Corneliu Burileanu

A general approach to analysis of distributed resistive structures

A new general method for calculation of thin-film-distributed resistive structures is presented. This method is based on the conformal mapping of the analyzed domain on the complex upper half-plane and the determination of the complex potential function as the solution of a boundary-values Volterra problem. Although the method inherently applies only to single-connected domains with known conformal representations on the upper half-plane, it may be extended also to other symmetrical multiple-connected configurations and in all cases when the positions of the conducting terminals in the upper half-plane are known. Two examples of application are given.

An Adaptive and Fast Speech Detection Algorithm

The detection of speech from silence (actually background noise) is essential in many speech-processing systems.In real-field applications, the correct determination of voice segments highly improves the overall system accuracy and minimises the total computation time.This paper1 presents a novel robust and reliable speech detection algorithm to be used in a speaker recognition system. The paper first introduces some basic concepts on speech activity detection and reviews the techniques currently used in speech detection tasks.Then, the proposed speech/non-speech detection algorithm is described and experimental results are discussed. Conclusions about the algorithm performances are finally presented.

Investigating the role of machine translated text in ASR domain adaptation: Unsupervised and semi-supervised methods

This study investigates the use of machine translated text for ASR domain adaptation. The proposed methodology is applicable when domain-specific data is available in language X only, whereas the goal is to develop a domain-specific system in language Y. Two semi-supervised methods are introduced and compared with a fully unsupervised approach, which represents the baseline. While both unsupervised and semi-supervised approaches allow to quickly develop an accurate domain-specific ASR system, the semi-supervised approaches overpass the unsupervised one by 10% to 29% relative, depending on the amount of human post-processed data available. An in-depth analysis, to explain how the machine translated text improves the performance of the domain-specific ASR, is also given at the end of this paper.

On Performance Improvement of a Speaker Verification System Using Vector Quantization, Cohorts and Hybrid Cohort-World Models

This paper presents the use of distance normalization techniques in order to improve speaker verification system performance. These techniques provide a dynamic threshold that compensates for the trial-to-trial variations and replaces the fixed threshold used in the classical speaker verification approach. Two methods are described: the cohort model normalization and a new and original hybrid cohort-world model normalization. These methods are compared from the point of view of storage space requirements and computational effort. Two algorithms are proposed: one uses existing user models, and the other creates new models. The algorithms were evaluated using the YOHO database and a proprietary database. The results showed that using these methods, the errors of false rejection are significantly reduced for a constant false acceptance error, when the cohort size is increasing. The algorithms also involve fewer computational resources than other algorithms, making them more suitable for commercial application.

Romanian Spoken Language Resources and Annotation for Speaker Independent Spontaneous Speech Recognition

This paper presents studies and early results with the scope to build a robust spontaneous speech recognition system in Romanian language. We have tried to give solutions to several issues that have arisen like building a large and accurate database within a reasonable time. A short description of the database is given and some statistics are collected in order to show its evolution in several stages of the project. Embedded training technique has been used for training triphones. As a consequence, the alignment problem has been studied and a solution is proposed for it. The final purpose of these attempts is to obtain substantial results in speech recognition for Romanian language that can be used as baseline for further results.

SMT-based ASR domain adaptation methods for under-resourced languages: Application to Romanian

This study investigates the possibility of using statistical machine translation to create domain-specific language resources. We propose a methodology that aims to create a domain-specific automatic speech recognition (ASR) system for a low-resourced language when in-domain text corpora are available only in a high-resourced language. Several translation scenarios (both unsupervised and semi-supervised) are used to obtain domain-specific textual data. Moreover this paper shows that a small amount of manually post-edited text is enough to develop other natural language processing systems that, in turn, can be used to automatically improve the machine translated text, leading to a significant boost in ASR performance. An in-depth analysis, to explain why and how the machine translated text improves the performance of the domain-specific ASR, is also made at the end of this paper. As bi-products of this core domain-adaptation methodology, this paper also presents the first large vocabulary continuous speech recognition system for Romanian, and introduces a diacritics restoration module to process the Romanian text corpora, as well as an automatic phonetization module needed to extend the Romanian pronunciation dictionary.

Text spotting in large speech databases for under-resourced languages

Lightly supervised acoustic modeling in under-resourced languages raises new issues due to the poor accuracy of Automatic Speech Recognition (ASR) systems for such languages and the quality of the speech transcriptions that may be found. In these conditions, the common alignment techniques are not always capable of aligning the ASR output and the approximate transcription. We propose two aligning methods that overcome these issues. In the first approach we apply an image processing algorithm on the matching matrix of the two texts to be aligned, while the second alignment approach is based on segmental DTW. The approaches outperform the current Dynamic Time Warping technique (DTW) by extracting in average 29% and 27% respectively more speech data than the currently used DTW.

Logic-based rhetorical structuring for natural language generation in human-computer dialogue

Usually, human-computer dialogue systems rely on ad-hoc solutions for the component performing speech turn generation, in natural language. However, integration of taskspecific and general world knowledge in order to provide a more reliable and natural interaction with humans also through more sophisticated language generation techniques becomes needed. In this paper we present performance improvements of a module simulating in first-order logic Segmented Discourse Representation Theory for language generation in dialogue. These improvements concern reductions in computational costs and enhancements in rhetorical coherence for the discourse structures obtained, and are obtained using speech-act related information for driving rhetorical relations computations.

Multilingual query by example spoken term detection for under-resourced languages

We propose a query-by-example approach to multilingual Spoken Term Detection for under-resourced languages based on Automatic Speech Recognition. The approach overcomes the main difficulties met under these conditions, i.e., providing a new method for building multilingual acoustic models with few annotated data and searching in approximate Automatic Speech Recognition transcriptions providing high scalability. The acoustic models are obtained by adapting well-trained phonemes to the ones from the envisaged languages. The mapping is made according to International Phonetic Alphabet phoneme classification and a confusion matrix. The weighting of query length and alignment spread are incorporated in the Dynamic Time Warping technique to improve the searching method. Experimental validation was conducted on a standard data set consisting of 3 hours of mixed African languages. The recorded speech has telephonic quality and it is a mix of read and spontaneous speech.

Savage16 - 16-bit RISC architecture general purpose microprocessor

This paper describes the architecture and the internal structure of “Savage16”, a fully functional general purpose reduced instruction set microprocessor, with a modified Harvard, five stage pipeline architecture. The memory organization and key architecture elements are being described, as well as the hardware block diagram and the internal structure. A summary of the instruction set is presented, along with a brief description of the addressing modes.