Time-Frequency and Geometric Analysis of Task-Dependent Learning in Raw Waveform Based Acoustic Models
Author:
Affiliation:
1. IIIT Delhi,Infosys Centre for AI,India
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/9745891/9746004/09746577.pdf?arnumber=9746577
Reference27 articles.
1. End-to-end speech emotion recognition using a novel context-stacking dilated convolution neural network
2. SmoothGrad: removing noise by adding noise;smilkov;Workshop on Visualization for Deep Learning,2017
3. Striving for simplicity: The all convolutional net;springenberg;International Conference on Learning Representations (ICLR),2015
4. Axiomatic attribution for deep networks;sundararajan;International Conference on Machine Learning (ICML),2017
5. Understanding and Visualizing Raw Waveform-Based CNNs
Cited by 3 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. Speech and speaker recognition using raw waveform modeling for adult and children’s speech: A comprehensive review;Engineering Applications of Artificial Intelligence;2024-05
2. Multi-Layer Acoustic & Linguistic Feature Fusion for ComParE-23 Emotion and Requests Challenge;Proceedings of the 31st ACM International Conference on Multimedia;2023-10-26
3. Towards on-Device Keyword Spotting using Low-Footprint Quaternion Neural Models;2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA);2023-10-22
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