Learning The Similarity Of Audio Music In Bag-Of-Frames Representation From Tagged Music Data.
Year: 2011
Type: article
Abstract: Due to the cold-start problem, measuring the similarity be-tween two pieces of audio music based on their low-level acoustic features is critical to many Music Information Re-trieval (MIR) systems. In this paper, we apply the bag-of-frames (BOF) approach to represent low-level acoustic fea-tures of a song and exploit music tags to help improve the performance of the audio-based music similarity computa-tion. We first introduce a Gaussian mixture model (GMM) as the encoding reference for BOF modeling, then we pro-pose a novel learning algorithm to minimize the similarity gap between low-level acoustic features and music tags with respect to the prior weights of the pre-trained GMM. The results of audio-based query-by-example MIR experi-ments on the MajorMiner and Magnatagatune datasets demonstrate the effectiveness of the proposed method, which gives a potential to guide MIR systems that employ BOF modeling. 1.
Institutions: Academia Sinica, National Taiwan University
Language: English
Topic: Music and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2296587773