当前位置:
X-MOL 学术
›
arXiv.cs.IR
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Audio Summarization with Audio Features and Probability Distribution Divergence
arXiv - CS - Information Retrieval Pub Date : 2020-01-20 , DOI: arxiv-2001.07098 Carlos-Emiliano Gonz\'alez-Gallardo, Romain Deveaud, Eric SanJuan, and Juan-Manuel Torres-Moreno
arXiv - CS - Information Retrieval Pub Date : 2020-01-20 , DOI: arxiv-2001.07098 Carlos-Emiliano Gonz\'alez-Gallardo, Romain Deveaud, Eric SanJuan, and Juan-Manuel Torres-Moreno
The automatic summarization of multimedia sources is an important task that
facilitates the understanding of an individual by condensing the source while
maintaining relevant information. In this paper we focus on audio summarization
based on audio features and the probability of distribution divergence. Our
method, based on an extractive summarization approach, aims to select the most
relevant segments until a time threshold is reached. It takes into account the
segment's length, position and informativeness value. Informativeness of each
segment is obtained by mapping a set of audio features issued from its
Mel-frequency Cepstral Coefficients and their corresponding Jensen-Shannon
divergence score. Results over a multi-evaluator scheme shows that our approach
provides understandable and informative summaries.
中文翻译:
具有音频特征和概率分布发散的音频摘要
多媒体资源的自动汇总是一项重要的任务,它通过在保持相关信息的同时浓缩资源来促进对个人的理解。在本文中,我们专注于基于音频特征和分布发散概率的音频摘要。我们的方法基于提取摘要方法,旨在选择最相关的片段,直到达到时间阈值。它考虑了段的长度、位置和信息量值。每个片段的信息量是通过映射一组从其梅尔频率倒谱系数及其相应的 Jensen-Shannon 散度分数发出的音频特征来获得的。多评估者方案的结果表明,我们的方法提供了可理解且内容丰富的摘要。
更新日期:2020-04-03
中文翻译:
具有音频特征和概率分布发散的音频摘要
多媒体资源的自动汇总是一项重要的任务,它通过在保持相关信息的同时浓缩资源来促进对个人的理解。在本文中,我们专注于基于音频特征和分布发散概率的音频摘要。我们的方法基于提取摘要方法,旨在选择最相关的片段,直到达到时间阈值。它考虑了段的长度、位置和信息量值。每个片段的信息量是通过映射一组从其梅尔频率倒谱系数及其相应的 Jensen-Shannon 散度分数发出的音频特征来获得的。多评估者方案的结果表明,我们的方法提供了可理解且内容丰富的摘要。