"Jonathan Sachs" <xxxxxxx@earthlink.not> wrote in message
news:qf7i91tdt1t47kh8j3g3bjvbfag45422h2@4ax.com...
>I want to touch on a point that I missed in my previous message.
>
> Natural-language speech recognition programs rely heavily on
> word-sequence frequencies to achieve accuracy. For example, if the
> program hears you say something that sounds like "I doughnut," it is
> likely to conclude that you said "I do not," because that is a much
> more likely sequence of words.
>
> When you contemplate using speech recognition to enter authors' names,
> search strings, etc., you have not only passed beyond the scope of
> limited-vocabulary speech recognition; you have passed beyond the
> scope of natural-language speech recognition, too. You are asking the
> software to recognize speech that is not only drawn from an unlimited
> vocabulary, but also lacks reliable word-frequency clues. This is
> beyond the capability of any currently available commercial software,
> even running on a full-fledged personal computer with a high-quality
> boom microphone, used by an experienced operator under nearly ideal
> conditions.

I disagree that these terms necessarily come from open-ended unlimited
vocabularies.
First, book author names, titles, isbns, etc are from large, well-organized
*finite* collections of terms,
essentially "books in print". Next, academic authors of preprints or
journal articles are, in principle, collectible
into similar finite collections.

When you get to general "search phrases", you're right, but I would hope to
train
my ebook listener on the technical terms that I search most often for, as
again, this is
a limited list, often repeated.

If, in the end, certain searches required a tablet pen input to recognize
the
term, so be it.

regards,
alan