@INPROCEEDINGS{Muller2012c,
  author = {Florian M{\"u}ller and Alfred Mertins},
  title = {Dereverberation with an Iterative Least-Squares Technique and Minimum
	Mean-Square Error Estimation for Automatic Speech Recognition},
  booktitle = {Proc. ITG Fachtagung Sprachkommunikation},
  year = {2012},
  address = {Braunschweig, Germany},
  month = {Sept.}
}

@INPROCEEDINGS{Muller2012b,
  author = {Florian M{\"u}ller and Alfred Mertins},
  title = {Enhancing Vocal Tract Length Normalization with Elastic Registration
	for Automatic Speech Recognition},
  booktitle = {Proc. Interspeech-2012},
  year = {2012},
  pages = {},
  address = {Portland, USA},
  month = {Sept.}
}

@INPROCEEDINGS{Muller2012a,
  author = {Florian Müller and Alfred Mertins},
  title = {On the Use of a Wave-Reflection Model for the Estimation of Spectral
	Effects due to Vocal Tract Length Changes with Application to Automatic
	Speech Recognition},
  booktitle = {Proc. 38th German Annual Conference on Acoustics (DAGA 2012)},
  year = {2012},
  address = {Darmstadt, Germany},
  month = {Mar.}
}

@INPROCEEDINGS{Muller2012,
  author = {Florian Müller and Alfred Mertins},
  title = {On Using the Auditory Image Model and Invariant-Integration for Noise
	Robust Automatic Speech Recognition},
  booktitle = {Proc. Int. Conf. Audio, Speech, and Signal Processing},
  year = {2012},
  address = {Kyoto, Japan},
  pages = {4905-4908},
  month = {Mar.}
}

@INPROCEEDINGS{Muller2011a,
  author = {Florian M{\"u}ller and Alfred Mertins},
  title = {Robust Continuous Speech Recognition through Combination of Invariant-Feature
	Based Systems},
  booktitle = {Proc. German Conf. Speech Signal Processing (ESSV 2011)},
  year = {2011},
  pages = {229-236},
  address = {Aachen, Germany},
  month = {Sept.}
}

@INPROCEEDINGS{Muller2011b,
  author = {Florian Müller and Alfred Mertins},
  title = {Noise Robust Speaker-Independent Speech Recognition with Invariant-Integration
	Features Using Power-Bias Subtraction},
  booktitle = {Proc. Interspeech-2011},
  year = {2011},
  pages = {1677-1680},
  address = {Florence, Italy},
  month = {Aug.}
}

@ARTICLE{Muller2011,
  author = {Florian Müller and Alfred Mertins},
  title = {Contextual invariant-integration features for improved speaker-independent
	speech recognition},
  journal = {Speech Communication},
  year = {2011},
  volume = {53},
  pages = {830 - 841},
  number = {6},
  abstract = {This work presents a feature-extraction method that is based on the
	theory of invariant integration. The invariant-integration features
	are derived from an extended time period, and their computation has
	a very low complexity. Recognition experiments show a superior performance
	of the presented feature type compared to cepstral coefficients using
	a mel filterbank (MFCCs) or a gammatone filterbank (GTCCs) in matching
	as well as in mismatching training-testing conditions. Even without
	any speaker adaptation, the presented features yield accuracies that
	are larger than for MFCCs combined with vocal tract length normalization
	(VTLN) in matching training-test conditions. Also, it is shown that
	the invariant-integration features (IIFs) can be successfully combined
	with additional speaker-adaptation methods to further increase the
	accuracy. In addition to standard MFCCs also contextual MFCCs are
	introduced. Their performance lies between the one of MFCCs and IIFs.},
  doi = {http://dx.doi.org/10.1016/j.specom.2011.02.002},
  issn = {0167-6393},
  keywords = {Speech recognition}
}

@INPROCEEDINGS{Condurache2010,
  author = {A. P. Condurache and F. Müller and A. Mertins},
  title = {An LDA-based relative hysteresis classifier with application to segmentation
	of retinal vessels},
  booktitle = {Proc. Int. Conf. Pattern Recognition (ICPR)},
  year = {2010},
  address = {Istanbul, Turkey},
  month = {Sept.},
  pages = {4202--4205},
  abstract = {In a pattern classification setup, image segmentation is achieved
	by assigning each pixel to one of two classes: object or background.
	The special case of vessel segmentation is characterized by a strong
	disproportion between the number of representatives of each class
	(i.e. class skew) and also by a strong overlap between classes. These
	difficulties can be solved using problem-specific knowledge. The
	proposed hysteresis classification makes use of such knowledge in
	an efficient way. We describe a novel, supervised, hysteresisbased
	classification method that we apply to the segmentation of retina
	photographies. This procedure is fast and achieves results that comparable
	or even superior to other hysteresis methods and, for the problem
	of retina vessel segmentation, to known dedicated methods on similar
	data sets.}
}

@INPROCEEDINGS{Muller2010a,
  author = {Florian M{\"u}ller and Alfred Mertins},
  title = {Invariant Integration Features Combined with Speaker-Adaptation Methods},
  booktitle = {Proc. Int. Conf. Spoken Language Processing (Interspeech 2010-ICSLP)},
  year = {2010},
  address = {Makuhari, Japan},
  month = {Sept.},
  pages = {2622--2625},
  abstract = {Speaker-normalization and -adaptation methods are essential components
	of state-of-the-art speech recognition systems nowadays. Recently,
	so-called invariant integration features were presented which are
	motivated by the theory of invariants. While it was shown that the
	integration features outperform MFCCs when used with a basic monophone
	recognition system, it was left open, if their benefits still can
	be observed when a more sophisticated recognition system with speaker-normalization
	and/or speaker-adaptation components is used. This work investigates
	the combination of the integration features with standard speaker-normalization
	and -adaptation methods. We show that the integration features benefit
	from adaptation methods and significantly outperform MFCCs in matching,
	as well as in mismatching training-test conditions.},
  keywords = {Speaker independency, invariant integration, speaker normalization, speaker adaptation}
}

@INPROCEEDINGS{Muller2010,
  author = {Florian Müller and Alfred Mertins},
  title = {Robust Features for Speaker-Independent Speech Recognition Based
	on a Certain Class of Translation-Invariant Transformations},
  booktitle = {Advances in Nonlinear Speech Processing},
  year = {2010},
  editor = {Jordi Sole-Casals and Vladimir Zaiats},
  volume = {5933},
  series = {LNAI},
  pages = {111-119},
  address = {Heidelberg, Germany},
  month = {Feb.},
  publisher = {Springer},
  isbn = {978-3-642-11508-0}
}

@INPROCEEDINGS{Muller2009b,
  author = {Florian Müller and Eugene Belilovsky and Alfred Mertins},
  title = {Generalized Cyclic Transformations in Speaker-Independent Speech Recognition},
  booktitle = {Proc. 2009 IEEE Automatic Speech Recognition and Understanding Workshop},
  year = {2009},
  address = {Merano, Italy},
  month = {Dec. 13-17}
}

@INPROCEEDINGS{Muller2009a,
  author = {Florian Müller and Alfred Mertins},
  title = {Invariant-integration method for robust feature extraction in speaker-independent
	speech recognition},
  booktitle = {Proc. Interspeech 2009},
  year = {2009},
  address = {Brighton},
  month = {Sept.}
}

@INPROCEEDINGS{Muller2009,
  author = {Florian Müller and Alfred Mertins},
  title = {Nonlinear translation-invariant transformations for speaker-independent
	speech recognition},
  booktitle = {ISCA Tutorial and Research Workshop on Non-Linear Speech Processing (NOLISP'09)},
  year = {2009},
  address = {Vic, Spain},
  month = {Jun.}
}

@INPROCEEDINGS{Kabus2008,
  author = {Sven Kabus and Florian Müller and Rafael Wiemker and Bernd Fischer},
  title = {Robust lung nodule growth measurement by combining registration and
	segmentation},
  booktitle = {Proceedings of the First International Workshop on Pulmonary Image
	Analysis},
  year = {2008},
  pages = {15 -- 23},
  address = {New York, USA},
  month = {Sept.}
}