Multimodal machine learning is a vibrant multi-disciplinary research field which addresses some of the original goals of artificial intelligence by integrating and modeling multiple communicative modalities, including linguistic, acoustic and visual messages. With the initial research on audio-visual speech recognition and more recently with language & vision projects such as image and video ca...

In this paper there are presenting solutions for increasing environmental robustness of a Romanian language continuous speech recognizer, previously built [1], [2] as a man-machine dialogue system. Multistyle training strategy is used to train the recognizer with various levels of artificial noise added on the clean speech. Experimental results prove that this scheme strongly increase the syste...

Artificial talkers and speech synthesis systems have long been used as a means of understanding both speech production and speech perception. This article begins with an overview and history of artificial speech systems which includes mechanical models, electronic devices, and computationbased simulations. The development of an airway modulation model is then described that simulates the time-v...

Many problems related to analysis and recognition of sound signals are characterized by the fact that finding the proper analysis rule or the proper recognition algorithm is very difficult. In addition the signal analysis methods and the methods of its recognition must be strictly adapted to the specific features of the particular task considered. It is worth noticing, that the situation is ess...

Your use of the JSTOR archive indicates your acceptance of JSTOR's Terms and Conditions of Use, available at http://www.jstor.org/page/info/about/policies/terms.jsp. JSTOR's Terms and Conditions of Use provides, in part, that unless you have obtained prior permission, you may not download an entire issue of a journal or multiple copies of articles, and you may use content in the JSTOR archive o...

A few years ago I undertook a new speech understanding research project, aiming to explore innovative techniques rather than pursue short-term results. My method was to build on the classic 1970s AI approaches to speech, as an alternative to the current mainstream speech understanding research methods. This led to a system that was competitive, both in elegance and performance, with other recen...

Introduction The problem-solving literature that arose in the 1960s and 1970s in the promising and exciting field of artificial intelligence has had a profound impact on Design Methodology. The introduction of these theories in Design Methodology, at the start of the 1970s, helped to systemize the models and methods of design existing then, and link them to models of problem solving in other fi...

In attempting to build an effective speech recognition infrastructure, there are several core challenges. First and foremost, such a system needs to be able to translate from spoken commands to function calls on specific agents. In doing do, it needs to use information from spoken statements to route commands to the appropriate agents. Additionally, in processing such commands, the infrastructu...

Speech recognition by machine has not yet been achieved because no suitable specification of the recognition process has been formulated for the machine. The author outlines the disturbances and constraints found in speech, and goes on to a description of the structure implied by the constraints. This description is a prerequisite of speech recognition for two reasons, first to describe general...

Artificial talkers and speech synthesis systems have long been used as a means of understanding both speech production and speech perception. The development of an airway modulation model is described that simulates the time-varying changes of the glottis and vocal tract, as well as acoustic wave propagation, during speech production. The result is a type of artificial talker that can be used t...