AdaMast: A Drum Sound Recognizer based on Adaptation and Matching of Spectrogram Templates
AdaMast: A Drum Sound Recognizer based on Adaptation and Matching of Spectrogram Templates
复制标题
DOI：
--
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
Kazuyoshi Yoshii;Masataka Goto;HIroshi G. Okuno
中科院分区：
文献类型：
--
作者：
Kazuyoshi Yoshii;Masataka Goto;HIroshi G. Okuno
本文描述了一个基于模板匹配的系统，称为AdaMast，它可以检测流行歌曲复调音频信号中的低音鼓，小鼓和高钹的开始时间。AdaMast使用鼓声的功率谱图作为模板。然而，在有其他声音存在的情况下，抄录鼓声有两个主要问题。第一个问题是，实际的鼓声谱图不能事先为每首歌准备好模板。第二个问题是包含鼓声的混合声的功率谱与模板（纯鼓声谱）有很大的不同。为了解决第一个问题，在AdaMast中构建了模板自适应算法。为了解决第二个问题，在模板匹配中使用的距离度量被设计为对其他声音的频谱重叠具有鲁棒性。在音频鼓检测大赛中，对低音鼓、小军鼓和高钹的转录率分别为72.8%、70.2%和57.4%，AdaMast获得了比赛的冠军。
This paper describes a template-matching-based system, called AdaMast, that detects onset times of the bass drum, snare drum, and hi-hat cymbals in polyphonic audio signals of popular songs. AdaMast uses the power spectrograms of the drum sounds as templates. However, there are two main problems in transcribing drum sounds in the presence of other sounds. The first problem is that actual drum-sound spectrograms cannot be prepared as templates beforehand for each song. The second problem is that power spectrograms of sound mixtures including the drum sound are greatly different from the template (pure drum-sound spectrogram). To solve the first problem, a template-adaptation algorithm is built into AdaMast. To solve the second problem, a distance measure used in the template matching is designed to be robust to the spectral overlapping of other sounds. The test results in Audio Drum Detection Contest were 72.8%, 70.2%, and 57.4% in transcribing the bass drums, snare drums, and hi-hat cymbals, respectively, and AdaMast won the contest.