A hybrid signal-feature system for music discovery (or finding needles in haystacks)

Ramin Samadani, Amir Said, Debargha MukherjeeProceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE 2003 · DOI

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.
BibTeX
@inproceedings{samadani2003hybrid,
  author = {Ramin Samadani and Amir Said and Debargha Mukherjee},
  title = {{A hybrid signal-feature system for music discovery (or finding needles in haystacks)}},
  booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
  year = {2003},
  doi = {10.1117/12.476454},
}

Loading related content...

Figure