Luminaries are the kinds of people who make the
speech technology industry move forward, whether
through technological innovation, visionary ideas,
thought leadership, or pushing, expanding, or
redefining current boundaries. The four luminaries
chosen this year by the editors of Speech Technology
have helped define the current state of the market,
but more importantly, their influence will continue to
shape the industry as a whole—and the world
beyond—well into the future.
/ BY LEONARD KLIE AND ERIC BARKIN /
14 | Speech Technology SEPTEMBER 2009 www.speechtechmag.com
head of the class living up to a set of standards
HCCL’S JUAN LOQUENDO’S
GILBERT, PH.D. PAOLO BAGGIA
H E H A S N ’ T R E VO L U - T E X T - T O - S P E E C H systems have not always had the best
T I O N I Z E D the way track records when it comes to reading documents out loud.
Americans vote for their Systems have generated some laughable mispronunciations
favorite candidates—at when they came across words they didn’t recognize. And it
least not yet—but that has been the same for speech recognition systems, which have
might all change if Juan generated some equally comical spellings for complex words
Gilbert, Ph.D., keeps or acronyms spoken by a user.
pushing along the way he To address this, speech systems include a dictionary of
has this past year. As head words whose pronunciations aren’t predictable from their
of the Human Centered spellings. But these dictionaries aren’t standard from one ven-
Computing Lab (HCCL) at dor to the next, so compiling them was often an arduous task.
Auburn University, where For Paolo Baggia, director of international standards at Lo-
he also served as an asso- quendo, an easier way had to exist. And so he set out, under
ciate professor of computer science and software engineering the aegis of the World Wide Web Consortium (W3C), to au-
for the past nine years, Gilbert was instrumental in the design thor the Pronunciation Lexicon Standard (PLS 1.0), a frame-
and development of Prime III, a voting machine with a multi- work for specifying word pronunciations used by speech
modal user interface and automatic speech recognition tech- syst