The SCC Speech Text Module makes use of automatic speech recognition (ASR) technology to generate accurate text transcriptions and corresponding closed captions (subtitle) files from digital audio and video media. Text transcriptions and closed captions can also be translated into any number of additional languages, regardless of the original spoken language.
Closed caption (subtitle) files can be generated in either SRT or VTT industry standard formats in any number of target languages.
Upon insertion into the SCC MediaServer digial asset management system, each word in the primary transcription is added to a corresponding time-code database field and indexed for searching via the SCC Mediaserver search engine.
As a result, users of the SCC MediaServer system are able to perform searches on any word or phrase spoken within each audio/video file, and matching search words are automatically highlighted in the transcript of each result record.
Users are also able to click on any word in the displayed transcript to automatically cue and initiate playback of the audio/video file at the exact point that word is spoken. During playback words are automatically highlighted as each word in spoken, greatly enhancing user experience.