As the volume of audio and video media has grown exponentially across the corporate world, so too has the cost of prosecution and analysis of legal audio and video files during early case assessment and eDiscovery phases. The application of artificial intelligence to what were traditionally manual tasks performed by legions of transcriptionists, translators, and high-cost legal professionals has the potential to revolutionize the evidentiary valuation of audio and video. Efficiently processing large volumes of files with a high degree of accuracy and minimal cost has only recently become a viable option for law firms and corporations.
The Veritone platform helps clients gain efficiencies and reduce cost by adding new artificial intelligence capabilities. The platform can render every second and frame of audio and video content searchable for things like words, phrases, faces, sentiment, and voice identification. It can produce an index of the processed data within minutes – a process that as recently as 2015 could take thousands of hours.
Using the Veritone, law firms, legal service providers, and corporate clients are able to:
- Search across all media types being reviewed in one simple interface
- Visualize and quantify patterns, key phrases, proper names and aliases, and repetitive topics
- Deploy software configurations to effectively manage required security and judicial protocols
- Utilize custom-trained machine learning models tuned for transcription accuracy in specialized use cases such as financial trading calls, depositions, police footage, surveillance cameras and multi-lingual conversations
- Create filters and other standardized search criteria to automatically aggregate new files and associated metadata
- Securely share key documents and media files to authenticated users
Michael McDonald is the general manager of Veritone Legal and has nearly 25 years of experience developing and implementing technology and software solutions for compliance, legal and related industries.