.png){kind=icon}
返回
Computationally Efficient Dilated Convolutional Model for Melody Extraction
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2022.3189313.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper we propose a dilated convolutional model for music melody extraction. Taking variable-q transforms (VQTs) as inputs, it first uses consecutive layers of convolution to capture local temporal-frequency patterns, and then a single layer of dilated convolution to capture global frequency patterns contributed by the pitches and harmonics of active notes. Compared with the contrast model without dilation, the proposed model can remarkably cut down the computational cost, and at the same time does not compromise the performance. Its advantages over existing models are two fold. First, it performs best on most datasets, for both general and vocal melody extraction. Second, it can achieve the best performance with least training data.
Keyword:
Convolution
Computational modeling
Kernel
Feature extraction
Harmonic analysis
Transforms
Training data
Melody extraction
variable-q transform
dilated convolution
computational cost
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
Effects of temperature variations on safety of reinforced concrete structures during construction温度变化对施工期间钢筋混凝土结构安全性的影响
PREAI
分享收藏Zonas de aludes en la Vallferrera: Clasificación y riesgo geomorfológicoVallferrera地区的雪崩区：分类与地质风险.png)
Pirineos
OAAI
PirineosIF0
OAAI分享收藏
Probabilistic power and gas flow analysis for electricity-gas coupled networks considering uncertainties in pipeline parameters考虑管道参数不确定性的电力-天然气耦合网络概率功率与气体流动分析
PREAI
分享收藏Endocytosis of lanthanum nitrate in the organic acid-secreting trichomes of chickpea (Cicer arietinum L.)硝酸镧在鹰嘴豆（Cicer arietinum L.）分泌有机酸的腺毛中的内吞作用
IF0
PREAI
分享收藏
查看更多内容