The businesses that have built voice recognition
applications claim "Yes", but professional users are saying
"No", they maintain that voice recognition is good if it's restricted
to documenting a few minutes of audio. The software fails to produce and
falters, when large file size audio recordings need to be converted into text.
Many television firms which started for transcribing digital
voice records of the program using voice recognition, are disappointed, because
of the low accuracy levels and the time it takes to transcribe the audio. These
firms use the transcripts for adding captions to television programs, and for
the captions to sync with the audio, the precision of the transcripts required
is 100%. This system disappointingly fails with this account.
The recorded information used by research workers from
interviews and focus groups also have experimented with speech recognition and
some of them appeared to be filled with the performance of the software. They
maintain that the program needs to be trained for speech recognition and it's
very convenient for transcribing notes that are brief. Nevertheless for big
size recordings they still depend on transcription firms to document
information that is recorded. There are inherent deficiencies in the
application which have to be figured out before large scale use of the application
becomes possible.
An attorney working for a legal business tried the voice
recognition for transcribing recordings of court-room proceedings, but the end
results were fatal according to him. The voice recognition did not transcribe
several minutes of the proceeding, legal terms were mispronounced and finally
he had to phone his routine transcription company for recording the
proceedings. The lawyer failed to desire to use the application at all for the
transcription of brief notes.
The commonality of views expressed by professionals that are
different does signify that commercial use of voice recognition applications in
not possible, you can find limitations of what it cannot and what it can do.
The transcription services for the moment shall stay in the human domain, and automation
will need to wait until the technology is mastered for commercial use.