Nexidia Brings Neural Phonetic Speech AnalyticsTM to Audio Discovery

USA/Canada News

02
Feb
2015

Editor

Nexidia, a market-leading provider of audio and video search technology, today announced significant enhancements to its legal discovery application, Nexidia Search. Nexidia Search will incorporate the company’s breakthrough technology, Neural Phonetic Speech AnalyticsTM, to provide improved workflow and discovery tools for the review of audio evidence.  

Nexidia invented the industry-leading approach for accurately and quickly reviewing large amounts of unstructured audio with its patented phonetic indexing and search technology. Neural Phonetic Speech AnalyticsTM builds on this capability by intelligently combining Nexidia’s state of the art automatic speech recognition engine with Nexidia’s patented phonetic index to produce word-level transcription and sentiment analysis, helping reviewers quickly understand the context of their data set. The system applies Nexidia’s latest advances in neural-net processing and language models for improved performance throughout the application.

These features add a new, visual approach for legal reviewers to automatically see and analyze the most common themes and topics that occur within a body of audio evidence. The system displays several reports, including word clouds depicting frequency of occurrence at both the word and phrase level, and a related phrase diagram that lets users show the most common words and phrases in relation to each other. This output can then be translated directly into queries that are run against the full phonetic index to quickly and accurately bring up all of the files that correspond to these searches. 

“This release adds the notion of concept search to Nexidia’s audio discovery solutions,” said Vice President and General Manager of Legal Markets, Jeff Schlueter. “Now, users can start with a visual reference to see what words and phrases are showing up frequently in the audio, and then use this information to search more deeply into the content using our traditional phonetic search.” 

In addition, the word-based analysis can use other textual content from a matter – such as emails, transcribed depositions, and news articles – to help improve the phrase recognition output and deliver results that closely represent the content of the recordings.

Nexidia Search will include several additional features appealing to legal reviewers, including improved workflows for assigning files to review teams, enhanced tools for managing large sets of review tags and meta-data categories, and enhancements to its Relativity plug-in to support Relativity 9.0. All of these new features will be demonstrated at the company’s booth #1310 at LEGALTECH® NEW YORK 2015, being held February 3rd - 5th at the Hilton New York, and are targeted for general availability by late March.