支持MIDI文件哼唱查询

发布于 2025-01-04 09:53:00 字数 48 浏览 3 评论 0原文

我读到可以通过使用 MIDI 文件哼唱来支持查询。有人可以告诉我如何做到这一点吗?

I read that one can support query by humming by using MIDI files. Can someone please give me an idea on how this can be done?

如果你对这篇内容有疑问,欢迎到本站社区发帖提问 参与讨论,获取更多帮助,或者扫码二维码加入 Web 技术交流群。

扫码二维码加入Web技术交流群

发布评论

需要 登录 才能够评论, 你可以免费 注册 一个本站的账号。

评论(2

铁憨憨 2025-01-11 09:53:00

如果您有权访问 IEEE 库:使用局部敏感哈希通过 midi 和音频的嗡嗡声进行查询

引用自 使用位置敏感哈希对 MIDI 和音频进行嗡嗡声查询,音频检索示例

我们提出了一种基于局部敏感的嗡嗡声查询方法
散列(LSH)。该方法通过以下方式构建旋律片段的索引
从旋律数据库中提取音高向量。在检索中,
该方法自动将所唱的查询转录成音符,然后
与索引构造类似地提取音高向量。对于每个
查询音高向量,该方法搜索相似的旋律片段
在数据库中获取候选旋律列表。这是
通过使用 LSH 可以有效地执行。候选旋律排名
通过它们与整个查询的距离并返回给用户。到
检索音频信号,我们应用自动旋律转录
直接从音乐构建旋律数据库的方法
录音。

If you have access to IEEE Library: Query by humming of midi and audio using locality sensitive hashing

Quoting from Query by Humming of MIDI and Audio Using Locality Sensitive Hashing, audio retrieval examples

We propose a query by humming method based on locality sensitive
hashing (LSH). The method constructs an index of melodic fragments by
extracting pitch vectors from a database of melodies. In retrieval,
the method automatically transcribes a sung query into notes and then
extracts pitch vectors similarly to the index construction. For each
query pitch vector, the method searches for similar melodic fragments
in the database to obtain a list of candidate melodies. This is
performed efficiently by using LSH. The candidate melodies are ranked
by their distance to the entire query and returned to the user. To
retrieve audio signals, we apply an automatic melody transcription
method to construct the melody database directly from music
recordings.

冰之心 2025-01-11 09:53:00

这是一个开源的哼唱查询系统,支持MIDI构建歌曲数据库:https://github.com/EmilioMolina/QueryBySingingHumming

参见参考文献:

[1] 王磊,黄沉,胡胜,梁家恩,徐博,一种基于多重相似性度量的蜂鸣系统查询的有效方法Fusion, ICALIP, 2008

[2] 王雷,黄沉,胡盛,梁家恩,徐波,基于特征融合、候选集约简和多重相似度测量重评分三种方法提高蜂鸣系统查询的搜索速度和准确性, INTERSPEECH,2008

[3] http://mirlab.org/dataSet/public/MIR-QBSH-corpus.rar

[4] http://www.esac-data.org/

Here is an open source query by humming system which support the midi for building song db: https://github.com/EmilioMolina/QueryBySingingHumming

and see the reference:

[1] Lei Wang, Shen Huang, Sheng Hu, Jiaen Liang, Bo Xu, An Effective and Efficient Method for Query by Humming System Based on Multi-Similarity Measurement Fusion, ICALIP, 2008

[2] Lei Wang, Shen Huang, Sheng Hu, Jiaen Liang, Bo Xu, Improving Searching Speed and Accuracy of Query by Humming System Based on Three Methods: Feature Fusion, Candidates Set Reduction and Multiple Similarity Measurement Rescoring, INTERSPEECH, 2008

[3] http://mirlab.org/dataSet/public/MIR-QBSH-corpus.rar

[4] http://www.esac-data.org/

~没有更多了~
我们使用 Cookies 和其他技术来定制您的体验包括您的登录状态等。通过阅读我们的 隐私政策 了解更多相关信息。 单击 接受 或继续使用网站,即表示您同意使用 Cookies 和您的相关数据。
原文