Profile avatar
pa9501460.bsky.social
R&D expert in Speech & Audio Processing and Coding (Compression) | Researcher @Dolby utilizing Deep Learning http://linkedin.com/in/arijitbiswas
4 posts 51 followers 131 following
Getting Started
Posts 6 Comments 3

MusicEval, a dataset of 2748 music clips with expert ratings, was created for evaluating text-to-music systems; a CLAP-based assessment model was also developed.

submitted 46 days ago • 0 comments

Are you a PhD student specializing in audio or AI? Interested in an internship with us in Barcelona? Apply here! We've had the pleasure of working with talented interns in the past, and the experience has been mutually very rewarding. www.linkedin.com/jobs/view/40...

submitted 51 days ago • 0 comments

🎉 Our paper, "RF-GML: Reference-free Generative Machine Listener," has been accepted to #ICASSP2025! 📄 Read the paper here: arxiv.org/abs/2409.10210 We look forward to presenting our findings at #ICASSP2025.

submitted 69 days ago • 0 comments

Do you want to work with me for some months? Two internship positions available at the Music Team of Sony AI in Barcelona! 👇

submitted 76 days ago • 1 comment

A new benchmark for spatially aligned audio-video generation was created, including a dataset, baseline diffusion model, and evaluation metrics; results showed gaps between the model and ground truth.

submitted 80 days ago • 0 comments

New paper from our lab, by Mark Saddler, using machine learning to test the role of temporal coding in hearing. Here is a quick summary. (1/n) www.nature.com/articles/s41...

submitted 86 days ago • 2 comments