ICASSP 2026

5/4 (Mon) ～ 5/8 (Fri), 2026 at Centre de Convencions Internacional de Barcelona (CCIB), Balcerona, Spain

2026 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2026) is the world’s largest and most comprehensive technical conference focused on signal processing and its applications. It offers a comprehensive technical program presenting all the latest development in research and technology in the industry that attracts thousands of professionals annually.

Sony is proud to be Platinum sponsor of ICASSP 2026. We look forward to this year's exciting exhibition opportunities, featuring a variety of ways to connect with participants in person. Sony will exhibit and participate.

Contents: Sony's Technical Programs at ICASSP 2026; Exhibition Booth; Follow us on LinkedIn!; Sony Women in Technology Award with Nature; Career Information

Sony's Technical Programs at ICASSP 2026

Oral

[AASP-L8: Music Signal Processing, Production, and Separation]
Automatic Music Mixing Using a Generative Model of Effect Embeddings

- Authors: Eloi Moliner, Marco A. Martínez Ramírez (Sony AI), Junghyun Koo (Sony AI), Wei-Hsiang Liao (Sony AI), Kin Wai Cheuk (Sony AI), Joan Serrà (Sony AI), Vesa Välimäki, Yuki Mitsufuji (Sony AI)
- Date/Time: May 7th (Thu) 16:30 - 16:50 (CEST)
- Place: Room 127+128

< Link >
- [Oral] https://www.cmsworkshops.com/ICASSP2026/PaperNum=16357
- [Paper] https://arxiv.org/abs/2511.08040

[AASP-L8: Music Signal Processing, Production, and Separation]
Automatic Music Sample Identification with Multi-Track Contrastive Learning

- Authors: Alain Riou (Sony AI), Joan Serrà (Sony AI), Yuki Mitsufuji (Sony AI)
- Date/Time: May 7th (Thu) 16:50 - 17:10 (CEST)
- Place: Room 127+128

< Link >
- [Oral] https://www.cmsworkshops.com/ICASSP2026/PaperNum=14887
- [Paper] https://arxiv.org/abs/2510.11507

[AASP-L5: Audio Understanding and Generation]
FoleyBench: A Benchmark For Video-to-Audio Models

- Authors: Satvik Dixit, Koichi Saito (Sony AI), Zhi Zhong (Sony Group Corporation), Yuki Mitsufuji (Sony AI), Chris Donahue
- Date/Time: May 6th (Wed), 17:30 - 17:50 (CEST)
- Place: Room 127+128

< Link >
- [Oral] https://www.cmsworkshops.com/ICASSP2026/PaperNum=17851
- [Paper] https://arxiv.org/abs/2511.13219

[AASP-L10: Music Content Analysis]
Noise-to-Notes: Diffusion-Based Generation and Refinement for Automatic Drum Transcription

- Authors: Michael Yeung (Sony Group Corporation), Keisuke Toyama (Sony Group Corporation), Toya Teramoto (Sony Group Corporation), Shusuke Takahashi (Sony Group Corporation), Tamaki Kojima (Sony Group Corporation)
- Date/Time: May 8th (Fri), 09:40 - 10:00 (CEST)
- Place: Room 127+128

< Link >
- [Oral] https://www.cmsworkshops.com/ICASSP2026/PaperNum=10215
- [Paper] https://arxiv.org/abs/2509.21739

[AASP-L3: Neural Speech and Audio Coding]
S-PRESSO: Ultra Low Bitrate Sound Effect Compression With Diffusion Autoencoders And Offline Quantization

- Authors: Zineb Lahrichi (Sony AI), Gaëtan Hadjeres (Sony AI), Gaël Richard, Geoffroy Peeters
- Date/Time: May 6th (Wed), 09:00 - 09:20
- Place: Room 127+128

< Link >
- [Oral] https://www.cmsworkshops.com/ICASSP2026/PaperNum=150808
- [Paper] https://arxiv.org/abs/2602.15082

Posters

[TH1.PA-25: Audio and Speech Quality and Intelligibility Measures III]
Can Hierarchical Cross-Modal Fusion Predict Human Perception of AI Dubbed Content?

- Authors: Ashwini Dasare (Sony Research India), Nirmesh Shah (Sony Research India), Ashishkumar Gudmalwar (Sony Research India), Pankaj Wasnik (Sony Research India)
- Date/Time: May 7th (Thu), 09:00 - 11:00 (CEST)
- Place: Poster Area 25

< Link >
- [Poster] https://www.cmsworkshops.com/ICASSP2026/PaperNum=16934
- [Paper] https://arxiv.org/abs/2603.28717

[TH2.PA-25: Sound Generation and Synthesis]
FlashFoley: Fast Interactive Sketch2Audio Generation

- Authors: Zachary Novack, Koichi Saito (Sony AI), Zhi Zhong (Sony Group Corporation), Takashi Shibuya (Sony AI), Shuyang Cui (Sony Group Corporation), Julian McAuley, Taylor Berg-Kirkpatrick, Christian Simon (Sony Group Corporation), Shusuke Takahashi (Sony Group Corporation), Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time: May 7th (Thu), 14:00 - 16:00 (CEST)
- Place: Poster Area 25

< Link >
- [Poster] https://www.cmsworkshops.com/ICASSP2026/PaperNum=14368/a>
- [Paper] https://openreview.net/pdf?id=dxwsVO0W47

[AASP-P23: Music Analysis II]
Leveraging Whisper Embeddings for Audio-based Lyrics Matching

- Authors: Eleonora Mancini, Joan Serrà (Sony AI), Paolo Torroni, Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time: May 7th (Thu), 16:30 - 18:30 (CEST)
- Place: Poster Area 25

< Link >
- [Poster] https://www.cmsworkshops.com/ICASSP2026/PaperNum=13868
- [Paper] https://arxiv.org/abs/2510.08176

[MMSP-P2: Temporal Modeling and Video Synthesis]
SAVGBench: Benchmarking Spatially Aligned Audio-Video Generation

- Authors: Kazuki Shimada (Sony AI), Christian Simon (Sony Group Corporation), Takashi Shibuya (Sony AI), Shusuke Takahashi (Sony Group Corporation), Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time: May 5th (Tue), 14:00 - 16:00 (CEST)
- Place: Poster Area 21

< Link >
- [Poster] https://www.cmsworkshops.com/ICASSP2026/PaperNum=10607
- [Paper] https://arxiv.org/abs/2412.13462

[GC-P10: Inaugural Music Source Restoration (MSR)]
Summary of The Inaugural Music Source Restoration Challenge

- Authors: Yongyi Zang, Jiarui Hai, Wanying Ge, Qiuqiang Kong, Zheqi Dai, Helin Wang, Yuki Mitsufuji (Sony AI), Mark Plumbley
- Date/Time: May 7th (Thu), 16:30 - 18:30 (CEST)
- Place: Poster Area 43

< Link >
- [Poster] https://www.cmsworkshops.com/ICASSP2026/PaperNum=19113
- [Paper] https://arxiv.org/abs/2601.04343

[AASP-P5: Music Separation and Transcription]
Towards Blind Data Cleaning: A Case Study in Music Source Separation,

- Authors: Azalea (Yijie) Gui (Sony AI/University of Toronto), Woosung Choi (Sony AI), Junghyun Koo (Sony AI), Kazuki Shimada (Sony AI), Takashi Shibuya (Sony AI), Joan Serrà (Sony AI), Wei-Hsiang Liao (Sony AI), Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time: May 5th (Tue), 14:00 - 16:00 (CEST)
- Place: Poster Area 27

< Link >
- [Poster] https://www.cmsworkshops.com/ICASSP2026/PaperNum=11809
- [Paper] https://arxiv.org/abs/2510.15409

[SLP-P31: Self-supervised and Unsupervised Domain Adaptation for ASR]
Windowed SummaryMixing: An Efficient Fine-Tuning of Self-Supervised Learning Models for Low-Resource Speech Recognition

- Authors: Aditya Srinivas Menon (Sony Research India), Kumud Tripathi (Sony Research India), Raj Gohil (Sony Research India), Pankaj Wasnik (Sony Research India)
- Date/Time: May 7th (Thu), 09:00 - 11:00 (CEST)
- Place: Poster Area 27

< Link >
- [Poster] https://www.cmsworkshops.com/ICASSP2026/PaperNum=12306
- [Paper] https://arxiv.org/abs/2602.09043

[AASP-P10: Music Generation II]
Break-the-Beat! Controllable MIDI-to-Drum Audio Synthesis

- Authors: Shuyang Cui (Sony Group Corporation), Zhi Zhong (Sony Group Corporation), Qiyu Wu (Sony Group Corporation), Zachary Novack (Sony Group Corporation), Woosung Choi (Sony AI), Keisuke Toyama (Sony Group Corporation), Kin Wai Cheuk (Sony AI), Junghyun Koo (Sony AI), Yukara Ikemiya (Sony AI), Christian Simon (Sony Group Corporation), Chihiro Nagashima (Sony Group Corporation), Shusuke Takahashi (Sony Group Corporation)
- Date/Time: May 6th (Wed), 14:00 - 16:00
- Place: Poster Area 25

< Link >
- [Poster] https://www.cmsworkshops.com/ICASSP2026/PaperNum=17036
- [Paper] https://ai.sony/blog/Advancing-AI-Highlights-from-March-2026

[AASP-P14: Music Analysis I]
Do Foundational Audio Encoders Understand Music Structure?

- Authors: Keisuke Toyama (Sony Group Corporation), Zhi Zhong (Sony Group Corporation), Akira Takahashi (Sony Group Corporation), Shusuke Takahashi (Sony Group Corporation), Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time: May 6th (Wed), 16:30 - 18:30 (CEST)
- Place: Poster Area 26

< Link >
- [Poster] https://www.cmsworkshops.com/ICASSP2026/PaperNum=10100
- [Paper] https://arxiv.org/abs/2512.17209

[AASP-P22: Audio and Speech Source Separation and Signal Enhancement II]
MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation

- Authors: Akira Takahashi (Sony Group Corporation), Shusuke Takahashi (Sony Group Corporation), Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time: May 7th (Thu), 16:30 - 18:30 (CEST)
- Place: Poster Area 24

< Link >
- [Poster] https://www.cmsworkshops.com/ICASSP2026/PaperNum=12520
- [Paper] https://arxiv.org/abs/2510.09065

[SLP-P23: Discrete Representations for ASR, Tokenization, and Segmentation]
Phonological Tokenizer: Prosody-Aware Phonetic Token via Multi-Objective Fine-Tuning with Differentiable K-Means

- Authors: Kentaro Onda (The University of Tokyo / Sony Group Corporation), Hayato Futami (Sony Group Corporation), Yosuke Kashiwagi (Sony Group Corporation), Emiru Tsunoo (Sony Group Corporation), Shinji Watanabe
- Date/Time: May 6th (Wed), 14:00 - 16:00
- Place: Poster Area 31

< Link >
- [Poster] https://www.cmsworkshops.com/ICASSP2026/PaperNum=16033
- [Paper] https://arxiv.org/abs/2601.19781

[AASP-P3: Music Generation I]
Diffusion Timbre Transfer Via Mutual Information Guided Inpainting

- Authors: Ching Ho Lee, Javier Nistal (Sony Computer Science Laboratories), Stefan Lattner (Sony Computer Science Laboratories), Marco Pasini, George Fazekas
- Date/Time: May 5th (Tue), 16:30 - 18:30 (CEST)
- Place: Poster Area 26

< Link >
- [Poster] https://www.cmsworkshops.com/ICASSP2026/PaperNum=14117
- [Paper] https://arxiv.org/abs/2601.01294

[AASP-P23: Music Analysis II]
VioPTT: Violin Technique-Aware Transcription from Synthetic Data Augmentation

- Authors: Ting-Kang Wang, Yueh-Po Peng, Li Su, Vincent K.M. Cheung (Sony Computer Science Laboratories, Inc.)
- Date/Time: May 7th (Thu), 16:30 - 18:30 (CEST)
- Place: Poster Area 25

< Link >
- [Poster] https://www.cmsworkshops.com/ICASSP2026/PaperNum=14491
- [Paper] https://arxiv.org/abs/2509.23759

[SPCOM-P1: Journal Presentations]
Deployment Strategy for Indoor Distributed MIMO System

- Authors: Yujie Zhang (Sony TDL Lund/Lund University), Juan Vidal Alegria, Jose Flordelis (Sony Europe/TDL-Lund), Erik Bengtsson (Sony Europe/TDL-Lund), Ove Edfors
- Date/Time: May 5th, 14:00 - 16:00 (CEST)
- Place: Poster Area 3

< Link >
- [Poster] https://www.cmsworkshops.com/ICASSP2026/PaperNum=19174
- [Paper] https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11355794

[IVMSP-P49: Diffusion models for Image Processing]
AHAI: Adaptive Hybrid-Attention Inference for Diffusion-Based Arbitrary Style Transfer

- Authors: Ting Yang, Zhenyuan Gao, Xiyao Liu, Songtao Wu (Sony China), Meiguang Zheng, Da Huang, Hui Fang
- Date/Time: May 8th (Fri), 14:00 - 16:00 (CEST)
- Place: Poster Area 16

< Link >
- [Poster] https://www.cmsworkshops.com/ICASSP2026/PaperNum=12581
- [Paper] https://repository.lboro.ac.uk/articles/

Workshop

Keynote Speech - Industry Track
WS-P5: Speech, Music and Mind 2026 (SMM26)

- Date/Time: May 4th (Mon) 09:00 - 18:00
- Place: Room 121
- Speaker: Yuki Mitsufuji (Sony AI/Sony Group Corporation)

Exhibition Booth
Open Hours

Visit our booth at the exhibition to explore our latest technology firsthand and engage with our team.

Location: P1
Sony Booth Open Hours:
- May 5th (Tue) 09:00 – 17:00 (CEST)
- May 6th (Wed) 09:00 – 17:00 (CEST)
- May 7th (Thu) 09:00 – 17:00 (CEST)
- May 8th (Fri) 09:00 – 17:00 (CEST)

Follow us on LinkedIn!

Sony Technology - https://www.linkedin.com/company/sony_technology/

Sony Women in Technology Award with Nature

The Sony Women in Technology Award with Nature recognizes exceptional early to mid-career researchers who are advancing technology. We invite eligible ICASSP attendees working in academia, for a research institution, or a university spinout to apply. Three winners will receive:

- US $250,000 to advance their research endeavors
- Global visibility through Nature Portfolio’s platforms
- Networking opportunities with distinguished technologists and visionary researchers

The application deadline is rapidly approaching!
Learn more and apply by Friday, June 5th, 2026: https://womenintechnology.sony.com/

Career Information

We look forward to working with highly motivated individuals to fill the world with emotion and to pioneer future innovation through dreams and curiosity. If interested, please access our career site and/or consider visiting the Sony booth (Booth#: P1) at the ICASSP exhibition area to know more about Sony Group.

Career Site Link: https://www.sony.com/en/SonyInfo/Careers/

Sony Group Technology Portal

You can explore our technology by clicking HERE.

Back to Academic Conferences

Technology