Curriculum learning based approach for noise robust language identification using DNN with attention

Author:

Vuddagiri Ravi Kumar,Vydana Hari Krishna,Vuppala Anil Kumar

Funder

SERB

Publisher

Elsevier BV

Subject

Artificial Intelligence,Computer Science Applications,General Engineering

Reference35 articles.

1. Language identification: A tutorial;Ambikairajah;IEEE Circuits and Systems Magazine,2011

2. Curriculum learning;Bengio,2009

3. Suppression of acoustic noise in speech using spectral subtraction;Boll;IEEE Transactions on Acoustics, Speech, and Signal Processing,1979

4. Braun, S., Neil, D., & Liu, S.-C. (2016). A curriculum learning method for improved noise robustness in automatic speech recognition. arXiv:1606.06864.

5. Significance of neural phonotactic models for large-scale spoken language identification;Brij Mohan Lal,2017

Cited by 22 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. Open-vocabulary object detection via debiased curriculum self-training;Expert Systems with Applications;2024-12

2. LIFA: Language identification from audio with LPCC-G features;Multimedia Tools and Applications;2023-12-14

3. Real Time Raspberry Pi based System for Linguistic Content Recognition from Speech;2023-08-07

4. Spoken Language Identification Using Prosody, Phonotactics, and Acoustics: A Review;Journal of Information & Knowledge Management;2022-07-14

5. Spoken Language Identification of Indian Languages in Adversarial Synthetic and Noisy Attacking Environments;2022 International Conference on Computing, Communication, Security and Intelligent Systems (IC3SIS);2022-06-23

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

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