We propose a novel audio signal processing algorithm of high-precision score-based audio indexing that accurately maps a music score with its corresponding audio. Specifically we improve the time precision of existing score-audio alignment algorithms to find the accurate positions of audio onsets and offsets. We achieve higher time precision by (1) improving the resolution of alignment sequences, and (2) admitting a hierarchy of spectrographic analysis results as audio alignment features. The performance of our proposed algorithm is testified by comparing the segmentation results with manually composed reference datasets. Our proposed algorithm achieves robust alignment results and enhanced segmentation accuracy and thus is suitable for audio engineering applications such as automatic music production and human-media interactions.

Authors: Zhou, Xiang; Ke, Fangyu; Shu, Cheng; Ren, Gang; Bocko, Mark F.
Affiliations: Bose Corporation, Framingham, MA, USA; University of Rochester, Rochester, NY, USA(See document for exact affiliation information.)
AES Convention: 135 (October 2013) Paper Number: 8931
Publication Date: October 16, 2013
Subject: Signal Processing

Click to purchase paper as a non-member or you can login as an AES member to see more options.

No AES members have commented on this paper yet.

Subscribe to this discussion

To be notified of new comments on this paper you can subscribe to this RSS feed. Forum users should login to see additional options.

Start a discussion!

If you would like to start a discussion about this paper and are an AES member then you can login here:
Username:
Password:

If you are not yet an AES member and have something important to say about this paper then we urge you to join the AES today and make your voice heard. You can join online today by clicking here.