Soham Deshmukh
@soham97.bsky.social
PhD candidate at Carnegie Mellon University
Senior Applied Scientist at Microsoft
🌐 https://soham97.github.io
🐙 https://github.com/soham97
🎓 https://scholar.google.com/citations?user=MasiEogAAAAJ&hl=en
Senior Applied Scientist at Microsoft
🌐 https://soham97.github.io
🐙 https://github.com/soham97
🎓 https://scholar.google.com/citations?user=MasiEogAAAAJ&hl=en
Reposted by Soham Deshmukh
Two new datasets were created; a prefix-tuning baseline and ADIFF, which uses a cross-projection module and position captioning, were compared; ADIFF showed significant improvements via objective and human evaluation.
ADIFF: Explaining audio difference using natural language
Soham Deshmukh, Shuo Han, Rita Singh, Bhiksha Raj
arxiv.org
February 10, 2025 at 7:07 AM
Two new datasets were created; a prefix-tuning baseline and ADIFF, which uses a cross-projection module and position captioning, were compared; ADIFF showed significant improvements via objective and human evaluation.
Great opportunity to work with amazing set of people!
📢 Audio AI Job opportunity at Adobe!
The Sound Design AI Group (SODA) is looking for an exceptional research engineer to join us in building the future of AI-assisted audio and video creation.
Strong ML background, GenAI experience a plus.
Details: adobe.wd5.myworkdayjobs.com/external_exp...
The Sound Design AI Group (SODA) is looking for an exceptional research engineer to join us in building the future of AI-assisted audio and video creation.
Strong ML background, GenAI experience a plus.
Details: adobe.wd5.myworkdayjobs.com/external_exp...
December 9, 2024 at 9:41 PM
Great opportunity to work with amazing set of people!