Wenqian Cui

@umpedronosapato Thanks man!

@easy4u2remember Congratulations! 🤘

Super excited to share that I recently had three papers accepted at AI conferences - two first-authored papers at ACL 2025 main conference and one at ICML 2025! 🎓🏆🚀 Immense gratitude to my brilliant co-authors who made this journey possible! #NLP #ACL2025 #ICML2025

I'm excited to continue pushing the boundaries of speech AI and would love to discuss research ideas in person! 🌟💡 If you're attending ACL 2025 in Vienna, let's meet up and explore potential collaborations. 🤝🌍

3. "Improving Conversational Capabilities of Speech Language Models via Generative Dual-channel Spoken Dialogue Learning" (ICML 2025) 💬👥

2. "VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models" (ACL 2025) 🧪🎯   ArXiv: lnkd.in/etjJA-Uz GitHub: lnkd.in/eNbszVDp 📈🔬

1. "Recent Advances in Speech Language Models: A Survey" (ACL 2025) 📚🔍   ArXiv: lnkd.in/etqDACvW GitHub: lnkd.in/ee3jQsvY 📊📝

``VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models,'' Wenqian Cui, Xiaoqi Jiao, Ziqiao Meng, Irwin King, ift.tt/N0X8uW2

9. ⚠ Current challenges in SpeechLM research include: - Understanding component choices for better efficiency. - Improving real-time generation capabilities. - Addressing safety risks (toxicity & privacy). There's much work ahead to enhance SpeechLMs! #ResearchChallenges #AI

8. ✅ We categorize the evaluation of SpeechLMs into different aspects, including representation, linguistic, paralinguistic evaluations and more. We also emphasize the need for human evaluations of SpeechLMs.

🚀 Really excited to share our new survey paper on Speech Language Models is now available! Dive deep into the world of speech-based foundation models and explore the future of human-computer interaction through voice. Read it here: arxiv.org/abs/2410.03751 #SpeechLM #AI

@umpedronosapato @ISMIRConf @jackjamesloth @matdiffusion Sounds really interesting! Congrats!!

Our paper 'Between the AI and Me: Analysing Listeners' Perspectives on AI- and Human-Composed Progressive Metal Music' just got accepted to @ISMIRConf 🤘 let's bring some #progmetal to SF 🎸 (w/ @jackjamesloth and @matdiffusion)

Fantastic time presenting at EvoMUSART 2024! Really grateful for the opportunity to network with such incredible minds. Looking forward to seeing you guys in the future! Also, a big thank to my supervisor @matdiffusion and co-author @umpedronosapato!!! @EvostarConf

Our new paper is out! 💡"MusicMagus: Zero-Shot Text-to-Music Editing via Diffusion Models" 📰arxiv: arxiv.org/abs/2402.06178 🎶demo: bit.ly/musicmagus-demo 🎥video: veed.io/view/227db478-…