Filters








3 Hits in 3.5 sec

Mic2Mic

Akhil Mathur, Anton Isopoussu, Fahim Kawsar, Nadia Berthouze, Nicholas D. Lane
2019 Proceedings of the 18th International Conference on Information Processing in Sensor Networks - IPSN '19  
With these in mind, we apply the principles of cycle-consistent generative adversarial networks (CycleGANs) to learn Mic2Mic using unlabeled and unpaired data collected from different microphones.  ...  In this work, we propose Mic2Mic -- a machine-learned system component -- which resides in the inference pipeline of audio models and at real-time reduces the variability in audio data caused by microphone-specific  ...  Audio and Speech applications of GANs. In the last few years, GANs have been used extensively for generating images [24, 30] .  ... 
doi:10.1145/3302506.3310398 dblp:conf/ipsn/MathurIKBL19 fatcat:gdr6htyeczaqlirpsto757grly

Generative Adversarial Networks in Human Emotion Synthesis:A Review [article]

Noushin Hajarolasvadi, Miguel Arjona Ramírez, Hasan Demirel
2020 arXiv   pre-print
In fact, affective computing observed a rapid derivation of generative models during the last two decades.  ...  In this context, facial expression synthesis, speech emotion synthesis, and the audio-visual (cross-modal) emotion synthesis is reviewed extensively under different application scenarios.  ...  Acknowledgements We would like to thank Eastern Mediterranean University for supporting this research work through the BAP-C project under the grant number BAP-C-02-18-0001.  ... 
arXiv:2010.15075v2 fatcat:4ifqzcdkevbm3jrxhxy4rpdnba

Generative Adversarial Networks in Human Emotion Synthesis: A Review

Noushin Hajarolasvadi, Miguel Arjona Ramirez, Wesley Beccaro, Hasan Demirel
2020 IEEE Access  
As conclusions, we indicate common problems that can be explored from the Generative Adversarial Networks (GAN) topologies and applications in emotion synthesis.  ...  In fact, affective computing observed a rapid derivation of generative models during the last two decades.  ...  ACKNOWLEDGEMENTS We would like to thank Eastern Mediterranean University for supporting this research work through the BAP-C project under the grant number BAP-C-02-18-0001.  ... 
doi:10.1109/access.2020.3042328 fatcat:v4w44sw6kjgcldsqnonozr3rja