Search results

Section: Publications & Resources

Publication: IEEE Transactions on Multimedia

The video captioning task aims to describe video content using several natural-language sentences. Although one-step encoder-decoder models have achieved promising progress, the generations always involve many errors, which are mainly caused by the large semantic gap between the visual domain and the language domain and by the difficulty in long-sequence generation.

Section: Events

September 13-15, 2021 Location: Zagreb, Croatia

Section: Events

October 18-22, 2021 Location: Virtual Conference

Section: Events

December 14-17, 2021 Location: Tokyo, Japan

Section: Events

November 16-19, 2021 Location: Virtual Conference

Section: Publications & Resources

Dr. Supavadee Aramvith received her B.S. (first class honors) degree in Computer Science from Mahidol University, Bangkok, Thailand, in 1993. She received her M.S. and Ph.D. degrees in Electrical Engineering from the University of Washington, Seattle, USA, in 1996 and 2001, respectively. 

Section: Publications & Resources

The IEEE Signal Processing Society (SPS) is honored to announce the elevation of 108 of its members to the grade of IEEE Senior Member. These members have demonstrated outstanding professional performance, exhibited professional maturity through long-term experience, and established themselves as leaders in their respective IEEE-designated fields of interest. 

What Your Job Will Be Like We are seeking a driven and results oriented Electrical Engineer to support existing research efforts to test geophysical instrumentation and perform signal analysis of seismic data. All research is team oriented and directed at increasing national and international monitoring capabilities for underground nuclear explosions. Opportunities exist to conduct research on improving methods for signal analysis of unique seismic datasets and interpret the results and communicate findings through presentations and publications.

Section: Publications & Resources

Associated SPS Event: IEEE ICASSP 2021 Grand Challenge Text-to-speech (TTS) or speech synthesis has witnessed significant performance improvement with the help of deep learning. The latest advances in end-to-end text-to-speech paradigm and neural vocoder have enabled us to produce very realistic and natural-sounding synthetic speech reaching almost human-parity performance. But this amazing ability is still limited to the ideal scenarios with a large single-speaker less-expressive training set.