Common approaches to automatic speech recognition (ASR) are based on training statistical models for the acoustics of speech. In our work, a retrieval-based ASR system is developed that does not rely on training and thus provides more flexible application. It is based on a set of known reference word utterances for each possibly occurring word in a test string. A test word string is identified ...

Speech can lead to increased performance in computer-based problem solving. Studies of complex interaction styles — such as command-line or system-delayed interaction — have found that complex interaction styles can lead to savings in the number of actions users take to reach a solution for certain tasks compared with direct manipulation. Speech can be viewed a complex interaction style because...

While the virtual environments are gaining more success each day there are many usability problems associated with them. The controlling methods, which usually rely heavily on the user’s hands, are one problem. There are situations and user groups in which this is not an acceptable way to use the computer. Here we approach this problem by using speech input. The relatively high error rates are ...

This study investigated whether auditory, speech perception, and phonological skills are tightly interrelated or independently contributing to reading. We assessed each of these three skills in 36 adults with a past diagnosis of dyslexia and 54 matched normal reading adults. Phonological skills were tested by the typical threefold tasks, i.e., rapid automatic naming, verbal short-term memory an...

Besides travel related information driver related information plays an increasing role while driving. In order to process this information and be able to drive safely at the same time, an information management is necessary in the vehicle. Speech interfaces offer a good solution since verbal interactions use resources which are not needed when driving. However, in practice experiments show that...

Since 100 B.C. humans are aware that the language consists of several distinct parts, called parts-of-speech. Identifying those parts-of-speech plays a crucial role in many fields of linguistics. Since TAGGIT, the first large-scale part-of-speech tagger, many algorithms and methods have been developed. Such include rule-based, probabilistic and hybrid taggers. When tagging large text corpora so...

In this paper, a wavelet transform domain realization of the blind equalization technique termed as EVA is applied to speech analysis. The conventional linear prediction problem can be viewed as a constrained blind equalization problem. Because the EVA does not impose any restriction to the probability distribution in the input (the glottal excitation), the principal features of speech can be e...

Automatic speech recognition lacks the ability to integrate contextual knowledge into its optimization process – a resource that human speech perception makes extensive use of. We discuss shortcomings of current approaches to solve this problem, formalize the problem of context-aware speech recognition and understanding and introduce a robot navigation game that can be used to demonstrate and e...

Single microphone speech enhancement systems have typically shown limited performance, while multiple microphone systems based on a least-squares error criterion have shown encouraging results in some contexts. In this paper we formulate a new approach to multiple microphone speech enhancement. Specifically, we formulate a maximum likelihood (ML) problem for estimating the parameters needed for...

oronasal region, as an important organ of taste and smell, being respected for its impact on the resonace, which is crucial for any normal speech production. different congenital, acquired and/or developmentalpdefect, may not only have impacts on the quality of respiration, phonation, resonance, also on the process of a normal speech. this article will enable readers to have more focus in such ...