Title :
Probabilistic state mapping as a model for speech production
Author :
Kalgaonkar, Kaustubh ; Clements, Mark A.
Author_Institution :
Sch. of ECE, Georgia Inst. of Technol., Atlanta, GA, USA
Abstract :
The model has been successfully applied to bandwidth expansion and speech enhancement. We are in the process of evaluating the performance of the model for automatic speech recognition in noisy environments. This probabilistic model shows great generality and can be applied to other problems such as speech modification and speaker separation.
Keywords :
probability; speech enhancement; speech recognition; automatic speech recognition; bandwidth expansion; probabilistic state mapping; speaker separation; speech enhancement; speech modification; speech production; Bandwidth; Filtering; Graphical models; Hidden Markov models; Narrowband; Nonlinear filters; Parameter estimation; Signal mapping; Speech processing; Subspace constraints;
Conference_Titel :
Signals, Systems and Computers, 2009 Conference Record of the Forty-Third Asilomar Conference on
Conference_Location :
Pacific Grove, CA
Print_ISBN :
978-1-4244-5825-7
DOI :
10.1109/ACSSC.2009.5470197
