AES E-Library

AES E-Library

High-Precision Score-Based Audio Indexing Using Hierarchical Dynamic Time Warping

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.

AES Convention: Paper Number:
Publication Date:

Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!

This paper costs $33 for non-members and is free for AES members and E-Library subscribers.

Learn more about the AES E-Library

E-Library Location:

Start a discussion about this paper!

AES - Audio Engineering Society