Can Transana produce a transcript for me?
Transana does not automatically generate a transcript, because voice recognition technology is not yet sophisticated enough to be able to produce a useful transcript from naturally occuring talk. Voice recognition software requires a single speaker, good audio quality, spoken punctuation, and extensive training of the software by the speaker. Most research video has, at most, one of these elements. Therefore, voice recognition simply isn’t practical. In Transana, you use the Transcript window’s Ctrl-S function to start and stop the video, and you type what you hear. It’s a slow process, but it’s the best way to produce an accurate, usable transcript. One researcher listens to his video, then dictates what he hears into his voice recognition software. He says that he gets pretty good results this way.
Transana does not automatically generate a transcript, because voice recognition technology is not yet sophisticated enough to be able to produce a useful transcript from naturally occuring talk. See http://www.transana.com/support/VoiceRecognition.htm. Voice recognition software requires a single speaker, good audio quality, spoken punctuation, and extensive training of the software by the speaker. Most research video has, at most, one of these elements. Therefore, voice recognition simply isn’t practical. In Transana, you use the Transcript window’s Ctrl-S function to start and stop the video, and you type what you hear. It’s a slow process, but it’s the best way to produce an accurate, usable transcript. One researcher listens to his video, then dictates what he hears into his voice recognition software. He says that he gets pretty good results this way.
