Nice work and brings us one step closer to unifying speech and audio models!

I'll be in New Orleans next week for NeurIPS. Happy to chat about audio & speech processing, or applied research in the industry. Feel free to DM me to chat! #NeurIPS2023

Spotted Yann LeCun in the wild at NeurIPS! Amazing ideas and discussions around self-supervised learning #NeurIPS2023

The 6 pages of responsible NLP checklist is a lot. Though some of the questions were a helpful reminder to add details, however, I would have preferred a smaller targeted checklist where the intended audience and the checklist’s impact was clearly specified.

Just learned despite everyone voting down *CL's 🤡-y arxiv embargo policy, it's still firmly in place for ACL 2024. If *CL were a company, the board & leadership wd be fired, the talent wd've left 5 years ago, the common stock wd be worth $0, & WSB wd be taking an interest.

Paper proposing to leverage audio-language models to measure audio quality in multiple tasks (TTA, TTM, speech denoising, etc.), in a reference-free way. One of the tricks is to compare against multiple *and opposite* quality-related text prompts. arxiv.org/abs/2402.00282

``PAM: Prompting Audio-Language Models for Audio Quality Assessment,'' Soham Deshmukh Dareen Alharthi Benjamin Elizalde Hannes Gamper Mahmoud Al Ismail Rita Singh Bhiksha Raj Huaming Wang … ift.tt/6HIcVpn

In this issue: LLMs in the Imaginarium: Tool Learning through simulated trial and error; Benchmarking LLMs across languages, modalities, models and tasks; Training audio captioning models without audio. msft.it/6016cIfvY

``Audio Entailment: Assessing Deductive Reasoning for Audio Understanding,'' Soham Deshmukh, Shuo Han, Hazim Bukhari, Benjamin Elizalde, Hannes Gamper, Rita Singh, Bhiksha Raj, ift.tt/mMbigfn

We have started hiring research interns for 2025. I am looking for a PhD student with background in multimodal generation/understanding. metacareers.com/jobs/374372872…. Flexible with the timing but summers are usually the best :) #internship2025 #multimodal #audio #speech AI at Meta