(Nexidia has) distinguished themselves through service to the industry and truly innovative new applications."
- Company Profile
- Phonetic Search Technology
- Phonetics Advantages
- Intellectual Property
- News & Events
- In The News
- Upcoming Webinars
- All Archived Webinars
- Community and Awards
- Board & Management
- Executive Management
- Technical Management
- Board Members
How Nexidia Phonetic Search works
Nexidia technology is based on phonetics—the systematic study of the sounds of human speech. In all the languages of the world, there are about 400 distinct sounds (known as “phonemes”) though most languages use only a fraction of that total. By using these tiny components of language, Nexidia is able to capture a true record of what is being said in an audio track, which can be searched more quickly, accurately and flexibly than with any other technology.
The process works in two phases. In the first phase, recorded audio is input into the system and a time-aligned phonetic index is created. Because phonemes are simply uttered sounds, the indexing is not affected by factors such as background noise, languages, dialects or speaking styles.
The second phase begins when a search is requested. Searches can be done directly on words or phrases, or using special operators such as Boolean strings or time-based proximity to other content. Nexidia’s proprietary search engine identifies and matches the phonetic equivalent of the search string and returns relevancy-ranked results.
The result is a process that not only creates the truest representation of spoken audio, but also enables the fastest, most accurate access to the information contained within the audio files. Whether used to improve the tagging of audio for syndication, to perform ad hoc searching for audio discovery and evidence, or for analysis and reporting on large volumes of customer call data, Nexidia delivers advantages no other technology can match.
Greater Speed: Phonemes are the tiniest building blocks of language. Using these small bits enables faster processing of audio and the ability to find words and phrases within context without requiring complex and difficult-to-maintain dictionaries.
Greater Accuracy: Today’s languages are changing rapidly. New words, industry terms, blended words, proper names, slang, code words, brand names, and even the non-standard mixing of different languages are all easily processed with the phonetic approach.
Greater Flexibility: Because Nexidia technology is not dictionary-based, there is no need to train the system for dialects or accents. Additionally, Nexidia is unaffected by unique speaking styles, jargon and even audio quality that can impact the performance and accuracy of text-to-speech methodologies, so you get what you need faster and with less impact on your resources.