Florian Müller

Learn More
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(More)
Trans- translation releases stalled ribosomes from truncated mRNAs and tags defective proteins for proteolytic degradation using transfer-messenger RNA (tmRNA). This small stable RNA represents a hybrid of tRNA- and mRNA-like domains connected by a variable number of pseudoknots. Comparative sequence analysis of tmRNAs found in bacteria, plastids, and(More)
A feature extraction method is presented that is robust against vocal tract length changes. It uses the generalized cyclic transformations primarily used within the field of pattern recognition. In matching training and testing conditions the resulting accuracies are comparable to the ones of MFCCs. However, in mismatching training and testing conditions(More)
The vocal tract length (VTL) is one of the variabilities that speaker-independent automatic speech recognition (ASR) systems encounter. Standard methods to compensate for the effects of different VTLs within the processing stages of the ASR systems often have a high computational effort. By using an appropriate warping scheme for the frequency centers of(More)
The spectral effects of vocal tract length (VTL) changes are one reason of why the recognition rate of today’s speaker-independent automatic speech recognition (ASR) systems is considerably lower than the one of speaker-dependent systems. By using certain types of filterbanks these effects can be described by a translation in subband-index space. In this(More)
The spectral effects of vocal tract length (VTL) differences are one reason for the lower recognition rate of today’s speaker-independent automatic speech recognition (ASR) systems compared to speakerdependent ones. By using certain types of filter banks the VTL-related effects can be described by a translation in subband-index space. In this paper,(More)
This paper presents new results about the robustness of invariantintegration features (IIF) in noisy conditions. Furthermore, it is shown that a feature-enhancement method known as “powerbias subtraction” for noisy conditions can be combined with the IIF approach to improve its performance in noisy environments while keeping the robustness of the IIFs to(More)
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(More)
Vocal tract length normalization (VTLN) is commonly applied utterance-wise with a warping function that makes the assumption of a linear dependence between the vocal tract length and the location of the formants. In this work we propose a datadriven method for enhancing the performance of systems that already use standard VTLN. The method is based on(More)
Foot-and-mouth disease virus (FMDV) uses an internal ribosome entry site (IRES), a highly structured segment of its genomic RNA, to hijack the translational apparatus of an infected host. Computational analysis of 162 type II picornavirus IRES RNA sequences yielded secondary structures that included only base pairs supported by comparative or experimental(More)