Beginning of this page
Jump to content

Japan

Beginning of content
Current position

Home > News Room > Text

NEC Develops Automatic Multi-Media Blog Creation System
- Robot aids gathering and editing of blog contents -

*****For immediate use March 5, 2007


Tokyo, March 5, 2007 --- NEC Corporation announced development of a new system for automatically creating multi-media blogs. The new system has been developed on NEC's prototype robot PaPeRo, and is initialized when a user begins a conversation with PaPeRo about the events of their day, which the system then records and analyzes. Following this, PaPeRo searches for suitable multi-media 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. This new system facilitates ease of multi-media-rich blog creation.

The novel system has been realized by integrating (1) large-vocabulary, continuous speech recognition technology, which converts the speech content of the video message into text and extracts important keywords, and (2) natural language, text retrieval technology, which enables searching of contents on the internet.

The features of the new system are as follows:

  1. Chat with PaPeRo to create your daily blog
    The speech contents of the video message are converted into text and extracted through large-vocabulary, continuous speech recognition technology. Multi-media web contents matching the extracted keywords are then uploaded and edited on the user's blog, enabling effortless creation of a multi-media blog.
  2. Natural language, text retrieval technology enables searching of internet contents
    Analyzing 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 engine (developed with a large database of spoken words). This allows searching and accurate location of multi-media contents suitable to the contents of the text message.

In recent years, blogs have gained a strong position within society as the voice of consumer opinion, and bloggers have started to avail more of voice, images, and other multi-media contents to enrich their blogs. However, it is very time consuming to locate appropriate and attractive contents on the web. NEC's new system facilitates simple and easy creation of multi-media rich blogs by carrying out the background work for the user.

The technology developed for this system can also be applied to a variety of other information terminals. NEC will continue to develop this system toward early commercialization.

* This research result will be presented at the "13th Annual Conference of the Association of Natural Language Processing" on March 20, which is being held from March 19 - 23 at Seta Campus of Ryukoku University (Ohtsu City, Shiga Prefecture, Japan).

About NEC Corporation
NEC Corporation (NASDAQ: NIPNY) is one of the world's leading providers of Internet, broadband network and enterprise business solutions dedicated to meeting the specialized needs of its diverse and global base of customers. NEC delivers tailored solutions in the key fields of computer, networking and electron devices, by integrating its technical strengths in IT and Networks, and by providing advanced semiconductor solutions through NEC Electronics Corporation. The NEC Group employs more than 150,000 people worldwide.
For additional information, please visit the NEC home page at: http://www.nec.com
* Newsroom: http://www.nec.co.jp/press/en/

***


NEC Press Contacts

In Japan
Diane Foley
NEC Corporation
d-foley@ax.jp.nec.com
+81-3-3798-6511


Readers are advised that the press releases and other information posted on this site are current only on their original publication date. Please note that such press releases and other information may now be outdated or rendered inaccurate due to passage of time or subsequent material changes in facts and circumstance.

End of content
End of this page
Top of this page