Don't Speak Too Fast: The Impact of Data Bias on Self-Supervised Speech Models
Author:
Affiliation:
1. National Taiwan University,Graduate Institute of Communication Engineering
2. National Taiwan University,College of Electrical Engineering and Computer Science
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/9745891/9746004/09747897.pdf?arnumber=9747897
Reference33 articles.
1. Insights on representational similarity in neural networks with canonical correlation;morcos;NeurIPS,2018
2. IEMOCAP: interactive emotional dyadic motion capture database
3. Speech Model Pre-Training for End-to-End Spoken Language Understanding
4. Voxceleb: Large-scale speaker verification in the wild
5. Deep Contextualized Acoustic Representations for Semi-Supervised Speech Recognition
Cited by 5 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. Feature Normalization for Fine-tuning Self-Supervised Models in Speech Enhancement;INTERSPEECH 2023;2023-08-20
2. Causal reasoning for algorithmic fairness in voice controlled cyber-physical systems;Pattern Recognition Letters;2023-04
3. How Does Pre-Trained Wav2Vec 2.0 Perform on Domain-Shifted Asr? an Extensive Benchmark on Air Traffic Control Communications;2022 IEEE Spoken Language Technology Workshop (SLT);2023-01-09
4. Towards Better Domain Adaptation for Self-Supervised Models: A Case Study of Child ASR;IEEE Journal of Selected Topics in Signal Processing;2022-10
5. DRAFT: A Novel Framework to Reduce Domain Shifting in Self-supervised Learning and Its Application to Children’s ASR;Interspeech 2022;2022-09-18
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