CONF valente:ICASSP:2007/IDIAP Combination of Acoustic Classifiers based on Dempster-Shafer Theory of evidence Valente, Fabio Hermansky, Hynek EXTERNAL https://publications.idiap.ch/attachments/papers/2007/valente-ICASSP-2007.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/valente:rr06-61 Related documents IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP) 2007 IDIAP-RR 06-61 In this paper we investigate combination of neural net based classifiers using Dempster-Shafer Theory of Evidence. Under some assumptions, combination rule resembles a product of errors rule observed in human speech perception. Different combination are tested in ASR experiments both in matched and mismatched conditions and compared with more conventional probability combination rules. Proposed techniques are particularly effective in mismatched conditions. REPORT valente:rr06-61/IDIAP Combination of Acoustic Classifiers based on Dempster-Shafer Theory of evidence Valente, Fabio Hermansky, Hynek EXTERNAL https://publications.idiap.ch/attachments/reports/2006/valente-idiap-rr-06-61.pdf PUBLIC Idiap-RR-61-2006 2006 IDIAP Published in ICASSP 2007 In this paper we investigate combination of neural net based classifiers using Dempster-Shafer Theory of Evidence. Under some assumptions, combination rule resembles a product of errors rule observed in human speech perception. Different combination are tested in ASR experiments both in matched and mismatched conditions and compared with more conventional probability combination rules. Proposed techniques are particularly effective in mismatched conditions.