Valossa Launches Voice-Controlled, AI-Powered Video Search Engine

Finnish startup Valossa launched as a company yesterday and released an artificial intelligence- and voice-powered, deep content video search technology.

Powered by voice recognition, it is now possible to have your TV, mobile device, or PC search engine know the answers to questions such as: "Show me science fiction films having double planet Earths," or "Two dogs falling in love while eating a plate of spaghetti."

Valossa's technology understands the contents of video files through text and pattern recognition AI. Designed for service and content providers, Valossa can reach down into video content, identify it, and make it searchable. Valossa's proprietary engine understands both the deep content data of videos and provides novel solutions for content indexing and discovery. Valossa uses both audio-visual information and metadata that describes the video content to provide new levels of search context. Valossa has also developed Deep Content technology that can be used to discover and recommend semantically-related content from large video collections.

By automatically analyzing and understanding video content, Valossa will help enable highly-relevant, autonomous insertion of ads into video content. Real-time video discovery and recommendations for live TV and recommendation of relevant content in real time through a smart TV or set-top box are also possible.

Totally cross-platform with Mac OS, Microsoft Windows, and Linux, this server-side technology enables virtually identical functionality to the Apple TV OS for any system provider. Valossa also integrates with all leading voice platform vendors, such as Amazon, Apple, Google, and Microsoft.

As a proof of concept, Valossa has made Whatismymovie.com available for demo testing and evaluation. The demonstration is designed to show how Valossa constructs unique Deep Content models from video content transcripts and metadata. These new algorithms and services havebeen developed through several university research projects with support from the Finnish Funding Agency for Innovation (Tekes) and the Academy of Finland.

SpeechTek Covers
for qualified subscribers
Subscribe Now Current Issue Past Issues