Voice Driven Emotion Reconstruction

For an alternative to videophone which requires wide
bandwidth, this research attempts to realize facial
expressions reconstruction based on voice
information by proposing a new system called Voice
Driven Emotion Recognizer Mobile Phone (VDERM) .
This system intends to reconstruct facial
expressions at the receiving end based on the
extracted emotions from the received voice tone. The
emotion recognizer system at the receiver side
identifies the emotion state of the received speech
signal and displays the corresponding facial
expression of that particular emotion. Thus, there
is no need to transmit the actual video signal from
the transmitter side and therefore, the existing 2G
mobile phone infrastructures can be used. A few
papers have been published in the course of
completing this research as listed in the appendix.
Aishah has continued to publish a journal paper
entitled Voice Driven Emotion Recognizer Mobile
Phone: Proposal and Evaluations in the
International Journal of Information Technology and
Web Engineering ( Vol. 3, Issue. 1, March 2008, pp.
53-69) as an extension to the previous work.

Autorentext
Aishah Abdul Razak received the B.Eng.(Hons.)Electronic Majoring Telecommunications from Multimedia University, Malaysia in 2000. Then she joined the university as academician and pursued MSc.(IT) by research entitled "Voice Driven Emotion Reconstruction for Virtual Reality Telecommunication" under the supervision of Prof. Ryoichi Komiya.

Klappentext
For an alternative to videophone which requires wide bandwidth, this research attempts to realize facial expressions reconstruction based on voice information by proposing a new system called "Voice Driven Emotion Recognizer Mobile Phone (VDERM)". This system intends to reconstruct facial expressions at the receiving end based on the extracted emotions from the received voice tone. The emotion recognizer system at the receiver side identifies the emotion state of the received speech signal and displays the corresponding facial expression of that particular emotion. Thus, there is no need to transmit the actual video signal from the transmitter side and therefore, the existing 2G mobile phone infrastructures can be used. A few papers have been published in the course of completing this research as listed in the appendix. Aishah has continued to publish a journal paper entitled 'Voice Driven Emotion Recognizer Mobile Phone: Proposal and Evaluations' in the International Journal of Information Technology and Web Engineering ( Vol. 3, Issue. 1, March 2008, pp. 53-69) as an extension to the previous work.