Onset detection: A new approach to QBH system
This work addresses the need for efficient and accurate song retrieval for users in music information retrieval, but it is incremental as it builds on existing QBH methods by refining onset detection.
The paper tackles the problem of improving Query by Humming (QBH) systems by focusing on precise onset detection, resulting in a system that is faster, more memory-efficient, and empirically more accurate than existing methods.
Query by Humming (QBH) is a system to provide a user with the song(s) which the user hums to the system. Current QBH method requires the extraction of onset and pitch information in order to track similarity with various versions of different songs. However, we here focus on detecting precise onsets only and use them to build a QBH system which is better than existing methods in terms of speed and memory and empirically in terms of accuracy. We also provide statistical analogy for onset detection functions and provide a measure of error in our algorithm.