What do end-to-end speech models learn about speaker, language and channel information? A layer-wise and neuron-level analysis

Author:

Chowdhury Shammur AbsarORCID,Durrani Nadir,Ali Ahmed

Funder

Qatar National Library

Publisher

Elsevier BV

Subject

Human-Computer Interaction,Theoretical Computer Science,Software

Reference97 articles.

1. Connecting Arabs: Bridging the gap in dialectal speech recognition;Ali;Commun. ACM,2021

2. Ali, A., Chowdhury, S.A., Hussein, A., Hifny, Y., 2021b. Arabic Code-Switching Speech Recognition using Monolingual Data. In: Proc. Interspeech 2021.

3. The MGB-5 challenge: Recognition and dialect identification of dialectal Arabic speech;Ali,2019

4. Speech recognition challenge in the wild: Arabic MGB-3;Ali,2017

5. Amodei, D., Ananthanarayanan, S., Anubhai, R., Bai, J., Battenberg, E., Case, C., Casper, J., Catanzaro, B., Cheng, Q., Chen, G., et al., 2016. Deep speech 2: End-to-end speech recognition in English and Mandarin. In: International Conference on Machine Learning. pp. 173–182.

Cited by 2 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. Voice Profile Authentication Using Machine Learning;EEPES 2024;2024-08-08

2. Refining Text Input For Augmentative and Alternative Communication (AAC) Devices: Analysing Language Model Layers For Optimisation;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

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