7 May 2003 A hybrid signal-feature system for music discovery (or finding needles in haystacks)
Author Affiliations +
Abstract
The radio plays a song that you like but that you do not recognize. How do you find the title and the artist? Previous approaches to finding a song in a database are based on pattern recognition. In some of the previous work features are extracted from a hummed song and decision rules are used to retrieve probable candidates from the database. Feature matching has not resulted in reliable searches from microphone samples. In this work, to find the song, we process a short, microphone recorded sample from it. Both a feature vector and a signal are precomputed for each song in a database and also extracted from the recording. The database songs are first sorted by feature distance to the recording. Then, normalized cross-correlation, even though nonlinear, is applied using overlap-save FFT convolution. A decision rule presents likely matches to the user for confirmation but controls the number of false alarms shown. This system, tested using hundreds of recordings, is reliable because signals are matched. The addition of the feature-ordered search and the decision rule result in database searches five times faster than signal matching alone.
© (2003) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ramin Samadani, Amir Said, Debargha Mukherjee, "A hybrid signal-feature system for music discovery (or finding needles in haystacks)", Proc. SPIE 5022, Image and Video Communications and Processing 2003, (7 May 2003); doi: 10.1117/12.476454; https://doi.org/10.1117/12.476454
PROCEEDINGS
6 PAGES


SHARE
Back to Top