Artificial Intelligence and Machine Learning have facilitated automation in various verticals of the media industry, thus, saving human intervention to a great extent
By Anisha Gakhar
Artificial intelligence (AI), also called machine intelligence or machine learning (ML), stands for scientifically devised intelligence demonstrated by machines, bots or computers, in paradox to the natural intelligence possessed by humans and other fauna. Advances in this sector, have enabled manufacturers and broadcasters to invent and execute smart tools and applications, to foster the quality of their content.
AI and its close relation machine learning systems, simply expand what can be made a repetitive, computer task, releasing people to create more content and build audiences by finding new delivery routes, and ensuring optimum monetisation.
AI aided content creation facilitates umpteen possibilities like colour correction, automated editing, conformance/compliance and performance optimisation, scene extraction and highlights creation. Caption generation for photos and videos, language translations and automatic narration generation are also achievable through the use of AI technology. Face recognition through automated meta-data tagging and extraction, person-in-scene detection and person-in-picture tracking are features that can be leveraged, whilst using this augmentation. It also facilitates logo detection, text extraction and speech-to-text conversion. The person-in-scene tracking is especially useful during sports highlights, for instance, tracking the person who hit the goal during a football match.
AI sits naturally in any software-defined workflow, optimising and ensuring efficient use of resources while maintaining quality output. AI components can be crafted as micro-services, ensuring they are embedded into the architecture to provide uncompromised efficiency. As part of the architecture, they are inherently virtualised, allowing AI systems to be hosted in a data centre or in the cloud.
For instance, ENCO’s enCaption4 solution for automated closed-captioning, is deployable on-premises or in the cloud. ENCO’s latest improvements in accuracy include a dictionary database that can be been expanded to 29 languages, making enCaption4 a solution expected to give true ROI value for broadcasters worldwide. Leveraging breakthroughs in ML technology, ENCO’s patented, AI-driven solution allows new languages to be added almost instantaneously. Furthermore, integration with popular newsroom computer systems from ENPS and Octopus among others takes advantage of news scripts and rundowns to learn and validate the spelling of local names and terminology.
“With more than three times the language support of previous generations, enCaption4 helps broadcasters around the world to reduce or eliminate the rising costs and short-notice staffing challenges of real-time stenocaptioners,” said Ken Frommert, president, ENCO. “We are helping our customers make an immediate on-air impact in news, sports and other programming with automated closed captioning,” he added.
EnCaption4’s high speed benchmark poses as a bridge between live speech and the corresponding caption display for an overall improved viewer experience, with accuracy rates exceeding 90 percent.
enCaption’s NDI compatibility simplifies the captioning workflow by eliminating the need for specialised encoding hardware. It automatically generates captions through its NDI input stream, and outputs an NDI signal, with captions keyed directly on top of the video stream. This interoperability offers a redundant and reliable solution for accurate closed captioning within live web and social media streams, such as Facebook Live.
“While online video distribution is
not subject to the same stringent closed captioning regulations as broadcast TV, the use of captions ensures a larger audience for any online video,” Frommert asserted. “Advocacy groups for the hard-of-hearing are also actively pushing for online video programs to contain captions. Those watching video on portable devices in public places, prefer to keep their volume down and turn on captions instead,” he added.