NEC Corporation has developed a system for automatically creating multimedia blogs by talking to a speech recognition enabled robot which helps illustrate the day’s events.
The system has been developed on NEC’s prototype robot PaPeRo, and is initialised when a user begins a conversation with PaPeRo about the events of their day, which the system then records and analyses. PaPeRo then searches for suitable multimedia contents on the internet, including images, illustrations and music, which are automatically uploaded and edited along with the video recording on the user’s blog.
It integrates large-vocabulary, continuous speech recognition technology, which converts the speech content into text and extracts important keywords, and natural language text retrieval technology, which enables searching of contents on the internet. Multimedia web contents matching the extracted keywords are then uploaded and edited on the user’s blog, enabling effortless creation of a multimedia blog.
Analysing the syntactic relationship, such as direct objects and predicate verbs, the system calculates similarities between the text in the contents on the internet and the video message text converted by a speech recognition. This allows searching and accurate location of multimedia contents suitable to the contents of the text message.