《Autoencoder-based Semi-Supervised Curriculum Learning For Out-of-domain Speaker Verification》电子版地址

简介: Autoencoder-based Semi-Supervised Curriculum Learning For Out-of-domain Speaker Verification

《Autoencoder-based Semi-Supervised Curriculum Learning For Out-of-domain Speaker Verification》Autoencoder-based Semi-Supervised Curriculum Learning For Out-of-domain Speaker Verification

电子书:

屏幕快照 2022-06-17 上午9.58.35.png

                
            </div>
目录
相关文章
|
4月前
|
存储 算法 计算机视觉
【博士每天一篇文献-模型】Meta-Learning Based Tasks Similarity Representation for Cross Domain Lifelong Learning
本文提出了一种基于元学习的跨域终身学习框架,通过跨域三元组网络(CDTN)学习任务间的相似性表示,并结合自注意模块与软注意网络(SAN)来增强特征提取和任务权重分配,以提高学习效率并减少对先前知识的遗忘。
52 1
【博士每天一篇文献-模型】Meta-Learning Based Tasks Similarity Representation for Cross Domain Lifelong Learning
|
4月前
|
机器学习/深度学习 算法 数据挖掘
【博士每天一篇文献-模型】Investigating Echo State Network Performance with Biologically-Inspired Hierarchical
本文研究了一种受果蝇生物启发的分层网络结构在回声状态网络(ESN)中的应用,通过引入层次随机块模型(HSBM)来生成具有更好结构性的网络拓扑,发现这种新拓扑结构的网络在Mackey-Glass系统预测和MNIST分类任务中表现出改善的整体解分布,从而提高了ESN的性能。
31 2
|
4月前
|
机器学习/深度学习 PyTorch 算法框架/工具
【文献学习】Phase-Aware Speech Enhancement with Deep Complex U-Net
文章介绍了Deep Complex U-Net模型,用于复数值的语音增强,提出了新的极坐标掩码方法和wSDR损失函数,并通过多种评估指标验证了其性能。
62 1
|
数据挖掘
【提示学习】Automatic Multi-Label Prompting: Simple and Interpretable Few-Shot Classification
文章提出了一种简单确高效地构建verbalization的方法:
|
7月前
|
存储 JSON 算法
【论文代码】②.1 STIOCS: Active learning-based semi-supervised training framework for IOC extraction
【论文代码】②.1 STIOCS: Active learning-based semi-supervised training framework for IOC extraction
39 0
|
机器学习/深度学习 自然语言处理 算法
TASLP21-Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relations
事件抽取是自然语言处理的一项基本任务。找到事件论元(如事件参与者)的角色对于事件抽取至关重要。
108 0
|
7月前
|
自然语言处理
【论文代码】① STIOCS: Active learning-based semi-supervised training framework for IOC extraction
【论文代码】① STIOCS: Active learning-based semi-supervised training framework for IOC extraction
49 0
|
机器学习/深度学习 自然语言处理
【论文精读】COLING 2022 - DESED: Dialogue-based Explanation for Sentence-level Event Detection
最近许多句子级事件检测的工作都集中在丰富句子语义上,例如通过多任务或基于提示的学习。尽管效果非常好,但这些方法通常依赖于标签广泛的人工标注
106 0
|
机器学习/深度学习 算法 数据挖掘
【多标签文本分类】Improved Neural Network-based Multi-label Classification with Better Initialization ……
【多标签文本分类】Improved Neural Network-based Multi-label Classification with Better Initialization ……
140 0
【多标签文本分类】Improved Neural Network-based Multi-label Classification with Better Initialization ……
《Multi-Task Multi-Network Joint-Learning of Deep Residual Networks and Cycle-Consistency Generative Adversarial Networks for Robust Speech Recognition》电子版地址
Multi-Task Multi-Network Joint-Learning of Deep Residual Networks and Cycle-Consistency Generative Adversarial Networks for Robust Speech Recognition
109 0
《Multi-Task Multi-Network Joint-Learning of Deep Residual Networks and Cycle-Consistency Generative Adversarial Networks for Robust Speech Recognition》电子版地址