Speech processing applications such as speech enhancement and speaker identification rely on the estimation of relevant parameters from the speech signal. Theseparameters must often be estimated from noisy observations since speech signals arerarely obtained in ‘clean’ acoustic environments in the real world. As a result, theparameter estimation algorithms we employ must be robust to environmental factorssuch as additive noise and reverberation. In this work we derive and evaluate approximate Bayesian algorithms for the following speech processing tasks: 1) speechenhancement 2) speaker identification 3) speaker verification and 4) voice activitydetection.




File list:
2011-thesis-Approximate Bayesian Inference for Robust Speech Processing-Maina_PhD.pdf