Mark Plumbley

Thanks to all co-authors and collaborators! @daizheqi1 @LiXiquan3423 @WeiLongZheng1 @markplumbley @QiuqiangK and many others who contributed to this work.

We found LALMs can answer ~50% of questions with SILENT input on the major benchmark. We present AudioMCQ: largest LALMs post-training dataset (571k samples) & Audio-Contribution-Aware SFT-RL post-training paradigm, achieving new SOTA Paper: arxiv.org/abs/2509.21060 #AudioAI

I'm super excited to announce that the MSR paper has been accepted at MMSP 2025, and the inaugural MSR challenge has been accepted as a grand challenge at ICASSP 2026! Thanks to Zheqi Dai, @QiuqiangK and @markplumbley for joint work on the paper, and @yaqubhai , Wanying Ge, Helin Wang and Prof. Kong's joint work on the challenge proposal. We'll share more information soon. Looking forward to advancing the next generation of solutions to the cocktail party problem!

📢Excited to announce the 1st workshop on 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗮𝗻𝗱 𝗣𝗿𝗼𝘁𝗲𝗰𝘁𝗶𝘃𝗲 𝗔𝗜 𝗼𝗻 𝗖𝗼𝗻𝘁𝗲𝗻𝘁 𝗖𝗿𝗲𝗮𝘁𝗶𝗼𝗻 (𝗚𝗲𝗻𝗣𝗿𝗼𝗖𝗖) at #NeurIPS2025 ! See you there🌴 🗓️Deadline: August 22nd, 2025 (23:59, AoE) 📷More info: genprocc.github.io

“United by Acoustics—FA Euronoise 2025 Family Shot.”

Great to have the opportunity to give a plenary talk at @FAeuronoise2025 - thanks to the organizers for putting on a great event!

Why existing music source separation models are already so good (easily >10 dB SDR), but mixing engineers rarely use them? Our answer: They need music source **restoration**. We introduce the music source restoration (MSR) task, which not only aims to separate the instruments, but also restore them to a state before any EQ, Compression, Reverb, Distortion and codec artifacts (e.g. MP3). We introduce the first dataset for this task, and found that the restoration task is much harder than separation. Paper: arxiv.org/abs/2505.21827 Model + Code: github.com/yongyizang/mus… Dataset: huggingface.co/datasets/yongy… HuggingFace Spaces: huggingface.co/spaces/yongyiz… Work done with Zheqi Dai, @markplumbley and @QiuqiangK . We are organizing a MSR challenge - if you are interested in participating, co-organizing or just learning more about this, please reach out to myself (zyy0116@gmail.com) or Prof. Qiuqiang Kong (qqkong@ee.cuhk.edu.hk)!

Relais Médicis, our favourite hotel in Paris, now has a cat "Chanel", do look out for her if you visit!

Looking forward to talking about Noise Network Plus at the Institute of Acoustics (@ioauk) London Branch hybrid meeting 6pm-7pm Wednesday 14 May 2025. (Registration for in-person attendance closes 5pm Mon 12 May) More below and at ioa.org.uk/civicrm/event/…

Representing #NoiseNetworkPlus at Urban Sound Symposium 2025 in Zurich last week (28-30 April), presenting our poster, with @ajtorija and Charlotte Clark. Poster: zenodo.org/records/147734… @s_graetzer @DrAlanHunter @cvssp_research @PeopleCentredAI

And the second day of #USS2025 starts this morning! @ClaudioGuarnac2 talking about traffic noise modeling and @ajtorija talking about drone noise.

Coming up 14 May 2025: 'London Branch hybrid meeting 'Noise Network Plus: A new interdisciplinary network to address noise pollution' presentation by Prof Mark Plumbley, University of Surrey (Centre for Vision Speech and Signal Processing) 19:00 - 19:00 AECOM, London, E1 8FA #acoustics #sound #noise #vibration ioa.org.uk/civicrm/event/…

JOB: Research Fellow in Generative Audio AI Applications from under-represented groups encouraged, incl. women, people from Black, Asian and minority ethnic groups, & people with disabilities. genai.ac.uk jobs.surrey.ac.uk/021025 @cvssp_research @PeopleCentredAI

Presenting "A decade of DCASE" @ieeeICASSP to a fully packed room. Co-authors @markplumbley, @RSerizel, @TuomasVirt @HeittolaToni. @DCASE_Challenge and @DCASE_Workshop would not be the same without the work of all the task organizers.

SPS Journal at #ICASSP2025 today: Apr 11: 2pm-3:30pm SAM-PJ1 (Poster 3G) Selective-Memory Meta-Learning with Environment Representations for Sound Event Localization and Detection Jinbo Hu, @Kalario_Cao, Ming Wu, @QiuqiangK, Feiran Yang, P, Jun Yang AAM openresearch.surrey.ac.uk/esploro/output…

Talk at #ICASSP2025 this pm: Apr 11: 2:30pm-2:45pm A decade of DCASE: achievements, practices, evaluations and future challenges @AnnamariaMsros @RSerizel @HeittolaToni @TuomasVirt P AASP-SS6-L7: 50 years of Audio and Acoustic Signal Processing Preprint: arxiv.org/abs/2410.04951

On now at #ICASSP2025: @Arshdee71825259 and Gabriel Bibbo presenting our demo: Apr 11: 11:30am-1:00 pm Personalized live sound recognition using efficient PANNs Arshdeep Singh, @LiuHaohe, Gabriel Bibbó, Thomas Deacon, Mark D. Plumbley Show and Tell Session II (Room: MR1.06)

Our paper at #ICASSP2025 today: Yi Yuan et al, w @wang_wenwu: "Sound-VECaps: Improving Audio Generation With Visual Enhanced Captions" Apr 10, 5:00pm-6:30pm, AASP-P22 Preprint/code/dataset/demos: yyua8222.github.io/Sound-VECaps-d… // @cvssp_research @PeopleCentredAI

Our paper being presented at #ICASSP2025 today (Apr 8: 5:00pm-6:30pm) FlowSep: Language-Queried Sound Separation with Rectified Flow Matching Yi Yuan, Xubo Liu, @LiuHaohe, Mark D. Plumbley, @wang_wenwu AASP-P4: Audio Source Separation I More at: audio-agi.github.io/FlowSep_demo/

Delighted to be at the launch of Noise Network Plus last week, the £1.8 m project where engineers, policymakers, industry, social scientists & campaigners have joined forces to create quieter products, buildings & transport systems, aiming to cut noise over the next 10-15 years