Dragon Voice Recognition Computer Software
Learn About The Newest Digital Technology
At one point I switched from the Shure mic and ACPA board to an OEM sound card and VXI mic. Performance seemed to drop quite a bit. Also, I am an expert Dragon user (I used to work there -- it helps). Using the product "right", following all the directions, getting a good understanding of how macros work, the best ways to correct things, etc., made a big difference compared to other people I know who weren't as proficient. If you're aggressive about renaming hard to recognize words, correcting errors, training words, etc., all this can really help I think. In the end, however, the number of different factors that can affect speech recognition performance (background acoustics, computer, microphone, speech card, user motivation, version of software, number of applications used, degree of consistency of user's subject matter, degree of consistency of user's voice, user understanding of product, application with which software is being used, -- to name just a few --) will make it very difficult to identify specific causes. I suggest that people following up to tghis thread try for answers of the form: I changed this and got some improvement/worsening vs. I do this and maybe that's why it works/doesn't. The former is an experiment, and the latter is speculation... ----- goodman@eecs.harvard.edu Joshua Goodman -- Computer Science Graduate Student studying NLP On Thu, 16 Jan 1997, edrose19 wrote: > Would like to propose a new thread of discussion. There > seems to be a very wide range in the performance of Dragon, > Kurzweil and Voicetype. NOT TALKING ABOUT COMPARING THE > PRODUCTS, but, rather, why User A of Dragon would > experience far better/worse performance than User B of Dragon, etc. > Does anyone have any ideas as to why? > Rose > >