简体繁体 English

歌曲识别算法

[英]Algorithm for Song recognition

原文 2012-06-11 15:05:58 6 2 android/ algorithm/ pattern-matching/ voice-recognition/ shazam

Any idea how i can go about implementing an algorithm for identifying a song, by matching it with a clip of the song or human voice or tune. 我知道如何通过将其与歌曲或人声或曲调的剪辑相匹配来实现识别歌曲的算法。 I dont expect anyone to write out the algo here :), i know it involves a lot of things together, but i would like to know how i can get started. 我不希望有人在这里写出算法:)，我知道它涉及很多东西，但我想知道我是如何开始的。 What are the technologies that i will need to consider for doing something like it. 做类似事情我需要考虑哪些技术。 I am looking at something similar to Shazaam or Midomi. 我正在寻找类似于Shazaam或Midomi的东西。 Also, is there an online service that does the same and provides API for doing it. 此外，是否有一个在线服务执行相同的操作并提供API。

2 个解决方案

I saw a presentation at the devoxx conference about this, have a look at it here . 我在devoxx会议上看到了一个关于此的演讲，请看这里。 And here is a blog post, by the speaker, about the same subject. 这是一篇由发言人撰写的关于同一主题的博客文章。

Oh, it simple. 哦，很简单。

Split song into pieces, run FFT on each, extract few main magnitudes and store them as a hash with time information. 将歌曲分成片段，在每个片段上运行FFT，提取几个主要幅度并将它们存储为带有时间信息的哈希值。
Then do the same with recorded audio and match with stored data with regards to time. 然后对录制的音频执行相同操作，并与存储的数据相关联。

Simple isn't it? 简单不是吗？ To be honest it's more complicated but idea is similar. 说实话，它更复杂，但想法是相似的。