• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • 1
  • Tagged with
  • 2
  • 2
  • 2
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Lietuvių kalbos atpažinimas, panaudojant Julius programinę įrangą / Speech Recognition of Lithuanian Using Julius Software

Braubartas, Ernestas 29 September 2008 (has links)
Signalų technologijų magistro darbo tema yra aktuali, nes nebepakanka įprastų informacijos įvedimo priemonių. Todėl ieškoti ir apdoroti informaciją, valdyti sudėtingus įrenginius ir programas daug patogiau būtų jei kompiuteriai ir įvairūs įrenginiai suprastų žmogaus kalbą. Pasaulyje panašios sistemos kuriamos jau daugelį metų. Tačiau šiuo metu lietuvių kalbos atpažinimo sistemos yra dar tik kūrimo stadijoje. Darbe nagrinėjamas Lietuvių kalbos žodžių atpažinimas skirstant juos į kategorijas ir naudojant paslėptuosius markovo modelius. Šio tyrimo tikslas – ištirti lietuvių kalbos žodžių skirstymo į kategorijas įtaką atpažinimo tikslumui.Taip pat tiriamas žodžių grupių bei pavienių žodžių atpažinimas. Akustinis modelis sukurtas su HTK paketu, kuris naudojasi paslėptųjų Markovo modelių metodika. Žodžių skirstymas į kategorijas aprašytas Backus-Naur formatu. Eksperimentai bus atliekami ir rezultatai gaunami naudojant, Julius programinės įrangos įrankius bei šio paketo, žodžių kategorijų pagrindu veikiančią, Julian kalbos atpažinimo sistemą. Geriausi rezultatai gauti bandant atpažinti pavienius žodžius suskirstytus į kategorijas. Atpažinimo tikslumas siekia 91 %. Bandant atpažinti žodžių sekas, nesuskirstytas į kategorijas, gautas atpažinimo tikslumas tesiekia 51 %. Microsoft Office Word 2003 meniu valdymo atpažinimo tikslumas siekia 82 %. / The theme of Master project of signal technology is actual, because not enough usual information introduction ways. Therefore information search and processing, complicated devices and programs control would be more handily if computers and devices understood human speech. Similar systems are designing for many years in the world. However Lithuanian speech recognition systems are still developing in nowadays. The thesis treats of isolated Lithuanian words recognition dividing them into category and using Hidden Markov Models. The idea of research is to explore categorization of Lithuanian words influence on the accuracy of recognition. The recognition of single words and word groups is under research too. Acoustic model is constructed by using HTK toolkit which is based on Hidden Markov Models. Categorization of words is described with Backus-Naur form. Experiments are made with Julius software speech recognition system Julian witch performs words category based recognition. Best results are got trying to recognize single words set into categories. The accuracy rate of recognition reaches 91 %. While trying to recognize uncategorized word sequences – the accuracy rate of recognition reaches only 51 %. The accuracy rate of Microsoft Office Word 2003 control menu recognition reaches 82 %.
2

CORRELAZIONI TRA SVILUPPO CONCETTUALE NELL'INFANZIA E ACQUISIZIONE DELLA PRIMA LINGUA / Relationships between conceptual development and first language acquisition

VERNICH, LUCA ANTONIO TOMMASO 23 March 2015 (has links)
L'obiettivo del presente lavoro è quello di esaminare criticamente le prospettive teoriche più note sul problema delle relazioni tra sviluppo concettuale del bambino ed acquisizione della prima lingua. Per quanto il lavoro si concentri in particolare sullo sviluppo della componente lessicale, ovvero sul legame tra concetti e apprendimento delle parole con cui gli stessi vengono codificati, verranno necessariamente trattati anche alcuni aspetti relativi alla competenza morfologica e sintattica. Dopo aver presentato sinteticamente le principali teorie proposte nell'ambito della linguistica acquisizionale e della psicologia dello sviluppo, procederemo ad una problematizzazione e discussione dei punti critici delle stesse alla luce dei risultati ottenuti in sede sperimentale negli ultimi anni. Partendo dalla consapevolezza che nell'ambito della linguistica, forse ancor più che in altre discipline, il contrasto tra impostazioni teoriche diverse si traduce spesso in discrepanze significative nell'interpretazione degli stessi dati empirici, abbiamo cercato di dare lo stesso spazio ai vari orientamenti teorici. L'obiettivo di questa tesi, infatti, non è quello di dare giudizi di merito sulla validità di una teoria in quanto tale rispetto ad un'altra, quanto di discutere in modo trasversale i nodi più problematici delle varie teorie e le implicazioni delle stesse. Questo intento è particolarmente evidente nelle conclusioni della tesi, strutturate intorno ad una serie di domande di ricerca. / This work provides a critical overview of the major theoretical perspectives on the relationships between conceptual development and first language acquisition. While our focus is on lexical development (ie. on the relation between learning a word and acquiring the relevant concept), we will also touch on some aspects which pertains more specifically to morphological and syntactical development. After briefly introducing the major theories developed in the field of first language acquisition and developmental psychology, we will discuss them in the light of experimental data collected in recent years. As the same empirical findings tend to be interpreted in completely different ways, in our work we tried to give voice to authors supporting different views. Our goal is not to assess the merits of these theores as such, but to take this comparison as an opportunity to discuss the implications and issues thereof. This will be particularly clear in the Conclusions of our work, which are structured as a series of research questions.

Page generated in 0.106 seconds