[MV] Voice recognition for transcription: Opinions sought

[Jonathan Levi, M.D.]

At 8:31 PM -0800 2/21/07, Rena Bussinger wrote:
>How involved is the initial training process? I am producing my 
>voice recordings from personal history interviews with subjects who 
>are active and willing participants. Would it be feasible to create 
>a speaker profile for each of my interview subjects, have them go 
>through the initial voice training process (on my laptop) and then 
>playback their recorded audio with iListen or DNS/Parallels active?

I'm afraid it doesn't sound practical. It will probably take each 
interviewee an unacceptably long time to train his/her own voice 
model; plus, in the early stages of use, there will probably be a lot 
of transcription errors for each user. Training a voice model is only 
worth the time and effort if it's going to be used for a long time 
afterwards, IMO. --Jonathan