Generated by All in One SEO v5.0.0.1, this is an llms.txt file, used by LLMs to index the site.

# ICT Research Blog

by John Salatas

## Posts

- [HandsFree Wear: A wrist gesture input method for Android based smartwatches](https://jsalatas.ictpro.gr/handsfree-wear-a-wrist-gesture-input-method-for-android-based-smartwatches/) - 1. Introduction In this article we will present an Application for interacting with an android wear smartwatch through wrist gestures. As smartwatches are typically worn in the wrist, one would expect a hands-free way of interaction, leaving the other hand free for other activities. Android wear also offers a voice activated interaction, however this wouldn’t
- [Letter to Phoneme Conversion in CMU Sphinx-4: Literature review](https://jsalatas.ictpro.gr/letter-to-phoneme-conversion-in-cmu-sphinx-4-literature-review/) - 1. Foreword Currently Sphinx-4 uses a predefined dictionary for mapping words to sequence of phonemes. I propose modifications in the Sphinx-4 code that will enable it to use trained models (through some king of machine learning algorithm) to map letters to phonemes and thus map words to sequence of phonemes without the need of a
- [Implementation of Elman Recurrent Neural Network in WEKA](https://jsalatas.ictpro.gr/implementation-of-elman-recurrent-neural-network-in-weka/) - Foreword In this article, we will discuss the implementation of the Elman Network or Simple Recurrent Network (SRN) [1],[2] in WEKA. The implementation of Elman NN in WEKA is actually an extension to the already implemented Multilayer Perceptron (MLP) algorithm [3], so we first study MLP and it's training algorithm, continuing with the study of
- [Implementation of Competitive Learning Networks for WEKA](https://jsalatas.ictpro.gr/implementation-of-competitive-learning-networks-for-weka/) - Foreword In a previous article, we shown that by using WEKA a researcher can easily implement her own algorithms without other technical concernings like binding an algorithm with a GUI or even loading the data from a file/database, as these tasks and many others are handled transparently by the WEKA framework. [1] In this article
- [A proposal for developing a mobile based environment to help children learning a foreign language](https://jsalatas.ictpro.gr/a-proposal-for-developing-a-mobile-based-environment-to-help-children-learning-a-foreign-language/) - (Update October 2016: A detailed text for this proposal can be found at [11]) 1. Introduction The main purpose of the proposed system is to help children learning a foreign language by promoting communication and language development skills through an engaging virtual collaboration environment in which children are encouraged to interact and communicate with other
- [Mobile based environment for foreign language learning: Application usage scenarios](https://jsalatas.ictpro.gr/mobile-based-environment-for-foreign-language-learning-application-usage-scenarios/) - 1. Introduction In our previous articles we presented a high level definition for a mobile based system for foreign language learning [1], as well as use case and sequence diagrams for the proposed system [2], which tries to bring into the foreign language teaching, the principles of active learning methodology introduced by the English scholar
- [WifiTags: An Adobe AIR Native Extension for getting available WiFi networks in Windows and Android Environments](https://jsalatas.ictpro.gr/wifitags-an-adobe-air-native-extension-for-getting-available-wifi-networks-in-windows-and-android-environments/) - 1. Introduction Adobe AIR is by design cross-platform and device-independent, but AIR applications can still access the capabilities and APIs of native platforms through AIR native extensions. A native code implementation provides access to device-specific features, enabling you to use platform-specific features, reuse existing native libraries, and achieve native-level speed for performance-sensitive code. These device-specific
- [Mobile based environment for foreign language learning: General implementation details and software architecture](https://jsalatas.ictpro.gr/mobile-based-environment-for-foreign-language-learning-general-implementation-details-and-software-architecture/) - 1. Introduction Following the analysis and design of the system as described in our previous articles [1] [2], in this article we present the initial implementation of the system, focusing on the general software architecture and providing a description of the full stack and tools used. We start by describing the various software layers and
- [Using the grapheme-to-phoneme feature in CMU Sphinx-4](https://jsalatas.ictpro.gr/using-the-grapheme-to-phoneme-feature-in-cmu-sphinx-4/) - Foreword This article summarizes and updates the previous articles [1] related to the new grapheme-to-phoneme (g2p) feature in CMU Sphinx-4 speech recognizer [2]. In order to support automatic g2p transcription in Sphinx-4 there were created a new weighted finite state transducers (wfst) in java [3] which its current API will be presented in a future
- [Porting openFST to java: Part 4](https://jsalatas.ictpro.gr/porting-openfst-to-java-part-4/) - Notice: Parts of this article may be outdated. There are many changes to its API and performance improvements recently in the java fst framework. Please refer to recent articles in Java FST Framework category for the latest info. Foreword This article, the fourth in a series regarding porting openFST to java, describes the latest version
- [Porting openFST to java: Part 3](https://jsalatas.ictpro.gr/porting-openfst-to-java-part-3/) - Notice: Parts of this article may be outdated. There are many changes to its API and performance improvements recently in the java fst framework. Please refer to recent articles in Java FST Framework category for the latest info. (originally posted at http://cmusphinx.sourceforge.net/2012/07/porting-openfst-to-java-part-3/) Foreword This article, the third in a series regarding, porting openFST to java,
- [Automating the creation of joint multigram language models as WFST: Part 2](https://jsalatas.ictpro.gr/automating-the-creation-of-joint-multigram-language-models-as-wfst-part-2/) - (originally posted at http://cmusphinx.sourceforge.net/2012/06/automating-the-creation-of-joint-multigram-language-models-as-wfst-part-2/) Foreword This a article presents an updated version of the model training application originally discussed in [1], considering the compatibility issues with phonetisaurus decoder as presented in [2]. The updated code introduces routines to regenerate a new binary fst model compatible with phonetisaurus’ decoder as suggested in [2] which will be
- [Porting openFST to java: Part 2](https://jsalatas.ictpro.gr/porting-openfst-to-java-part-2/) - Notice: Parts of this article may be outdated. There are many changes to its API and performance improvements recently in the java fst framework. Please refer to recent articles in Java FST Framework category for the latest info. (originally posted at http://cmusphinx.sourceforge.net/2012/05/porting-openfst-to-java-part-2/) Foreword This article, the second in a series regarding, porting openFST to java,
- [Porting openFST to java: Part 1](https://jsalatas.ictpro.gr/porting-openfst-to-java-part-1/) - Notice: Parts of this article may be outdated. There are many changes to its API and performance improvements recently in the java fst framework. Please refer to recent articles in Java FST Framework category for the latest info. Foreword This article is the first part of a series of articles on porting openFST[1] in java.
- [Phonetisaurus: A WFST-driven Phoneticizer – Framework Review](https://jsalatas.ictpro.gr/phonetisaurus-a-wfst-driven-phoneticizer-framework-review/) - Foreword This article tries to analyze the phonetisaurus g2p [1], [2] code by describing it's main parts and algorithms behind these. Phonetisaurus is a modular system and includes support for several third-party components. The system has been implemented primarily in python, but also leverages the OpenFST framework [3]. 1. Overall Architecture The procedure for model
- [Extending WEKA](https://jsalatas.ictpro.gr/extending-weka/) - Foreword This article is part of John's Salatas BSc. Thesis with subject "Implementation of Artificial Neural Networks and Applications in Foreign Exchange Time Series Analysis and Forecasting" (Greek text) completed at May 2011 under the supervision of Ass. Prof. C. N. Anagnostopoulos (Cultural Technology and Communication Dpt., University of Aegean). 1. Introduction to WEKA The
- [Mobile based environment for foreign language learning: Use cases and sequence diagrams](https://jsalatas.ictpro.gr/mobile-based-environment-for-foreign-language-learning-use-cases-and-sequence-diagrams/) - 1. Introduction In our previous article we presented a high level definition for a mobile based system for foreign language learning. We presented the system’s architecture and the different user roles involved in the system along with the basic functionality for each of these roles. In the current article, we continue the analysis of the
- [Java FST framework API Review](https://jsalatas.ictpro.gr/java-fst-framework-api-review/) - Foreword This article summarizes and updates various previous articles [1] related to the implementation of a java weighted finite states transducers framework that can use existing openFst [2] models or export java fst object to openFst format and which is available at the CMUSphinx SVN reopsitory at [3]. The following sections include brief descriptions of
- [Porting phonetisaurus many-to-many alignment python script to C++](https://jsalatas.ictpro.gr/porting-phonetisaurus-many-to-many-alignment-python-script-to-c/) - Notice: This article is outdated. The application described here is now part of the SphinxTrain application. Please refer to recent articles in CMUSphinx category for the latest info. (originally posted at http://cmusphinx.sourceforge.net/2012/05/porting-phonetisaurus-many-to-many-alignment-python-script-to-c/) Foreword Following our previous article on phonetisaurus [1] and the decision to use this framework as the g2p conversion method for my GSoC
- [Automating the creation of joint multigram language models as WFST](https://jsalatas.ictpro.gr/automating-the-creation-of-joint-multigram-language-models-as-wfst/) - Notice: This article is outdated. The application described here is now part of the SphinxTrain application. Please refer to recent articles in CMUSphinx category for the latest info. (originally posted at http://cmusphinx.sourceforge.net/2012/06/automating-the-creation-of-joint-multigram-language-models-as-wfst/) Foreword Previous articles have introduced the C++ code to align a pronounciation dictionary [1] and how this aligned dictionary can be used in
- [Using OpenGrm NGram Library for the encoding of joint multigram language models as WFST](https://jsalatas.ictpro.gr/using-opengrm-ngram-library-for-the-encoding-of-joint-multigram-language-models-as-wfst/) - (originally posted at http://cmusphinx.sourceforge.net/2012/06/using-opengrm-ngram-library-for-the-encoding-of-joint-multigram-language-models-as-wfst/) Foreword This article will review the OpenGrm NGram Library [1] and its usage for language modeling in ASR. OpenGrm makes use of functionality in the openFST library [2] to create, access and manipulate n-gram language models and it can be used as the language model training toolkit for integrating phonetisaurus' model
- [Compatibility issues using binary fst models generated by OpenGrm NGram Library with phonetisaurus decoder](https://jsalatas.ictpro.gr/compatibility-issues-using-binary-fst-models-generated-by-opengrm-ngram-library-with-phonetisaurus-decoder/) - (originally posted at http://cmusphinx.sourceforge.net/2012/06/compatibility-issues-using-binary-fst-models-generated-by-opengrm-ngram-library-with-phonetisaurus-decoder/) Foreword Previous articles have shown how to use OpenGrm NGram Library for the encoding of joint multigram language models as WFST [1] and provided the code that simplifies and automates the fst model training [2]. As described in [1] the generated binary fst models with the procedures described in those articles

## Pages

- [About Me](https://jsalatas.ictpro.gr/about-me/) - Hey! I’m John Salatas and I don’t like to talk about myself. Please have a look around and I’m sure you will know me better. The best way to start is by studying my latest CV. Fields that I'm currently interesting in, include Applications of Artificial Intelligence and Machine Learning (Genetic Algorithms / Artificial Neural
- [Πρόταση για την ανάπτυξη ενός περιβάλλοντος βασισμένο σε κινητές συσκευές για την υποβοήθηση της εκμάθησης ξένων γλωσσών από παιδιά](https://jsalatas.ictpro.gr/a-proposal-for-developing-a-mobile-based-environment-to-help-children-learning-a-foreign-language-gr/) - 1.Εισαγωγή Ο κύριος σκοπός του προτεινόμενου συστήματος είναι να βοηθήσει μαθητές που φοιτούν στην πρωτοβάθμια και τις πρώτες τάξεις της δευτεροβάθμιας εκπαίδευσης να μάθουν μια ξένη γλώσσα, προωθώντας τις δεξιότητες επικοινωνίας και την ανάπτυξη της γλώσσας μέσα από ένα ελκυστικό εικονικό περιβάλλον συνεργασίας, όπου ενθαρρύνεται η αλληλεπίδραση και η επικοινωνία με άλλους μαθητές από όλο

## Categories

- [WEKA](https://jsalatas.ictpro.gr/category/weka/)
- [CMUSphinx](https://jsalatas.ictpro.gr/category/cmusphinx/)
- [GSoC 2012](https://jsalatas.ictpro.gr/category/gsoc-2012/)
- [phonetisaurus](https://jsalatas.ictpro.gr/category/phonetisaurus/)
- [openFST](https://jsalatas.ictpro.gr/category/openfst/)
- [OpenGrm NGram](https://jsalatas.ictpro.gr/category/opengrm-ngram/)
- [Java FST Framework](https://jsalatas.ictpro.gr/category/java-fst-framework/)
- [mobile development](https://jsalatas.ictpro.gr/category/mobile-development/)
- [m-learning](https://jsalatas.ictpro.gr/category/m-learning/)
- [BigBlueButton](https://jsalatas.ictpro.gr/category/bigbluebutton/)

## Tags

- [WEKA](https://jsalatas.ictpro.gr/tag/weka-2/)
- [java](https://jsalatas.ictpro.gr/tag/java/)
- [machine learning](https://jsalatas.ictpro.gr/tag/machine-learning/)
- [artificial intelligence](https://jsalatas.ictpro.gr/tag/artificial-intelligence/)
- [competitive learning](https://jsalatas.ictpro.gr/tag/competitive-learning/)
- [neural networks](https://jsalatas.ictpro.gr/tag/neural-networks/)
- [Self-Organizing Maps](https://jsalatas.ictpro.gr/tag/self-organizing-maps/)
- [Learning Vector Quantization](https://jsalatas.ictpro.gr/tag/learning-vector-quantization/)
- [LVQ](https://jsalatas.ictpro.gr/tag/lvq/)
- [SOM](https://jsalatas.ictpro.gr/tag/som/)
- [Elman](https://jsalatas.ictpro.gr/tag/elman/)
- [Multilayer Perceptron](https://jsalatas.ictpro.gr/tag/multilayer-perceptron/)
- [MLP](https://jsalatas.ictpro.gr/tag/mlp/)
- [recurrent neural networks](https://jsalatas.ictpro.gr/tag/recurrent-neural-networks/)
- [backpropagation](https://jsalatas.ictpro.gr/tag/backpropagation/)
- [RNN](https://jsalatas.ictpro.gr/tag/rnn/)
- [JMM](https://jsalatas.ictpro.gr/tag/jmm/)
- [conditional random fields](https://jsalatas.ictpro.gr/tag/conditional-random-fields/)
- [CRF](https://jsalatas.ictpro.gr/tag/crf/)
- [automated speech recognition](https://jsalatas.ictpro.gr/tag/automated-speech-recognition/)
- [ASR](https://jsalatas.ictpro.gr/tag/asr/)
- [g2p](https://jsalatas.ictpro.gr/tag/g2p/)
- [C++](https://jsalatas.ictpro.gr/tag/c/)
- [python](https://jsalatas.ictpro.gr/tag/python/)
- [joint multigram models](https://jsalatas.ictpro.gr/tag/joint-multigram-models/)
- [OpenGrm](https://jsalatas.ictpro.gr/tag/opengrm/)
- [language modeling](https://jsalatas.ictpro.gr/tag/language-modeling/)
- [NLP](https://jsalatas.ictpro.gr/tag/nlp/)
- [Natural Language Processing](https://jsalatas.ictpro.gr/tag/natural-language-processing/)
- [grapheme to phoneme](https://jsalatas.ictpro.gr/tag/grapheme-to-phoneme/)
- [l2s](https://jsalatas.ictpro.gr/tag/l2s/)
- [letter to sound](https://jsalatas.ictpro.gr/tag/letter-to-sound/)
- [fst](https://jsalatas.ictpro.gr/tag/fst/)
- [wfst](https://jsalatas.ictpro.gr/tag/wfst/)
- [java fst](https://jsalatas.ictpro.gr/tag/java-fst/)
- [ubiquitous computing](https://jsalatas.ictpro.gr/tag/ubiquitous-computing/)
- [pervasive computing](https://jsalatas.ictpro.gr/tag/pervasive-computing/)
- [context aware](https://jsalatas.ictpro.gr/tag/context-aware/)
- [online learning](https://jsalatas.ictpro.gr/tag/online-learning/)
- [AIR](https://jsalatas.ictpro.gr/tag/air/)
- [Flash](https://jsalatas.ictpro.gr/tag/flash/)
- [elearning](https://jsalatas.ictpro.gr/tag/elearning/)
- [moodle](https://jsalatas.ictpro.gr/tag/moodle/)
- [flex](https://jsalatas.ictpro.gr/tag/flex/)
- [BlazeDS](https://jsalatas.ictpro.gr/tag/blazeds/)
- [Spring](https://jsalatas.ictpro.gr/tag/spring/)
- [Hibernate](https://jsalatas.ictpro.gr/tag/hibernate/)
- [Actionscript](https://jsalatas.ictpro.gr/tag/actionscript/)
- [AIR native extension](https://jsalatas.ictpro.gr/tag/air-native-extension/)
- [phonetisaurus](https://jsalatas.ictpro.gr/tag/phonetisaurus/)
- [openFST](https://jsalatas.ictpro.gr/tag/openfst/)
- [mobile development](https://jsalatas.ictpro.gr/tag/mobile-development/)
- [m-learning](https://jsalatas.ictpro.gr/tag/m-learning/)
- [BigBlueButton](https://jsalatas.ictpro.gr/tag/bigbluebutton/)
- [wrist gestures](https://jsalatas.ictpro.gr/tag/wrist-gestures/)
- [android](https://jsalatas.ictpro.gr/tag/android/)
- [smartwatch](https://jsalatas.ictpro.gr/tag/smartwatch/)
- [android wear](https://jsalatas.ictpro.gr/tag/android-wear/)