Auto-transcription of video footage and audio tracks
DynDevice allows you to completely transcribe the content of the videos and audio tracks that are inserted in their courses.
The specific algorithms of this functionality combine the most modern and advanced Speech to Text (STT), Automatic Speech Recognition (ASR) and Information Retrieval (IR) technologies to guarantee authors using DynDevice automatic transcription, indexing and search of any multimedia content included in its e-Learning courses.
The feature uses modern Deep-Learning * and DNN (Deep Neural Network) algorithms to ensure accuracy levels with 98% peaks in speech recognition. These algorithms also allow to optimize the use of the necessary cloud HW resources, allowing to obtain transcripts in times of about 1: 0.25.
By taking advantage of this powerful feature of DynDevice you will be able to:
- add subtitles to your videos automatically, ensuring accessibility even to people without hearing
- index and make the courses searchable with respect to the actual and complete content they expose
- make courses advisable to users based on real needs, preferences and correlations with other users
Automatic transcription is available for Italian and English languages.
* Deep learning is the field of research of machine learning and of artificial intelligence based on different levels of representation, corresponding to hierarchies of characteristics of factors or concepts, where high-level concepts are defined on the basis of low-level concepts.