iiinova — where your digital self keeps evolving

Reposted by Emmanouil Benetos

arXiv cs.SD Sound @cssd-bot.bsky.social · 23/09/2026

Sungkyun Chang, Keshav Bhandari, Simon Dixon, Emmanouil Benetos: Synthesis and editing of multi-instrument audio mixtures using scalar-quantised latents with MIDI Span conditioning arxiv.org/abs/2609.25546 arxiv.org/pdf/2609.25546 arxiv.org/html/2609.25546

001

Reposted by Emmanouil Benetos

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 03/07/2026

Shahar Elisha, Mariano Beguerisse-D\'iaz, Emmanouil Benetos: Audio-Based Understanding of Audiobook Narration Appeal arxiv.org/abs/2607.02473 arxiv.org/pdf/2607.02473 arxiv.org/html/2607.02473

001

Reposted by Emmanouil Benetos

arXiv cs.SD Sound @cssd-bot.bsky.social · 02/09/2026

Yupei Li, Qiyang Sun, Emmanouil Benetos, Berrak Sisman, Bj\"orn Schuller: Perceptible or Not? Diagnosing Passive Fingerprints for Speech Deepfake Attribution arxiv.org/abs/2609.00765 arxiv.org/pdf/2609.00765 arxiv.org/html/2609.00765

001

Reposted by Emmanouil Benetos

arXiv cs.SD Sound @cssd-bot.bsky.social · 20/08/2026

Aditya Bhattacharjee, Christos Plachouras, Sungkyun Chang, Emmanouil Benetos: Finetuning Strategies for Querying Sounds by Vocal Imitation arxiv.org/abs/2608.19174 arxiv.org/pdf/2608.19174 arxiv.org/html/2608.19174

001

Reposted by Emmanouil Benetos

arXiv cs.SD Sound @cssd-bot.bsky.social · 25/06/2026

Jackson Loth, Xavier Riley, Simon Dixon, Emmanouil Benetos: Velocity Prediction in Automatic Guitar Transcription arxiv.org/abs/2606.24912 arxiv.org/pdf/2606.24912 arxiv.org/html/2606.24912

021

Reposted by Emmanouil Benetos

arxiv cs.CL @arxiv-cs-cl.bsky.social · 03/07/2026

Shahar Elisha, Mariano Beguerisse-D\'iaz, Emmanouil Benetos Audio-Based Understanding of Audiobook Narration Appeal arxiv.org/abs/2607.02473

001

Reposted by Emmanouil Benetos

arXiv cs.SD Sound @cssd-bot.bsky.social · 02/06/2026

Garcia, Bhattacharjee, Mason-Williams, Mason-Williams, Benetos, Reiss: Quality Audio Prototyping: a prototype system for unified sound retrieval and procedural generation arxiv.org/abs/2606.00629 arxiv.org/pdf/2606.00629 arxiv.org/html/2606.00629

111

Reposted by Emmanouil Benetos

arXiv cs.SD Sound @cssd-bot.bsky.social · 14/05/2026

Keshav Bhandari, Sungkyun Chang, Abhinaba Roy, Francesca Ronchini, Emmanouil Benetos, Dorien Herremans, Simon Colton: Text2Score: Generating Sheet Music From Textual Prompts arxiv.org/abs/2605.13431 arxiv.org/pdf/2605.13431 arxiv.org/html/2605.13431

001

Reposted by Emmanouil Benetos

arXiv cs.SD Sound @cssd-bot.bsky.social · 03/03/2026

Ma, Xia, Gao, Chen, Ye, Yang, Chang, Ding, Li, Yuan, Dixon, Benetos: CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction arxiv.org/abs/2603.00610 arxiv.org/pdf/2603.00610 arxiv.org/html/2603.00610

001

Reposted by Emmanouil Benetos

Ryan Heuser @ryanheuser.com · 26/02/2026

I'm on a 38(!)-author paper just published in Frontiers in Artificial Intelligence, "Computational hermeneutics: evaluating generative AI as a cultural technology". We splice Schleiermacher and hermeneutic theory into AI debates, arguing AI are "context machines". www.frontiersin.org/journals/art...

frontiersin.org

Frontiers | Computational hermeneutics: evaluating generative AI as a cultural technology

Generative AI (GenAI) systems are increasingly recognized as cultural technologies, yet current evaluation frameworks often treat culture as a variable to be...

55420

Reposted by Emmanouil Benetos

Christopher Mitcheltree @christhetree.bsky.social · 17/02/2026

SCRAPL: Scattering Transform with Random Paths for Machine Learning I’m excited to share our #ICLR2026 paper on SCRAPL: an algorithm that makes wavelet scattering transforms usable as differentiable loss functions! paper: openreview.net/forum?id=RuYwbd5xYa web: christhetr.ee/scrapl/

112

Reposted by Emmanouil Benetos

Elisabetta Versace @elisabettaversace.bsky.social · 24/01/2026

Our new pre-print shows how unsupervised clustering methods can identify biologically meaningful differences in early vocal production, with no human feedback. @antorrisi.bsky.social has led this interdisciplinary collaboration based on computational methods + #chicks 🐣 arxiv.org/abs/2601.12203

A) Dendrogram of the development dataset showing the clustering structure and optimal cut points, and spectrograms of representative calls extracted from cluster 0 and cluster 1. Within the main
clusters, we observed further branching; B) UMAP projection divided into 𝐾 = 2 clusters using HAC.

1208

Reposted by Emmanouil Benetos

arXiv cs.SD Sound @cssd-bot.bsky.social · 11/11/2025

Peeters, Rafii, Fuentes, Duan, Benetos, Nam, Mitsufuji: Twenty-Five Years of MIR Research: Achievements, Practices, Evaluations, and Future Challenges arxiv.org/abs/2511.07205 arxiv.org/pdf/2511.07205 arxiv.org/html/2511.07205

002

Reposted by Emmanouil Benetos

arXiv cs.SD Sound @cssd-bot.bsky.social · 11/11/2025

Termeh Taheri, Yinghao Ma, Emmanouil Benetos: SAR-LM: Symbolic Audio Reasoning with Large Language Models arxiv.org/abs/2511.06483 arxiv.org/pdf/2511.06483 arxiv.org/html/2511.06483

001

Reposted by Emmanouil Benetos

convai-rg.bsky.social @convai-rg.bsky.social · 03/11/2025

📢 Join our Conversational AI Reading Group! 📅 Thursday, Nov 6th | 11 AM - 12 PM EST 🎙 Speaker: Emmanouil Benetos ( @emmanouilb.bsky.social ) - Queen Mary University of London 📖 Topic: "Machine learning paradigms for music and audio understanding" 🔗 Details: (poonehmousavi.github.io/rg)

poonehmousavi.github.io

Pooneh Mousavi

Homepage of Pooneh Mousavi

021

Reposted by Emmanouil Benetos

C4DM at QMUL @c4dm.bsky.social · 31/10/2025

🎶 [C4DM Seminar] Advancing Music Experience Through Music Information Research 🕒 3–4 PM, 5th November 📍 TBC We’re excited to welcome Dr. Masataka Goto, Senior Principal Researcher at the National Institute of Advanced Industrial Science and Technology (AIST), Japan.

001

Reposted by Emmanouil Benetos

Prepared Minds Lab @preparedmindslab.bsky.social · 29/10/2025

our inventor @antorrisi.bsky.social with poster on #VocalEcho: Closed-loop system for vocal interactions #BioDCASE at 12:21 CET (11.21 UK time) 🐥 🔀 🤖🎈 Streaming dcase.community/workshop2025... @c4dm.bsky.social @emmanouilb.bsky.social @preparedmindslab.bsky.social @elisabettaversace.bsky.social

045

Reposted by Emmanouil Benetos

arXiv cs.SD Sound @cssd-bot.bsky.social · 24/09/2025

Aditya Bhattacharjee, Marco Pasini, Emmanouil Benetos: Scalable Evaluation for Audio Identification via Synthetic Latent Fingerprint Generation arxiv.org/abs/2509.18620 arxiv.org/pdf/2509.18620 arxiv.org/html/2509.18620

013

Reposted by Emmanouil Benetos

Ted Underwood @tedunderwood.com · 29/08/2025

New preprint on "Computational Hermeneutics," co-authored by too many people to list in one post. TL;DR: GenAI is a cultural technology, and needs to be evaluated in ways that recognize situatedness, plurality, and ambiguity as the conditions of meaning — not noise to be minimized.

papers.ssrn.com

Computational Hermeneutics: Evaluating Generative AI as a Cultural Technology

<div> <div> <div> <p>Generative AI (GenAI) systems are increasingly recognized as cultural technologies, yet current evaluation frameworks often treat cul

1213848

Reposted by Emmanouil Benetos

arXiv cs.SD Sound @cssd-bot.bsky.social · 17/07/2025

Sungkyun Chang, Simon Dixon, Emmanouil Benetos: RUMAA: Repeat-Aware Unified Music Audio Analysis for Score-Performance Alignment, Transcription, and Mistake Detection arxiv.org/abs/2507.12175 arxiv.org/pdf/2507.12175 arxiv.org/html/2507.12175

044

Reposted by Emmanouil Benetos

arXiv cs.SD Sound @cssd-bot.bsky.social · 08/07/2025

Ludovic Tuncay, Etienne Labb\'e, Emmanouil Benetos, Thomas Pellegrini: Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning arxiv.org/abs/2507.02915 arxiv.org/pdf/2507.02915 arxiv.org/html/2507.02915

005

Reposted by Emmanouil Benetos

Ivan MH @meresmanhiggs.bsky.social · 25/06/2025

Our paper on automatic sample identification (arxiv.org/abs/2506.14684) was accepted at @ismir_conf 2025! 🎵🎶 We propose an architecture that can detect music samples that have been reused in new compositions, even after pitch-shifting, time-stretching, and other transformations!🧵

Image with the name of the paper "REFINING MUSIC SAMPLE IDENTIFICATION WITH A SELF-SUPERVISED GRAPH NEURAL NETWORK", names of the authors (Aditya Bhattacharjee, Ivan Meresman Higgs, Mark Sandler, and Emmanouil Benetos from Queen Mary University of London, UK), and a figure with the illustrated ASID methodology (2 stages): (A) Given a query, we compute segment-level embeddings (fingerprints), matched to reference embeddings via approximate nearest-neighbour (ANN) search; based on which, candidate songs are retrieved from the reference database through a lookup process (dotted arrows). (B) A multi-head cross-attention (MHCA) classifier refines and ranks candidates using node embedding matrices NMq (query) and NMr (references).

162

Reposted by Emmanouil Benetos

arXiv Sound @arxiv-sound.bsky.social · 17/06/2025

CMI-Bench, a comprehensive music instruction following benchmark, evaluates audio-text LLMs on diverse MIR tasks, revealing performance gaps compared to supervised models and biases.

arxiv.org

CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following

Yinghao Ma, Siyou Li, Juntao Yu, Emmanouil Benetos, Akira Maezawa

001

Reposted by Emmanouil Benetos

C4DM at QMUL @c4dm.bsky.social · 06/06/2025

🎉 Congrats to Sungkyun Chang, Simon Dixon, and Emmanouil Benetos — their submission earned 2nd place at the 2025 Automatic Music Transcription Challenge! 🥈 ai4musicians.org/transcriptio... #C4DM #MusicAI #AMTChallenge2025.

ai4musicians.org

Leaderboard

031

Reposted by Emmanouil Benetos

arXiv Sound @arxiv-sound.bsky.social · 04/06/2025

**Lyrics Transcription:** Consistency loss aligns vocal and mixture encoder representations, improving transcription on music mixtures.

arxiv.org

Enhancing Lyrics Transcription on Music Mixtures with Consistency Loss

Jiawen Huang, Felipe Sousa, Emir Demirel, Emmanouil Benetos, Igor Gadelha

012

Reposted by Emmanouil Benetos

Christos Plachouras @cplachouras.bsky.social · 13/05/2025

Excited to share our new paper: arxiv.org/abs/2505.06224! We introduce a unified framework for evaluating model representations beyond downstream tasks, and use it to uncover some interesting insights about the structure of representations that challenge conventional wisdom 🔍🧵

153

Reposted by Emmanouil Benetos

Christos Plachouras @cplachouras.bsky.social · 10/04/2025

how much music data do we actually need to pretrain effective music representation learning models? we decided to systematically investigate this in our latest #ICASSP2025 paper with @emmanouilb.bsky.social and Johan Pauwels

172

Reposted by Emmanouil Benetos

QMUL School of Electronic Engineering and Computer Science @qmuleecs.bsky.social · 20/03/2025

Exciting research update! EECS PhD students have developed a novel approach that enables large language models (LLMs) to “hear” and “understand” sound - a breakthrough in multimodal generative #AI: www.qmul.ac.uk/eecs/news-an...

qmul.ac.uk

EECS PhD researcher pioneers AI that can

053

Reposted by Emmanouil Benetos

C4DM at QMUL @c4dm.bsky.social · 28/11/2024

Next Tuesday, 3/12 at 2pm, we will host a seminar by Manvi Agarwal on 'Fast Structure-informed Positional Encoding for Music Generation'. More info at: www.c4dm.eecs.qmul.ac.uk/news/2024-03...

081