We propose a new generative model for polyphonic music based on nonlinear Independent Subspace Analysis (ISA) and factorial Hidden Markov Models (HMM). ISA represents chord spectra...
We significantly improve the computational efficiency of a probabilistic approach for multiple pitch tracking. This method is based on a factorial hidden Markov model and two al...
Recognition of chatting activities in social interactions is useful for constructing human social networks. However, the existence of multiple people involved in multiple dialogue...
Deep belief networks are a powerful way to model complex probability distributions. However, it is difficult to learn the structure of a belief network, particularly one with hidd...
Ryan Prescott Adams, Hanna M. Wallach, Zoubin Ghah...
We propose statistical predicate invention as a key problem for statistical relational learning. SPI is the problem of discovering new concepts, properties and relations in struct...