TY - GEN
T1 - Collaborative Learning to Generate Audio-Video Jointly
AU - Kurmi, Vinod K.
AU - Bajaj, Vipul
AU - Patro, Badri N.
AU - Venkatesh, K. S.
AU - Namboodiri, Vinay P.
AU - Jyothi, Preethi
PY - 2021/6/11
Y1 - 2021/6/11
N2 - There have been a number of techniques that have demonstrated the generation of multimedia data for one modality at a time using GANs, such as the ability to generate images, videos, and audio. However, so far, the task of multi-modal generation of data, specifically for audio and videos both, has not been sufficiently well-explored. Towards this, we propose a method that demonstrates that we are able to generate naturalistic samples of video and audio data by the joint correlated generation of audio and video modalities. The proposed method uses multiple discriminators to ensure that the audio, video, and the joint output are also indistinguishable from real-world samples. We present a dataset for this task and show that we are able to generate realistic samples. This method is validated using various standard metrics such as Inception Score, Frechet Inception Distance (FID) and through human evaluation.
AB - There have been a number of techniques that have demonstrated the generation of multimedia data for one modality at a time using GANs, such as the ability to generate images, videos, and audio. However, so far, the task of multi-modal generation of data, specifically for audio and videos both, has not been sufficiently well-explored. Towards this, we propose a method that demonstrates that we are able to generate naturalistic samples of video and audio data by the joint correlated generation of audio and video modalities. The proposed method uses multiple discriminators to ensure that the audio, video, and the joint output are also indistinguishable from real-world samples. We present a dataset for this task and show that we are able to generate realistic samples. This method is validated using various standard metrics such as Inception Score, Frechet Inception Distance (FID) and through human evaluation.
KW - Audio-video generation
KW - Cross-modal learning
UR - http://www.scopus.com/inward/record.url?scp=85115144447&partnerID=8YFLogxK
U2 - 10.1109/ICASSP39728.2021.9413802
DO - 10.1109/ICASSP39728.2021.9413802
M3 - Chapter in a published conference proceeding
AN - SCOPUS:85115144447
SN - 9781728176062
VL - 2021
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 4180
EP - 4184
BT - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PB - IEEE
T2 - 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021
Y2 - 6 June 2021 through 11 June 2021
ER -