COMBINING AUDIO AND SYMBOLIC DESCRIPTORS FOR MUSIC CLASSIFICATION FROM AUDIO

COMBINING AUDIO AND SYMBOLIC DESCRIPTORS FOR MUSIC CLASSIFICATION FROM AUDIO
复制标题

结合音频和符号描述符对音频进行音乐分类

DOI:
--
复制
发表时间:
2007
期刊:
影响因子:
--
通讯作者:
J. Iñesta
J. Iñesta
中科院分区:
--
文献类型:
--
作者:
T. Lidy;Andreas Rauber;A. Pertusa;J. Iñesta

文献摘要

被引文献

相似文献

最近在音乐流派分类方面的研究表明,使用音色音频特征可以达到玻璃天花板。为了克服这一点,需要组合具有不同特征的多个不同特征集。我们提出了一种新的方法来扩展功能的范围:我们使用转录系统将音频数据转录成符号形式,从该表示中提取符号描述符,并将它们与音频功能联合收割机相结合。通过这种方法,我们能够超越玻璃天花板,并进一步改善音乐流派分类。在这项工作中,在[3]中提出的系统的方法进行了描述和评估。
Recent research in music genre classification hints at a glass ceiling being reached using timbral audio features. To overcome this, the combination of multiple different feature sets bearing diverse characteristics is needed. We propose a new approach to extend the scope of the features: We transcribe audio data into a symbolic form using a transcription system, extract symbolic descriptors from that representation and combine them with audio features. With this method, we are able to surpass the glass ceiling and to further improve music genre classification. In this work, the methodology of the system presented in [3] is described and evaluated.