The MLLP releases the open source transLectures-UPV Platform (TLP) version 3.0

MLLPThe Universitat Politècnica de València’s MLLP research group is pleased to announce the release of version 3.0 of the open source transLectures-UPV Platform (TLP) for the integration of automated transcription and translation technologies into media repositories. With this new release, TLP now provides support for the transcription and translation of the full content of MOOCs (multilingual subtitling of video/audio + translation of text contents).

The transLectures-UPV Platform (TLP), developed by the Universitat Politècnica de València’s (UPV) Machine Learning and Language Processing (MLLP) research group, is an open source piece of software designed to integrate automated transcription and translation technologies into a media repository. Its main components are the TLP Database, Web Service, Ingest Service, TLP Text Translation Editor, and TLP Media Player. The MLLP is releasing TLP version 3.0, now available for download from the TLP page.

With this new release, TLP now provides support for the transcription and translation of the full content of MOOCs: in addition to the already existing support for multilingual subtitling of media files, TLP 3.0 adds support now for translation of text contents.

We are especially proud of the capabilities of the new TLP Text Translation Editor, which include side-by-side text translation editing and web preview for HTML text files. This is now a part of TLP 3.0, in addition to the advanced multilingual subtitle editing capabilities of the TLP Media Player, including side-by-side subtitle editing while watching the video and an intuitive graphical UI for modification of subtitle segments (add, remove, make them shorter, longer, combine several segments…).

The TLP API has also gone up a version to v3, in order to allow for the automated uploading of both media files and text documents to our platform, and downloading of subtitles and text translations.

A complete description of TLP’s functionalities can be found in the TLP 3.0 documentation.

The fastest way to try all TLP features, old and new, is to access the MLLP transcription and translation platform, which integrates our own software TLP and TLK (the transLectures-UPV Toolkit for speech recognition), our machine translation technology, and our text-to-speech synthesis technology. Just open a trial account and start uploading media and text files to try our automatic transcription and translation technology, and even integrate it with your own media repository via our API.

The MLLP research group, made up of researchers based at the Universitat Politècnica de València (UPV), have been developing for years their expertise and tools for machine learning and language processing in the fields of educational technologies and big data within the ideal framework of the EU projects transLectures and EMMA. The MLLP has been an integral part of both projects, and within the ongoing project EMMA, TLP is being intensively used for the full transcription and translation of MOOC contents in several languages from leading European universities.

The MLLP’s TLP and TLK are also being used as the basis for automatic subtitle generation in the educational media repositories of our own Universitat Politècnica de València (Polimedia), and of the Carlos III University of Madrid (you can learn more about our projects here). So far, our technology has been used to generate multilingual subtitles for over 18 000 media files (over 3 700 hours) and translations for over 8 700 text documents (over 59 000 sentences).

So download TLP 3.0 or try it now in the MLLP transcription and translation platform. We’ll keep you updated on new developments and releases of our software; just keep checking our website and follow us on Twitter, @mllpresearch!

Posted in All, Tools and tagged , , .