figure 1. the siri interface accepts speech
as input, attempting to support a dialogue;
in the first action, a query for a phone
number shows a message conveying the
system’s understanding of the question as
it performs a search.
figure 2. in the second action, the system
replaces the confirmation bubble with
the answer, offering a command to make
the phone call; note the use of graphics
alongside text to enrich the output.
figure 3. in the concluding action, the
system partly understands the intention
of the question (about a location) but
incorrectly interprets a request for a
distance as a request for a location.
and suggesting promising directions
for research.
speech input
Speech-based user interfaces gener-
ally, and speech for search input in
particular, are likely to gain a much
stronger presence in the coming years.
At least three technological trends sup-
port the move toward spoken queries:
First, phone-based mobile devices pro-
vide a natural way to capture speech,
since phones are used in large part
for spoken conversations. Second, the
technology for speech recognition, af-
ter years of only incremental progress,
is improving by leaps and bounds,
thanks to huge data repositories being
generated through the use of mobile
phones. (To assemble a large train-
ing set of spoken corrected data for
its speech-recognition system, Google
hosted, from 2007 to 2010, a free 411
information service for phones.
28) And
third, touch-screen interfaces are in-
creasingly popular, especially when
paired with mobile devices. Neither
small devices nor touch screens lend
themselves well to typing, making spo-
ken input more attractive, though clev-
er finger-swipe-based input methods
(such as Shape Writer for entering text39
and Gesture Search for menu naviga-
tion19) provide compelling alternatives
to typing.
social search: collaboration
Though observational studies have
found that people often search collaboratively, tools have only recently been
developed to explicitly support people
searching together. Such support reflects a broader research renaissance
in tools for real-time shared activity
(such as shared online whiteboards
and document-editing tools).