Speech-to-Text System Provides Comprehensive and Fully Searchable Metadata Allowing for Faster Media Production
AMSTERDAM, THE NETHERLANDS—At IBC, world-leading media technology innovator Solid State Logic (SSL) demonstrated how its Gravity media production management system can now automatically populate ingested media with detailed, fully searchable data generated from audio content via a new Speech-to-Text system.
Media asset management systems rely on metadata embedded in the media. However, this metadata is typically limited to aspects of a digital signal related to timecode, sync, blanking, title and other descriptive data or time-consuming manually entered data.
Gravity’s Speech-to-Text system goes much further by recognizing speech within audio streams and generating a full text transcription in real time. The full transcription is placed within the metadata and made available for subsequent key word or text string search. Each word of the text is referenced to timecode in the associated media. The result is a highly accurate and searchable database that allows the user to find required media quickly and efficiently, vastly improving the speed of media production.
Speech-to-Text is one of a number of applications now exclusively available for SSL’s Gravity platform, a complete content acquisition, management and distribution solution providing all the encoding and transcoding tools required for fast package production, coupled with the capability of generating multiple, simultaneous output formats in different resolutions to cover any broadcasting situation.
Solid State Logic is the world’s leading manufacturer of analogue and digital audio consoles and provider of creative tools for music, broadcast and post production professionals. For more information about our award-winning products, please visit: www.solid-state-logic.com.
