Nexidia is the developer and provider of the most effective phonetic-based technology for audio and video search.By transforming audio-video data into business intelligence, Nexidia allows both government and commercial enterprises to leverage untapped information previously locked away in audio-video content.
Based on years of research and development, Nexidia’s phonetic engine is the only technology that allows the user to search on proper names, places, industry terms and jargon without extensive training and cumbersome dictionaries. The process is adaptable to a range of audio analyses and excels across the full spectrum of audio quality. The Nexidia, Inc. technology is based on years of ongoing intensive research and invention by both the Georgia Institute of Technology and Nexidia’s Research and Development Team.
Audio Discovery
While effective risk mitigation requires consistent, uniform policy enforcement across records of all types, the lack of a highly scalable, accurate audio-video discovery solution has hampered the ease of discoverability of audio-video records. In the event of a lawsuit or regulatory action, the prohibitive cost and difficulty of retrieving these specific communications from amid vast numbers of more mundane audio files can force companies to accept a costly settlement.
Rather than spending valuable person-hours listening to recorded audio, Nexidia Forensic Search enables compliance managers, lawyers and auditing professionals to establish key words and phrases to be “searched” and identified in the audio record.
Government
Audio intelligence and the ability to analyze surveillance in multiple languages is mission critical for organizations in the fight against illegal or dangerous activities. Manually translating, transcribing and searching these communications can take up to 5 times real time- costing precious time, money and manpower.
Nexidia’s technology enables timely identification of threats and trends contained within voice recordings.
Contact Center
Recorded audio from contact center interactions provides organizations with tremendous customer and market intelligence. Obtaining insight into this information asset allows forward-thinking organizations to integrate the customer voice into their business-enabling them to impact customer satisfaction, improve product offerings, reduce operational costs, identify and maximize revenue opportunities and ensure adherence to internally or externally regulated processes.
Nexidia Enterprise Speech Intelligence provides a scalable speech analytics solution - enabling customers to extract actionable intelligence from these untapped assets.
Rich Media
Rich media providers are faced with vast and ever increasing volumes of data and growing demand from consumers to make this media accessible. The growth in rich media content has created a market need to go beyond traditional metadata approaches and unlock the rich information contained in audio and video in order to easily index, search and access this content. Companies in industries such as media creation & aggregation, content management, advertising, broadband and telecom recognize the need to dramatically enhance discoverability, relevance, and personalization of rich media search to create new advertising opportunities and new subscription services around the searching, navigating, and playback of rich media.
Nexidia Developer Edition enables content creators and aggregators to rapidly deliver rich media search capabilities to their consumers through the web.
The Phonetic Approach
Phonetics is the systematic study of the sounds of human speech. It provides a means of describing and classifying virtually all the sounds that can be produced by the human voice. This study is based on phonemes - the smallest unit of human speech.
All utterances made in the entire world have been catalogued within a 400 phoneme range. The majority of languages fall around the 40 phoneme range. Searches using phoneme pattern matching can be executed on:
• blended words
• proper names, slang, code words, brands, etc.
• non-standard grammar patterns
• ad-hoc use of different languages
Phonetic Searching
As archives of digital audio expand, and people need to find specific information within those archives, it becomes clear that a highly efficient method of searching recorded media is required. The metadata that currently tags audio information (such as title, date of recording, subject, or person) is not sufficient for the accurate and rapid retrieval of specifically requested data.
Nexidia’s Phonetic Search Engine (abbreviated as PSE, trademark-pending) is an open-vocabulary retrieval system, which greatly reduces the time, and increases the accuracy of searches against large collections of recorded speech. Searches can be conducted at speeds over 548,000 times faster than real-time playback of the recordings.
The Advantages of Phonetic Searching
There are compelling reasons why using the Phonetic Search Engine is preferable to using speech-to-text searches. The PSE has a completely open vocabulary. No base lexicon is required. In contrast, the speech-to-text method must map all words into lexicon entries. For example, if a word is not in the dictionary, the speech-to-text solution will not find it in the audio
Another advantage of the PSE is that accuracy is not compromised for speed. Speech-to-text must limit its search and must make hard decisions about word bindings – else searches are too slow and unpredictable. This is why speech-to-text lexicons are never large enough and seldom contain enough key search terms, which are often proper names or unusual phrases.
Some speech-to-text systems have tried to improve their accuracy by introducing a semantics-based constraints i.e., probability of word sequences process, that can sometimes produces inaccuracies and extends processing time. In addition, it will never be complete due to the inherent flexibility of the human language. Phonetic searching emphasizes how things sound, not what strict grammar rules may infer they mean. This is especially evident when searching for proper names. Exact spelling is not required.
For example, the PSE can find references to “Sudetenland” spelled properly, or even as “ Sue Dayton Land.” This might be an extreme example, but the utility of this kind of searching becomes obvious when you look at a name like “Qaddafi” that has been written with many different spellings such as Khaddafi, Quadafy, and Kaddafi. This name could be input into the PSE as KADOFFEE and still be found.
