Sound Papers

New Sound papers from computing with sound, sound as an information channel. Thank you to arXiv for use of its open access interoperability.

[Sound Papers @SoundPapers]

The Moving Drone: Negotiating Agency Between the Voice and the Virtual

Nithya Shikarpur, Victor Arul, Anna Huang
https://t.co/zCx7nLpise [𝚌𝚜.𝚂𝙳]
💬Published in NIME music track 2026

[Sound Papers @SoundPapers]

Generative Modeling of Bach-Style Symbolic Music: A Comparative Study of Autoregressive, Latent-Variable, and Adversarial Approaches

Kyuil Lee, Dezhi Yu, Yongkang Huang
https://t.co/tnFpUaSixv [𝚌𝚜.𝚂𝙳 𝚌𝚜.𝙻𝙶]

[Sound Papers @SoundPapers]

Towards Personalized Federated Learning for Dysarthric Speech Recognition

Tao Zhong, Mengzhe Geng, Jiajun Deng, Shujie Hu, Xunying Liu
https://t.co/3WwXJS3KVo [𝚌𝚜.𝚂𝙳 𝚌𝚜.𝙰𝙸]

[Sound Papers @SoundPapers]

Emo-LiPO: Listwise Preference Optimization for Fine-Grained Emotion Intensity Control in LLM-based Text-to-Speech

Yihang Lin, Li Zhou, Congwei Cao, Dongchu Xie, Xiaoxue Gao, Chen Zhang, Haizhou Li
https://t.co/wkagyDImW6 [𝚌𝚜.𝚂𝙳]
💬Accepted by IJCAI 2026

[Sound Papers @SoundPapers]

Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment

Xiang Li, Yixuan Zhou, Jingran Xie, Zhiyong Wu, Hui Wang
https://t.co/lZOudeMe5f [𝚌𝚜.𝚂𝙳 𝚌𝚜.𝙻𝙶]
💬Accepted to ICML 2026, demo website available at https://t.co/CMN5twNQru

[Sound Papers @SoundPapers]

BASENet: Band-Adapted Speech Enhancement Network with Cross-Band Attention

Damien Martins Gomes, François Capman
https://t.co/xXLO5lFO8l [𝚌𝚜.𝚂𝙳 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]

[Sound Papers @SoundPapers]

AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation

Zeyue Tian, Lei Ke, Zhaoyang Liu, Ruibin Yuan, Liumeng Xue, Yujiu Yang, Weijia Chen, Xu Tan, Qifeng Chen, Wei Xue, Yike Guo
https://t.co/k7lJpI6vnj [𝚌𝚜.𝚂𝙳 𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙼𝙼]

[Sound Papers @SoundPapers]

Missing-Token Prompted Reliability-Aware Fusion for Robust Polyglot Speaker Identification

Peng Jia, Li Dai, Jia Li, Zhenzhen Hu, Ye Zhao, Richang Hong
https://t.co/EqWLX6qwAZ [𝚌𝚜.𝚂𝙳]

[Sound Papers @SoundPapers]

Fast-SDE: Efficient Single-Microphone Sound Source Distance Estimation in Reverberant Environments

Jiang Wang, Runwu Shi, …
https://t.co/FWmCwihYea [𝚌𝚜.𝚂𝙳 𝚌𝚜.𝚁𝙾]
💬To appear in the 35th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)

[Sound Papers @SoundPapers]

PianoKontext: Expressive Performance Rendering from Deadpan Context

Dmitrii Gavrilev
https://t.co/aakWE2cEVH [𝚌𝚜.𝚂𝙳 𝚌𝚜.𝙻𝙶]

[Sound Papers @SoundPapers]

Lung-SRAD: Spectral-Aware Regularized Audio DASS with Dual-Axis Patch-Mix Contrastive Learning for Respiratory Sound Classification

Hemansh Shridhar, Miika Toikkanen, June-Woo Kim
https://t.co/hnAsInRjWM [𝚌𝚜.𝚂𝙳 𝚌𝚜.𝙰𝙸]
💬Accepted to Interspeech 2026

[Sound Papers @SoundPapers]

Quality Adaptive Angular Margin Learning for Respiratory Sound Classification

Yoon Tae Kim, Heejoon Koo, Miika Toikkanen, June-Woo Kim
https://t.co/DxroLQb0Bw [𝚌𝚜.𝚂𝙳 𝚌𝚜.𝙰𝙸]
💬Accepted to Interspeech 2026

[Sound Papers @SoundPapers]

Snapping Matters: Context-Aware Onset Refinement for Automatic Music Transcription

Abhirup Saha, Hans-Ulrich Berendes, Meinard Müller, Ben Maman
https://t.co/hl9pe2JmgF [𝚌𝚜.𝚂𝙳]

[Sound Papers @SoundPapers]

Real-Time Language Model Jamming: A Case Study for Live Music Accompaniment Generation

Bowen Zheng, Andrew H. Yang, Jiaqi Ruan, Jia He, Xinyue Li, Yuan-Hsin Chen, Ziyu Wang, Xiaosong Ma
https://t.co/SxF5nhyS2k [𝚌𝚜.𝚂𝙳 𝚌𝚜.𝙾𝚂]
💬Accepted to RTAS 2026

[Sound Papers @SoundPapers]

Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clustering

Haoning Xu, Zhaoqing Li, Huimeng Wang, Youjun Chen, Chengxi Deng, Mengzhe Geng, …
https://t.co/9dG2jRyjx3 [𝚌𝚜.𝚂𝙳 𝚌𝚜.𝙰𝙸 𝚎𝚎𝚜𝚜.𝙰𝚂]
💬Accepted by Interspeech 2026

[Sound Papers @SoundPapers]

Feature-Aligned Speech Watermarking for Robustness to Reconstruction Distortions

Haiyun Li, Shuhai Peng, Zhisheng Zhang, Jingran Xie, Xiaofeng Xie, Hanyang Peng, Zhiyong Wu
https://t.co/Wpg457vHay [𝚌𝚜.𝚂𝙳 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙼𝙼]
💬Accepted by ICME2026

[Sound Papers @SoundPapers]

SpAArSIST: Sparsified AASIST for Efficient and Reliable Anti-Spoofing

Anton Firc, Vojtěch Staněk, Zbyněk Lička, Kamil Malinka, Martin Perešíni
https://t.co/mjsnPcRCbB [𝚌𝚜.𝚂𝙳 𝚌𝚜.𝙻𝙶]
💬Accepted at Interspeech 2026

[Sound Papers @SoundPapers]

The Hidden Cost of Pairwise Verification in Synthetic Speech Source Tracing

Anton Firc, Zbyněk Lička, Vojtěch Staněk, Kamil Malinka
https://t.co/AyLVjEGbZM [𝚌𝚜.𝚂𝙳]
💬Accepted at Interspeech 2026

[Sound Papers @SoundPapers]

CS-YODAS: A Mined Dataset of In-the-Wild Code-Switched Speech

Brian Yan, Qingzheng Wang, Matthew Wiesner, Anuj Diwan, Olga Iakovenko, Alexander Polok, Injy Hamed, Shuichiro Shimizu, Iris Emerman Thomas Hain, David R. Mortensen, …
https://t.co/b2RJWFqcoe [𝚌𝚜.𝚂𝙳]

[Sound Papers @SoundPapers]

Steering Where to Listen: Instruction-Based Activation Steering Redirects Temporal Attention in Large Audio-Language Models

Tsung-En Lin, Hung-Yi Lee
https://t.co/XzmgcfoIIO [𝚌𝚜.𝚂𝙳 𝚌𝚜.𝙰𝙸 𝚎𝚎𝚜𝚜.𝙰𝚂]