Multi-model story collection
The sharing process of the PicMemory is based on
attaching story contents to the photos. Family
members can capture or choose photos from albums
and then upload the photos to the family sharing space.
For bridging the technology gaps of the elderly, we
adopted voiced interface for the elderly to listen and
record the stories by the familiar way of speaking. And
we also provided the text interface for the younger
could type text messages as usual. The interfaces are
shown in Figure 1, we applied a long-press-gesture to
point out a region for leaving messages or recording
the voices, for example, we could describe the paint by
leaving a message on the paint. After recording voices,
we designed a double-click-gesture to stop recording
and also defined the tap gesture to play the recorded
voices. The PicMemory integrated with Text-To-Speech (TTS)
and Automatically Speech Recognition (ASR) modules,
which are provided by SpeechKit. The TTS module is
used to read out the text messages for the elderly who
may not be able to see words clearly. And the ASR
module can help the elderly to transcribe their oral
narratives without typing. At the end of this part, we
collected a set of multi-model stories that including
photos, voice recordings, and text messages.