no code implementations • 4 Aug 2016 • Christian Huemmer, Ramón Fernández Astudillo, Walter Kellermann
In this paper, we advance a recently-proposed uncertainty decoding scheme for DNN-HMM (deep neural network - hidden Markov model) hybrid systems.
no code implementations • 14 Apr 2016 • Christian Huemmer, Christian Hofmann, Roland Maas, Walter Kellermann
In this article, we present the elitist particle filter based on evolutionary strategies (EPFES) as an efficient approach for nonlinear system identification.
no code implementations • 18 Nov 2014 • Christian Huemmer, Roland Maas, Walter Kellermann
In this article, we derive a new stepsize adaptation for the normalized least mean square algorithm (NLMS) by describing the task of linear acoustic echo cancellation from a Bayesian network perspective.
no code implementations • 9 Oct 2014 • Andreas Schwarz, Christian Huemmer, Roland Maas, Walter Kellermann
We propose a spatial diffuseness feature for deep neural network (DNN)-based automatic speech recognition to improve recognition accuracy in reverberant and noisy environments.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 11 Oct 2013 • Roland Maas, Christian Huemmer, Armin Sehr, Walter Kellermann
This article provides a unifying Bayesian network view on various approaches for acoustic model adaptation, missing feature, and uncertainty decoding that are well-known in the literature of robust automatic speech recognition.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2