Highlights

FAMIUM SAND Stream Analytics

FAMIUM SAND is a streaming analytics solution that collects and analyzes streaming metrics to provide in-depth video client session data and streaming performance information like average throughput, buffer level, representation switch events and initial playout delay (QoE metrics defined in ISO/IEC 23009-1) to help deeply understand streaming problems and client behavior to allow optimization of workflows.

MPEG-H Authoring Suite

The upgraded version 3.7 of the MPEG-H Authoring Suite (MAS) – a toolset for the creation of MPEG-H Masters - is now available as free download. Some highlights of the new features include additional Component Layouts for better DAW integration in the MPEG-H Authoring Plug-in and export session templates for use in broadcast devices in the MPEG-H Authoring Tool.

AI-Powered Video Encoding & Optimized Streaming

The world's Internet traffic is predominantly made up of video streaming, which can lead to 'bandwidth hogging' and loss in quality when large volumes of content are disseminated online. With an objective of achieving bitrate savings while maintaining optimal quality, our FAMIUM Deep Encode solution utilizes AI methods to enhance and automate Per-Title-Encoding and Per-Scene-Encoding processes.   

xHE-AAC

Many service providers worldwide are relying on FFmpeg-based ingest and encoding frameworks. Those can now easily be enabled for xHE-AAC audio encoding thanks to the new MainConcept xHE-AAC FFmpeg plugin, which incorporates Fraunhofer’s high-quality production encoder software. In addition to the basic plugin functionality, MainConcept offers professional services for service provider-specific workflow optimizations.

Mining Platform

Content-based metadata allows more easy retrieval, reuse, and monetarization of media assets, whether text, audio, image, or video. The Fraunhofer IAIS Mining Platform integrates various AI-based services to facilitate the fully automatic, scalable analysis of media assets. The containerized system can run on any Kubernetes cluster, supports customized analysis workflows and models, and can be readily integrated via its simple REST API.

Dialog+

Many people find it hard to follow speech in broadcasting and streaming due to loud background sounds. Dialog+, an MPEG-H production technology, addresses this issue and ensures clear speech by allowing the adaption of loudness levels of both speech and background sounds. To achieve this, it uses a solution based on deep learning and can be applied when only a final mix is available. This makes it possible to customize the speech level to individual requirements.

Back to IBC 2021