Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery

This work tackles the problem of learning a set of language specificacoustic units from unlabeled speech recordings given aset of labeled recordings from other languages. Our approachmay be described by the following two steps procedure: firstthe model learns the notion of acoustic units from the labelleddata and then the model uses its knowledge to find new acousticunits on the target language. We implement this processwith the Bayesian Subspace Hidden Markov Model (SHMM), amodel akin to the Subspace Gaussian Mixture Model (SGMM)where each low dimensional embedding represents an acousticunit rather than just a HMMs state. The subspace is trainedon 3 languages from the GlobalPhone corpus (German, Polishand Spanish) and the AUs are discovered on the TIMIT corpus.Results, measured in equivalent Phone Error Rate, show thatthis approach significantly outperforms previous HMM basedacoustic units discovery systems and compares favorably withthe Variational Auto Encoder-HMM.