.png){kind=icon}
返回
An improved vector quantization method using deep neural network
.png){kind=icon}
PRE
AI
DOI：10.1016/j.aeue.2016.12.002.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
To address the challenging problem of vector quantization (VQ) for high dimensional vector using large coding bits, this work proposes a novel deep neural network (DNN) based VQ method. This method uses a k-means based vector quantizer as an encoder and a DNN as a decoder. The decoder is initialized by the decoder network of deep auto-encoder, fed with the codes provided by the k-means based vector quantizer, and trained to minimize the coding error of VQ system. Experiments on speech spectrogram coding demonstrate that, compared with the k-means based method and a recently introduced DNN-based method, the proposed method significantly reduces the coding error. Furthermore, in the experiments of coding multi-frame speech spectrogram, the proposed method achieves about 11% relative gain over the k-means based method in terms of segmental signal to noise ratio (SegSNR). (C) 2016 Elsevier GmbH. All rights reserved.
Keyword:
Deep neural network
Vector quantization
Auto-encoder
Binary coding
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
A
IF:
3.2
论文数:
5.8K
被引数:
8.3K
机构
引用论文
Improved Particle Size Control for the Dispersion Polymerization of Methyl methacrylate in Supercritical Carbon Dioxide超临界二氧化碳中甲基丙烯酸甲酯分散聚合的改进粒度控制
OAAI
.png){kind=icon}
OAAI分享收藏
没有更多内容
没有更多内容