Communication, National University of Defense Technology
Publisher
Institute of Electronics, Information and Communications Engineers (IEICE)
Subject
Applied Mathematics,Electrical and Electronic Engineering,Computer Graphics and Computer-Aided Design,Signal Processing
Link
https://www.jstage.jst.go.jp/article/transfun/E103.A/1/E103.A_2019EAL2104/_pdf
Reference17 articles.
1. [1] O. Novotný, O. Plchot, O. Glembek, J. Cernocký, and L. Burget, “Analysis of DNN speech signal enhancement for robust speaker recognition,” Computer Speech and Language, vol.58, pp.403-421, Nov. 2019. 10.1016/j.csl.2019.06.004
2. [2] O. Plchot, L. Burget, H. Aronowitz, and P. Matejka, “Audio enhancing with DNN autoencoder for speaker recognition,” Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol.1, pp.5090-5094, Shanghai, China, March 2016. 10.1109/icassp.2016.7472647
3. [3] S. Du, X. Xiao, and E.S. Chng, “DNN feature compensation for noise robust speaker verification,” Proc. IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP), vol.1, pp.871-875, Chengdu, China, July 2015. 10.1109/chinasip.2015.7230529
4. [4] S. Mahto, H. Yamamoto, and T. Koshinaka, “I-vector transformation using a novel discriminative denoising autoencoder for noise-robust speaker recognition,” Proc. Conference of the International Speech Communication Association (INTERSPEECH), vol.1, pp.3722-3726, Stockholm, Sweden, Aug. 2017. 10.21437/interspeech.2017-731
5. [5] J. Guo, N. Xu, K. Qian, Y. Shi, K. Xu, Y.N. Wu, and A. Alwan, “Deep neural network based i-vector mapping for speaker verification using short utterances,” Speech Commun., vol.105, pp.92-102, Dec. 2018. 10.1016/j.specom.2018.10.004
Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Increasing the Robustness of i-vectors with Model Compensated First Order Statistics;Afyon Kocatepe University Journal of Sciences and Engineering;2023-03-01
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
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3