Music Fingerprinting Using Finite State Transducers - A Novel Application of FSTs

Explore a novel application of finite state transducer (FST) technology to music fingerprinting in this hour-long conference talk by Pedro J. Moreno, a research scientist at Google. Discover how FSTs, traditionally used in speech applications, can be effectively applied to music fingerprinting with impressive results. Gain insights into the integration of acoustic modeling techniques with FSTs for this purpose. Learn about the speaker's collaborative work with Prof. Mehriar Mohri and Eugene Weinstein at NYU. Additionally, get an overview of current activities in Google's speech team. This presentation, delivered at the Center for Language & Speech Processing (CLSP) at Johns Hopkins University in 2009, offers a unique perspective on the intersection of FST technology and music analysis.

Music Fingerprinting Using Finite State Transducers, a Novel Application of FSTs – Pedro Moreno 2009