SAIL LABS Announces New Release of Media Mining Indexer 6.2

SAIL LABS Announces New Release of Media Mining Indexer 6.2

SAIL LABS Technology, one of the top providers of speech technology solutions, is proud to announce the availability of Media Mining Indexer 6.2, the new major release of its flagship product for real-time, multi-lingual, multimedia indexing. The Media Mining Indexer is based upon SAIL LABS’ own award winning speech recognition technology and provides a suite of best-of-breed components for multimedia processing, transforming audio and video data into indexed and searchable information in real-time. “We are proud to introduce the latest version of the Media Mining Indexer. This newest version is the result of our ongoing investments in innovation and represents a quantum leap forward in terms of system flexibility and stability, overall performance and processing capabilities to optimally respond to client needs. Our customers will be pleased with the progress and we invite all others to join us on the way into the future, “says Gerhard Backfried, Head of Research at SAIL LABS. Standard Features of the Media Mining Indexer include:
  • Automatic Speech Recognition enabling accurate conversion of speech to text, even in the presence of high levels of background noise
  • Speaker Change Detection segregating audio segments based on speaker and audio environment for focused information retrieval
  • Speaker Identification attributing statements to certain speakers (“who” has been saying “what” in the news?)
  • Topic Classification helping to classify stories related to specific interests
  • Named Entity Detection tagging words within the text with categories of entities such as persons, locations, organizations.
  • Real-time Indexing: Transcripts are generated in parallel to the broadcast.
  • Language Model Toolkit: The Language Model Toolkit enables addition of domain-specific vocabulary and context to help keep pace with a rapidly changing news environment.
SOME OF THE EXCITING NEW FEATURES INCLUDE: General Improvements
  • Easier installation due to pre-packaged Perl
  • Enhanced text processing capabilities for use in the Text Mining Indexer
  • Stability improvements
Speech Engine
  • New models for international and US English
  • High density configuration for parallel decoders
  • New set of models to balance accuracy versus speed to promote real-time processing
  • Modular and transparent reloading of models
  • Support of new languages i.e. Catalan, Swedish, Portuguese, Bahasa (Indonesia), Italian, Farsi and Romanian
Named Entity Detection
  • Improved named entity detection of names via unified lists across languages
  • Improved communication with Media Mining Server to synchronize named entity detection with profiles (via URI=Uniform Resource Identifier)
  • Extensible named-entity categories
Topic Detection
  • Improved topic models for all languages
  • Improved communication with Media Mining Server to relate topics to profiles
Language Model Tool
  • Improved text preprocessing for Greek, Hebrew, Italian, Farsi, US and international English
  • Support of further languages: Catalan, Swedish, Portuguese, Bahasa (Indonesia), Italian, Farsi and Romanian
Speaker Identification Improved communication with Media Mining Server to relate recognized speakers to their respective profiles. Available Languages: Currently US English, International English, Spanish, French, German, Arabic, Russian, Polish, Greek, Catalan, Swedish, Portuguese, Norwegian, Hebrew, Bahasa (Indonesia), Italian, Mandarin Chinese, Farsi and Romanian are supported. Media Mining Indexer 6.2 is available immediately from SAIL LABS and its global network of partners to new customers and to registered customers with support & maintenance contracts including updates.

Share on Social Media

Share on linkedin
Share on twitter
Share on google