1,720,974 research outputs found
The development of phonetic dictionary and language model for latvian speech processing
No full textDarbā tika pētītas divas no svarīgākajām sastāvdaļām ir valodas modelis un fonētiskā vārdnīca. Analizēta četru dažādu tekstu korpusu un to apvienojumu ietekme uz runas atpazīšana kvalitāti latviešu valodā. Testētas trīs dažādas fonētiskās izrunas ieguves metodes. Iegūtais rezultāts ir valodas atkarīgs, bet izmantotās metodes ir valodas neatkarīgas. Bāzlīnijas nepārtrauktas runas atpazīšanas sistēmas precizitāte ir 36.17%. Pēc uzlabojumu veikšanas precizitāte paaugstinājās par 6.45%, no 36.17% uz 42.62%. Lai gan labākie rezultāti tika sasniegti ar bāzlīnijas metodēm, darba izstrādes laikā iegūtās zināšanas ļaus pilnveidot bāzlīnijā izmantoto metožu kvalitāti.
Atslēgvārdi: runas atpazīšanas sistēmas, runas atpazīšana process, valodas modeļi, fonētiskā vārdnīca.The study investigated two of the most important components of speech processing - a language model and phonetic dictionary. Comparison of four different text corpora and their combination was done to estimate language model impact on Latvian speech recognition. Three different phonetic pronunciation extraction methods were tested. The result is language dependent, but the methods used are language independent. The baseline for continuous speech recognition system is 36.17%. After improvement the accuracy increased by 6:45% from 36.17% to 42.62%. Although the best results were achieved with the baseline methods, the knowledge gained in method development will help to improve the quality of the methods used in the baseline.
Keywords: speech recognition systems, speech recognition, language modeling, graphe-to-phoneme modelation
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
The Analysis and Development of the Card Game Klondike
No full textAr katru dienu dažādas datorspēles kļūst aizvien populārākas bērnu vidū, bet nevienam nepatīk spēlēt spēles, kurās nevar uzvarēt. Šajā kvalifikācijas darbā ir aprakstīta kāršu spēles „Klondaikas pasjanss” (no angļu val. Klondike Solitaire) analīzes sistēma, ar kuras palīdzību varētu atrast izspēlējamus sadalījumus, lai varētu piedāvāt lietotājiem spēlēt tikai uzvaramas situācijas. Sistēma sagatavo arī plašākus datus par analīzes rezultātiem, kurus apstrādājot, varētu atrast kritērijus, pēc kuriem noteikt sadalījuma grūtības pakāpi.
Darba pasūtītājs un izstrādātājs ir darba autors. Programma izstrādāta VB.NET valodā, izmantojot „Microsoft .NET 4.5” ietvaru.
Atslēgvārdi: VB.NET, Klondaikas pasjanss, kāršu spēle, analīzeEvery day computer games become more popular amongst children. Though, nobody likes to play games which cannot be won. The system discussed in this written work offers to play only the card deals of card game called Klondike Solitaire which can be won. The system also creates wide broad of analytics data which could provide the criterion for finding out the difficulty of the deal.
The developer and customer is the same person. The program has been developed on .Microsoft NET 4.5 framework using VB.NET programming language.
Key words: VB.NET, Klondike Solitaire, card game, analytic
Clustering algorithms for large scale data sets
No full textMūsdienās, strauji pieaugot internetā pieejamajam informācijas apjomam, aktuāla tēma valodu tehnoloģiju jomā ir informācijas grupēšana (klasterēšana) pēc vienotiem principiem vieglākai informācijas uztveramībai un izkaisītas informācijas apjoma mazināšanai. Darbā "Liela apjoma datu kopu klasterēšanas algoritmi" teorētiskajā daļā izpētītas un apkopotas metodes dokumentu klasterēšanai ar mērķi atrast piemērotāko metodi vai metožu kopu daudzvalodu ziņu straumju klasterēšanai. Darbā arī pētītas un salīdzinātas dažādas klasterēšanas rezultāta novērtēšanas metrikas. Praktiskajā daļā izstrādāta un izvērtēta sistēma daudzvalodu ziņu straumju klasterēšanai, tā darbības rezultāti un turpmāki pētījuma virzieni apkopoti darba nobeigumā.Nowadays one of the current trends of language technologies is information clustering with common traits for simplified information perception and reduction of scattered information amount in the continuous large information flow. Study "Clustering algorithms for large scale data sets" theoretical part includes research of the methods used in document clustering. The goal is to find the most suitable method or set of methods for multilingual message stream clustering. The work also contains research and comparison of various metrics of clustering result evaluation. The practical part includes implementation and evaluation of the system for multilingual news clustering. The results and future research directions are included in the end of the work
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
The training of end-to-end text-to-speech synthesis model for Latvian language
No full textBakalaura darbā tiek izpētītas un aprakstītas dažādas runas sintēzes tehnoloģijas, no kurām padziļināti tiek apskatītas neirona tīklu bāzētās tehnoloģijas un to pilnīgie runas sintēzes modeļi, ņemot vērā pēdējo gadu straujo attīstību mašīnmācīšanās tehnoloģijās. Pilnīgi runas sintēzes modeļi parasti tiek trenēti uz angļu valodas datu kopas un reti tiek trenēti uz citu valodu datiem. Darba laikā tiek veikta pilnīga runas sintēzes modeļa trenēšana uz latviešu valodas audio ierakstiem un tiek izveidots pirmās fāzes StyleTTS 2 runas sintēzes modelis. Otrās fāzes trenēšanas laikā tiek konstatēta kļūda modeļu trenēšanā, pēc kuras tiek uzsākta kļūdas cēloņa noteikšana, kuras laikā tiek atrastas nepilnības runas sintēzes piedāvātā modelī fonēmas līmeņa BERT modelī, kuru ir nepieciešams izveidot latviešu valodai, lai turpinātu StyleTTS 2 runas sintēzes modeļa trenēšanu.In this bachelor thesis different speech synthesis technologies are researched and described of which neural network-based technologies and their complete speech synthesis models are discussed in depth, taking into account the rapid advances in machine learning technologies in recent years. Full speech synthesis models are usually trained on English language datasets and rarely trained on non-English language datasets. In this work we train a full speech synthesis model on Latvian audio recordings and build a first phase StyleTTS 2 speech synthesis model. During the second phase training an error is detected in the model training, after which the determination of the cause of the error is initiated, during which gaps in the proposed model of speech synthesis are found in the phoneme-level BERT model, which needs to be created for Latvian in order to continue training the StyleTTS 2 speech synthesis mod
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
- …
