数据与计算发展前沿 ›› 2021, Vol. 3 ›› Issue (4): 81-92.doi: 10.11871/jfdc.issn.2096-742X.2021.04.007

• 技术与应用 • 上一篇    下一篇

热门数字音频预测技术综述

张怡宁1,2(),何洪波1,*(),王闰强1()   

  1. 1.中国科学院计算机网络信息中心,北京 100190
    2.中国科学院大学,北京 100049
  • 收稿日期:2021-01-21 出版日期:2021-08-20 发布日期:2021-08-30
  • 通讯作者: 何洪波
  • 作者简介:张怡宁,中国科学院计算机网络信息中心,在读硕士研究生,主要研究方向为科学传播技术及应用、web数据挖掘及应用。
    本文中承担的任务是文献调研、文献分析与归纳总结等。
    ZHANG Yining, she is a graduate student in Computer Network Information Center of Chinese Acade-my of Sciences. Her main research fields include science com-munication technology and application, network data mining and application.
    In this paper, she is responsible for literature research, literature analysis and summary.
    E-mail: zhangyining@cnic.cn|何洪波,中国科学院计算机网络信息中心,高级工程师,硕士生导师,主要研究方向为网络科普相关技术的研究与应用、web数据挖掘和信息推荐。
    本文中负责思路解析和把握文章逻辑与框架。
    HE Hongbo is a senior engineer and master tutor of Computer Network Information Center of Chinese Academy of Sciences. His main research fields include research and application of internet-based popular science related technologies, web data mining and information recommendation.
    In this paper, he is responsible for analyzing ideas and grasping the logic and framework of the article.
    E-mail: hhb@cnic.cn|王闰强,中国科学院计算机网络信息中心,正高级工程师,新媒体技术与应用发展部常务主任,主要从事新媒体科学传播与教育技术、应用和服务研究和实践。
    本文中负责把握文章总体方向与框架。
    WANG Runqiang is a senior engineer and executive director of New Media Technology and Appli-cation Development Department of Computer Network Infor-mation Center of Chinese Academy of Sciences. He is mainly engaged in the research and practice of new media science communication and educational technology, application and service.
    In this paper, he is responsible for grasping the overall direction and framework of the article.
    E-mail: wrq@cnic.cn
  • 基金资助:
    中国科学院信息化专项“新媒体环境下的科学传播平台”(XXH13504-04)

A Survey on Popular Digital Audio Prediction Techniques

ZHANG Yining1,2(),HE Hongbo1,*(),WANG Runqiang1()   

  1. 1. Computer Network Information Center, Chinese Academy of Sciences, Beijing 100190, China
    2. University of Chinese Academy of Sciences, Beijing 100049, China
  • Received:2021-01-21 Online:2021-08-20 Published:2021-08-30
  • Contact: HE Hongbo

摘要:

【目的】近些年网络数字音频受众愈发广泛,研究热门数字音频预测技术对于数字音频领域的发展具有重要意义。【文献范围】我们采用关键词检索和引文二次检索的方法收集了该领域相关的论文。【方法】本文通过广泛的文献查阅,总结了在该研究领域中学者们对热门指标的定义,归纳了预测热门音频常用的四大类内部特征,综述和分析了常用的预测模型,并展望了热门数字音频预测技术未来的发展趋势和研究方向。【结果】通过选取恰当的特征表示,可以成功地预测热门音乐与热门播客,其中热门音乐预测领域的研究成果更为丰富可观。【局限】国内学术界对热门音频预测领域开展的研究较少,因而所能检索到的中文文献也较为匮乏。【结论】热门数字音频预测领域仍然存在着广阔的发展空间,尤其是我国热门播客预测领域仍存在着很大的研究空白。

关键词: 数字音频, 音乐, 播客, 热度预测, 音频特征, 机器学习, 深度学习

Abstract:

[Objective] In recent years, the number of online digital audio audiences have increased greatly. It is of great significance to study the popular digital audio prediction techniques for the development of digital audio systems. [Coverage] Relevant papers in this field are collected by using keyword search and citation retrieval. [Methods] Through extensive literature review, we have summarized the definitions of popular indicators by scholars in this research field, categorized the four main types of internal features commonly used for predicting popular audio, reviewed and analyzed commonly used prediction models. We also forecast the future development trends and research directions of this field. [Results] By selecting appropriate feature representations, popular music and popular podcasts can be successfully predicted, in which the research on popular music prediction are more versatile and impressive. [Limitations] There is little domestic research in the field of popular audio prediction, so the number of retrieved Chinese literature is very small. [Conclusions] There is still huge growth potential in popular digital audio prediction, especially for podcast prediction, which is still an underdeveloped realm in China.

Key words: digital audio, music, podcast, popularity prediction, audio features, machine learning, deep learning