Group items tagged

""Julius" is a high-performance, two-pass large vocabulary continuous speech recognition (LVCSR) decoder software for speech-related researchers and developers. Based on word N-gram and context-dependent HMM, it can perform almost real-time decoding on most current PCs in 60k word dictation task. Major search techniques are fully incorporated such as tree lexicon, N-gram factoring, cross-word context dependency handling, enveloped beam search, Gaussian pruning, Gaussian selection, etc. Besides search efficiency, it is also modularized carefully to be independent from model structures, and various HMM types are supported such as shared-state triphones and tied-mixture models, with any number of mixtures, states, or phones. Standard formats are adopted to cope with other free modeling toolkit such as HTK, CMU-Cam SLM toolkit, etc. The main platform is Linux and other Unix workstations, and also works on Windows. Most recent version is developed on Linux and Windows (cygwin / mingw), and also has Microsoft SAPI version. Julius is distributed with open license together with source codes. Note: you should prepare a language model and an acoustic model to run a speech recognition with Julius. "

a full Flex (flash)video chat with audio and video support made using Open Source RED5 technology and Flash : You do noy need to purchase expensive solution such as Flash Media Server. If you have your own server, deploy the RED5 server side solution, and install our red5 Recorder: You've done it ! You have your own Video recoder solution including Video, Audio, and player...

Red5 Flash Server is a module package for Drupal which allows you to record Flash video files (FLV) by using a standard web cam (or built-in web camera) together with the Red5 Open Source Flash Server (http://osflash.org/red5). The difference to similar video recorder modules is that we want people to be independent of third-party providers. People should run their own Red5 Flash server instead. The advantages are: * you can create your own video conversation community * you have full access to your Flash video files * you can record high quality videos without paying a license fee (because Red5 Flash server is open source and free - but offering same functionality as Adobe Flash Server)

Open source toolkit for speech recognition

"NonVisual Desktop Access (NVDA) is a free and open source screen reader for the Microsoft Windows operating system. Providing feedback via synthetic speech and Braille, it enables blind or vision impaired people to access computers running Windows for no more cost than a sighted person. Major features include support for over 20 languages and the ability to run entirely from a USB drive with no installation."

Transana is software for professional researchers who want to analyze digital video or audio data. Transana lets you analyze and manage your data in very sophisticated ways. Transcribe it, identify analytically interesting clips, assign keywords to clips, arrange and rearrange clips, create complex collections of interrelated clips, explore relationships between applied keywords, and share your analysis with colleagues. The result is a new way to focus on your data, and a new way to manage large collections of video and audio files and clips. Transana is inexpensive and Open Source. It was developed at the Wisconsin Center for Education Research, where it continues to be maintained and enhanced. It is widely used in the education research community, where video is an integral part of most researchers' methods. Researchers in many other disciplines also find it useful in their work.

SynPhony is an open-source project that will assist in teaching literacy skills for alphabetic writing systems. It is a database system designed to systematically present the patterns of a language and track a user's progress as they acquire reading skills. There are four main components to SynPhony: linguistic, pedagogic, user knowledge base, and reports. Although English is the first language being targeted, the structure and methods used will be suitable for many other languages as well.

"The Opencast Matterhorn project is an enterprise-level, easy-to-install open source podcast and rich media capture, processing and delivery system."

Mediathread is an open-source platform for exploration, analysis, and organization of web-based multimedia content. Mediathread connects to a variety of image and video collections (such as YouTube, Flickr, library databases, and course libraries), enabling users to lift items out of these collections and into an analysis environment. In Mediathread, items can then be clipped, annotated, organized, and embedded into essays and other written analysis.

"The Global WordNet Organization is pleased to post information about wordnets on its website and welcomes submissions reporting on relevant work. Strictly commercial efforts will not be posted. Open source efforts are strongly encouraged. We only post links to resources that follow the wordnet design, which includes * links to WordNet (Princeton or others that are linked to PWN); * WN structure (minimally: synset, hyponymy) "

We are using open source teleconferencing technology to conduct 1-on-1 and group classes via video, voice, flash technology for displaying Chinese characters and shared whiteboard where the teacher & student can observe each other's Chinese writing capabilities. In addition, we offer video clips of Chinese culture events also. As student learn the language, and they will be able to learn the Chinese culture as well.

Media Cloud is a system that lets you see the flow of the media. The Internet is fundamentally altering the way that news is produced and distributed, but there are few comprehensive approaches to understanding the nature of these changes. Media Cloud automatically builds an archive of news stories and blog posts from the web, applies language processing, and gives you ways to analyze and visualize the data. The system is still in early development, but we invite you to explore our current data and suggest research ideas. This is an open-source project, and we will be releasing all of the code soon.

Open source dictionary project, including stroke animations, audio, character information, and more.

WORLD CALL LANGUAGE LINKS LIBRARY - Free/Open Source Language Education Resource Repository

HandBrake is an open-source GPL-licensed, multiplatform, multithreaded DVD to MPEG-4 converter, available for Mac OS X, Linus and Windows

"This article is designed to help users who are new to NonVisual Desktop Access (NVDA) learn the basic controls for testing web content, and to serve as a reference for the occasional NVDA user. NonVisual Desktop Access (NVDA) is a free and open source screen reader for the Microsoft Windows operating system. It supports over 20 languages and can run on any computer entirely from a USB drive with no installation."

The International Journal of ePortfolio (IJeP) is a double-blind, peer-reviewed, open access journal freely available online. Subscriptions and fees are not required to access this journal; however, readers desiring hardcopies of issues can order them via our Current Issue and Past Issues links above. The mission of the International Journal of ePortfolio (IJeP) is to encourage the study of practices and pedagogies associated with ePortfolio in educational settings. The journal's focus includes the explanation, interpretation, application, and dissemination of researchers', practitioners', and developers' experiences relevant to ePortfolio. It also serves to provide a multi-faceted, single source of information for those engaging in projects and practices associated with ePortfolio. A refereed (blind) peer-reviewed journal, IJeP embraces inquiry into ePortfolio in educational settings holistically; therefore, manuscripts considering the following areas of investigation are welcomed: instruction and principles of learning that utilize and inform practical, effective ePortfolio methodologies; evaluation and assessment methodologies and practices supported by ePortfolio; case studies and best practices regarding applications of ePortfolio for learning, assessment, and professional development supported by scholarship of teaching and learning practices and research methodologies; theoretically rich accounts of the principles grounding ePortfolio work and its relationship to larger social and cultural phenomena; and innovative development and applications of technologies that enable new ePortfolio practices. IJeP employs a rolling submission process; however, those wishing to be considered for the next issue of IJeP should plan to submit their manuscript by December 1, 2011. Those submitting manuscripts to IJeP can expect the review process to take approximately 90 days.

The Online Language Environments (OLE) Board is a web based threaded discussion instructional tool that utilizes voice, video and text to replicate the functions of a language lab. OLE is used for, but not restricted to, oral practice, listening comprehension, speaking practice and reading and writing practice. The OLE Board can be used to supplement instruction in face-to-face classes as homework assignments, and can be used in entirely distance classes. CERCLL support provides assistance to improve the technological capabilities and establish the pedagogical strategies of the OLE Board, which has been successfully piloted in French, Arabic, various Indigenous languages and ESL. Specific deliverables for the OLE Board project include templates and pedagogical strategies with examples for Arabic, Persian, Turkish, Japanese, Chinese and Portuguese; online and print user and instructor documentation; lesson plans and use case scenarios; usability studies for further desired improvement; piloting of multi-institutional usage. We also provide for the protocols necessary to integrate the OLE Board for use with course management systems. The OLE Board is being developed as an open-source product that will be available to the wider language instruction community.

VoxForge was set up to collect transcribed speech for use in Open Source Speech Recognition Engines ("SRE"s) such as such as ISIP, HTK, Julius and Sphinx. We will categorize and make available all submitted audio files (also called a 'Speech Corpus") and Acoustic Models in GPL format. Users can record themselves reading text excerpts in their native language, or they can access the recordings already recorded in all languages

" * Sophie Author allows users to create complex networked multimedia documents without specialized training. * Sophie Reader allows readers to read Sophie books in a browser without downloading a separate application. * Comment frames allow easily constructed spaces for discussion inside of books. * Browser frames allow embedding fully functional web browsers in book pages. * Sophie can import, embed, and export PDF files. * Easy to use embedded books: Sophie books can open inside other Sophie books. * Frame-based timelines present an easy way to create animations. * Sophie Server allows uploading, managing, and downloading books on a server. * Sophie Server allows simultaneous collaborative creation of books."