Search

Time–frequency representations of the speech signals provide dynamic information about how the frequency component changes with time. In order to process this information, deep learning models with convolution layers can be used to obtain feature maps. In many speech processing applications, the time–frequency representations are obtained by applying the short-time Fourier transform and using single-channel input tensors to feed the models. However, this may limit the potential of convolutional networks to learn different representations of the audio signal. In this paper, we propose a methodology to combine three different time–frequency representations of the signals by computing continuous wavelet transform, Mel-spectrograms, and Gammatone spectrograms and combining then into 3D-channel spectrograms to analyze speech in two different applications: (1) automatic detection of speech deficits in cochlear implant users and (2) phoneme class recognition to extract phone-attribute features. For this, two different deep learning-based models are considered: convolutional neural networks and recurrent neural networks with convolution layers.

Parkinson’s disease is a progressive neurological disorder that affects the motor system and produces several problems to control muscles and limbs. One of the major manifestations of the disease appears in gait and typically causes disability in the most advanced stages of the disease. Gait assessment is suitable for the diagnosis and monitoring of the neurological state of the patients. Gait is mainly evaluated from signals collected with inertial sensors attached to the limbs, and kinematics features are commonly extracted. Besides the classical kinematic methods, there are nonlinear phenomena in the gait process that cannot be properly modeled with kinematic features. This study proposes the use of several nonlinear dynamics features to assess gait impairments of Parkinson’s patients. We consider classical nonlinear features including correlation dimension, largest Lyapunov exponent, Hurst exponent, and others. In addition, we propose a novel nonlinear analysis based on the construction of Gaussian mixture models to find clusters in Poincare sections. The nonlinear dynamics features proposed here are used to discriminate between Parkinson’s patients and healthy subjects, and to classify patients in different stages of the disease. To the best of our knowledge, this is the first study that considers nonlinear dynamics analysis including Poincare sections to assess gait impairments of patients with Parkinson’s disease.

Patients with chronic laryngitis and T1 vocal cord cancer were compared using perceptual and text-based objective voice and speech analyses in order to determine which group is more affected in its ability to communicate and whether a distinction between the two pathologies is possible.In all, 13 patients with histologically proven chronic laryngitis and 13 patients with T1 vocal cord cancer were compared perceptually by five speech therapists on the basis of seven criteria and objectively by a speech recognition system and prosodic analysis.Both, the data of the five speech therapists and the results of the automatic analysis revealed no significant differences between the two patient groups.A distinction between chronic laryngitis and T1 vocal cord carcinoma by mere voice and speech analysis is not possible, because the patient groups do not show significant differences in their voice quality.

Hintergrund In dieser Studie wird ein objektives Verfahren fur die Verstandlichkeitsmessung mit dem Postlaryngektomie-Telefontest (PLTT) mittels automatischer Spracherkennungstechnik beschrieben.

Hintergrund Spaltfehlbildungen konnen trotz adaquater Behandlung funktionelle Beeintrachtigungen, z. B. Lautbildungsstorungen, verursachen. Diese variieren individuell stark. Typisch sind z. B. veranderte nasale Luftfuhrung und verlagerte Artikulation, die zu einer verminderten Verstandlichkeit fuhren. Ein Zusammenhang zwischen der Art der Spaltfehlbildung und der Verstandlichkeit konnte bisher nur durch kategoriale, subjektive Bewertungen beschrieben werden. In dieser Studie wird die spaltabhangige Verstandlichkeit erstmals objektiv und numerisch mittels automatischer Spracherkennungstechnik quantifiziert.

This contribution introduces MOBSY, a fully integrated, autonomous mobile service robot system. It acts as an automatic dialogue-based receptionist for visitors to our institute. MOBSY incorporates many techniques from different research areas into one working stand-alone system. The techniques involved range from computer vision over speech understanding to classical robotics. Along with the two main aspects of vision and speech, we also focus on the integration aspect, both on the methodological and on the technical level. We describe the task and the techniques involved. Finally, we discuss the experiences that we gained with MOBSY during a live performance at our institute.

Automatic speech recognition and understanding has been subject to intensive research for several decades. A few years ago, the first commercial applications for the technology resulting from these efforts began to emerge. It is now obvious that speech recognition technology will soon play an important role in everyday life and also in business. In this paper, we outline the basic principles of speech recognition technology and analyze its potentials and also its limitations We discuss current and possible future applications, ranging from simple command control systems and dictation systems to natural language dialogue and translation systems.