In clinical practice, the severity of disordered voice is typically rated by a professional with auditory-perceptual judgment. The present study aims to automate this assessment procedure, in an attempt to make the assessment objective and less laborintensive. In the automated analysis, glottal airflow is estimated from the analyzed voice signal with an inverse filtering algorithm. Automatic as...

This brief presents a simple derivation of the standard model-free control for the non-minimum phase systems. The robustness of the proposed method is studied in simulation considering the case of switched systems. This work is distributed under CC license http://creativecommons.org/licenses/ by-nc-sa/3.0/ ar X iv :1 10 6. 16 97 v1 [ m at h. O C ] 9 J un 2 01 1

The behaviour of the voice source characteristics in connected speech was studied. Voice source parameters were obtained by automatic inverse filtering, followed by automatic fitting of a glottal waveform model to the data. Consistent relations between voice source parameters and prosodic features were observed.

This paper proposes a new perspective on the problem of multidimensional spectral factorization, through helical mapping: ddimensional (dD) data arrays are vectorized, processed by 1D cepstral analysis and then remapped onto the original space. Partial differential equations (PDEs) are the basic framework to describe the evolution of physical phenomena. We observe that the minimum phase helical...

This paper introduces a novel rotation-based framework for arbitrary-oriented text detection in natural scene images. We present the Rotation Region Proposal Networks (RRPN), which is designed to generate inclined proposals with text orientation angle information. The angle information is then adapted for bounding box regression to make the proposals more accurately fit into the text region in ...