Roland Maas

Lehrstuhl für Multimediakommunikation und Signalverarbeitung (LMS) Professur für Signalverarbeitung

Multi-style training of HMMS with stereo data for reverberation-robust speech recognition (2011) Sehr A, Hofmann C, Maas R, Kellermann W Conference contribution, Conference Contribution Extension of the remos concept to frequency-filtering-based features for reverberation-robust speech recognition (2011) Maas R, Wolf M, Sehr A, Nadeu C, Kellermann W Conference contribution, Conference Contribution Frame-wise HMM adaptation using state-dependent reverberation estimates (2011) Sehr A, Maas R, Kellermann W Conference contribution, Conference Contribution Reverberation Modeling for Robust Speech Recognition (2011) Maas R, Sehr A, Kellermann W Conference contribution Multi-Style Reverberation Models and Efficient Model Adaptation for Robust Distant-Talking Speech Recognition with REMOS (2010) Maas R, Sehr A, Kellermann W Conference contribution A novel approach for matched reverberant training of HMMs using data pairs (2010) Sehr A, Hofmann C, Maas R, Kellermann W Conference contribution, Conference Contribution Reverberation model-based decoding in the logmelspec domain for robust distant-talking speech recognition (2010) Sehr A, Maas R, Kellermann W Journal article, Original article A highly efficient optimization scheme for remos-based distant-talking speech recognition (2010) Maas R, Sehr A, Gugat M, Kellermann W Conference contribution, Conference Contribution Towards a better understanding of the effect of reverberation on speech recognition performance (2010) Sehr A, Habets E, Maas R, Kellermann W Conference contribution Model-based dereverberation in the logmelspec domain for robust distant-talking speech recognition (2010) Sehr A, Maas R, Kellermann W Conference contribution, Conference Contribution