This paper presents an investigation of what is gained in the process of dictionary creation by using a speech reference corpus of one million words in conjunction with a huge written reference corpus. It also analyses how much additional effort this requires. Collecting spoken data takes a great deal of effort, and existing speech corpora are rather insignificant in size compared to written corpora, which represent the main and often only source of lexicographic information. However, it is clear that the use of spoken and written language differs with regard to lexical patterns and collocations, and that written corpora, irrespective of their size and structure, cannot provide sufficient data for the description of lexical features in spoken language use. The results demonstrate that even a small speech corpus of one million words provides additional information about the most common, the most general and the most typical spoken usages.
COBISS.SI-ID: 19374870
The authors introduce a flexible and efficient algorithm and a novel system used for the planning, generation, and realization of conversational behavior (co-verbal behavior). Such behavior is best described as a set of moving body parts, which are meaningful. In terms of prosody, it is synchronized with the accompanying speech. The movement and shapes generated as a co-verbal behavior represent a contextual link between a repertoire of independent motor skills (shapes, movements, and poses that conversational agent can reproduce and execute), and the intent/meaning of spoken sequences (context). The actual intent/meaning of spoken content is identified through language-dependent linguistic markers and prosody. The knowledge databases used to determine the intent/meaning of text are based on the linguistic analysis and classification of the text into semiotic classes and subclasses achieved through annotation of multimodal corpora based on the proposed EVA annotation scheme. The scheme allows for capturing features at a functional (context-dependent), as well as at a descriptive (context-independent) level. The functional level captures high-level features that describe the correlation between speech and co-verbal behavior, whereas the descriptive level allows us to capture and define body-poses and shapes independently of verbal content and in high-resolution. The annotation scheme, therefore, not only interlinks speech and gesture at a semiotic level, but also serves as a basis for the creation of a context independent repertoire of movement and shapes.
COBISS.SI-ID: 19378454
The book covers language modeling and automatic speech recognition for inflective languages (e.g. Slavic languages), which represent roughly half of the languages spoken in Europe. These languages do not perform as well as English in speech recognition systems and it is therefore harder to develop an application with sufficient quality for the end user. The authors describe the most important language features for the development of a speech recognition system. This is then presented through the analysis of errors in the system and the development of language models and their inclusion in speech recognition systems, which specifically address the errors that are relevant for targeted applications. The error analysis is done with regard to morphological characteristics of the word in the recognized sentences. The book is oriented towards speech recognition with large vocabularies and continuous and even spontaneous speech. Today such applications work with a rather small number of languages compared to the number of spoken languages.
COBISS.SI-ID: 19856918
Implementation of a reliable maximum power point tracking design as an analog circuit for use on a satellite relying on solar power generation within low Earth orbit is presented. The environment in which such a spacecraft system would function is evaluated. A specific maximum power point tracking algorithm is selected with regards to environmental constraints. A further increase in reliability was achieved by only using carefully selected analog components that are suitable for use within a space environment. The system was prototyped, and its power conversion performance was characterized using a custom-built measurement setup.
COBISS.SI-ID: 19384598
Advanced approach for implementing radiation protection for Fault Detection, Isolation and Recovery techniques designed especially for nanosatellites is presented, capable of ensuring reliable operation in harsh orbits using Commercial off the Shelf components. In order to assure reliable operation, the protection policy is split into two levels: the Low Level, which ensures that no permanent damage occurs to the satellite's electronics, which then allows the use of a High Level tasked with maintaining high availability. A hierarchical approach, consisting of three types of current limiters in combination with fault tolerant logic is proposed. The impacts of various radiation-induced faults are analyzed with respect to proposed techniques to mitigate them.
COBISS.SI-ID: 20037398