Wyniki wyszukiwania - BazTech

1

Effect of Time-domain Windowing on Isolated Speech Recognition System Performance

Ananthakrishna Thalengala, Anitha H., Girisha T.

International Journal of Electronics and Telecommunications

|

2022

|

Vol. 68, No. 1

161--166

EN

Speech recognition system extract the textual data from the speech signal. The research in speech recognition domain is challenging due to the large variabilities involved with the speech signal. Variety of signal processing and machine learning techniques have been explored to achieve better recognition accuracy. Speech is highly non-stationary in nature and therefore analysis is carried out by considering short time-domain window or frame. In the speech recognition task, cepstral (Mel frequency cepstral coefficients (MFCC)) features are commonly used and are extracted for short time-frame. The effectiveness of features depend upon duration of the time-window chosen. The present study is aimed at investigation of optimal time-window duration for extraction of cepstral features in the context of speech recognition task. A speaker independent speech recognition system for the Kannada language has been considered for the analysis. In the current work, speech utterances of Kannada news corpus recorded from different speakers have been used to create speech database. The hidden Markov tool kit (HTK) has been used to implement the speech recognition system. The MFCC along with their first and second derivative coefficients are considered as feature vectors. Pronunciation dictionary required for the study has been built manually for mono-phone system. Experiments have been carried out and results have been analyzed for different time-window lengths. The overlapping Hamming window has been considered in this study. The best average word recognition accuracy of 61.58% has been obtained for a window length of 110 msec duration. This recognition accuracy is comparable with the similar work found in literature. The experiments have shown that best word recognition performance can be achieved by tuning the window length to its optimum value.

2

Wybrane aspekty systemów wywiadu, obserwacji i rozpoznania (ISR)

Matela Kamila

Wiedza Obronna

|

2021

|

nr 3

238--253

PL

Niniejsza praca jest próbą syntetycznego przedstawienia współczesnego rozumienia i zastosowania jednego z kluczowych dla każdej armii na świecie obszarów – wywiadu, obserwacji i rozpoznania (ISR). W artykule dokonano podsumowania najważniejszych aspektów ISR i implementacji tego zagadnienia w siłach zbrojnych Polski i NATO oraz wyzwań z nimi związanych. Z uwagi na znaczący postęp technologiczny zaprezentowano również aspekty techniczne jednego z najszybciej rozwijających się rodzajów rozpoznania i wywiadu – analizy obrazu. Każdy rozdział zawiera odniesienie do polskich sił zbrojnych.

EN

This paper is an attempt to synthetically present the contemporary understanding and application of one of the key areas for any army in the world - intelligence, surveillance and reconnaissance (ISR). The article summarizes the most important aspects of ISR and its implementation in the Polish and NATO armed forces, as well as the challenges associated with them. Due to significant technological progress, technical aspects of one of the fastest growing types of reconnaissance and intelligence - image analysis - are also presented. Each chapter contains a reference to the Polish Armed Forces.

3

Introduction to coastal HF maritime surveillance radars

Ilcev Dimov Stojce

Polish Maritime Research

|

2019

|

nr 3

153--162

EN

This paper presents the main technical characteristics and working performances of coastal maritime surveillance radars, such as low-power High-Frequency Surface Wave Radars (HFSWR) and Over the Horizon Radars (OTHR). These radars have demonstrated to be a cost-effective long-range early-warning sensor for ship detection and tracking in coastal waters, sea channels and passages. In this work, multi-target tracking and data fusion techniques are applied to live-recorded data from a network of oceanographic HFSWR stations installed in Jindalee Operational Radar Network (JORN), Wellen Radar (WERA) in Ligurian Sea (Mediterranean Sea), CODAR Ocean Sebsorsin and in the German Bight (North Sea). The coastal Imaging Sciences Research (ISR) HFSWR system, Multi-static ISR HF Radar, Ship Classification using Multi-Frequency HF Radar, Coastal HF radar surveillance of pirate boats and Different projects of coastal HF radars for vessels detecting are described. Ship reports from the Automatic Identification System (AIS), recorded from both coastal and satellite Land Earth Stations (LES) are exploited as ground truth information and a methodology is applied to classify the fused tracks and to estimate system performances. Experimental results for all above solutions are presented and discussed, together with an outline for future integration and infrastructures.

4

Unmanned aircraft systems in support of the land forces. Selected issues

Zieliński T.

Zeszyty Naukowe / Wyższa Szkoła Oficerska Wojsk Lądowych im. gen. T. Kościuszki

|

2017

|

Nr 2

195--210

EN

The following paper presents selected aspects of the employment of unmanned aircraft systems (UAS) during land force operations, it focuses on its capabilities and constrains. In contemporary operations land forces, mainly UAS of I and II class category, are used in ISR missions, most frequently for the tactical support (armed roles) of land forces. These activities are treated as an additional element of the improvement of situational awareness, they also strengthen fire support. The presented article is based on allied and coalition doctrinal papers associated with unmanned aircraft systems.

5

Molecular dialogue between plant resistance pathways – SAR and ISR

Kulbat K., Szczodrowska A.

Biotechnology and Food Science

|

2014

|

Vol. 78, nr 2

129--139

EN

During normal vegetation, plants are exposed to many stress factors, such as the presence of heavy metal ions in the soil, chemical pesticides, excessive UV radiation or pathogenic microorganisms. In response to local infections, plants activate salicylic or jasmonic acid-dependent signaling pathways. Systemic Acquired Resistance (SAR) and Induced Systemic Resistance (ISR) are two forms of induced resistance. The SAR pathway requires the accumulation of endogenous salicylic acid and provides protection against biotrophic pathogens. ISR requires the biosynthesis of jasmonic acid and protects against necrotrophic pathogens. Based on recent scientific research, cross-talk between SAR and ISR signaling pathways is thought to be involved in whole-plant resistance against a wide range of pathogens.