ICASSP2024

4/14 (Sun) ~ 4/19 (Fri), 2024 At COEX in Seoul, Korea

• 

The 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024) is the IEEE Signal Processing Society’s flagship conference on signal processing and its applications. This 49th edition of ICASSP will be held in COEX, Seoul, Korea from April 14th to 19th 2024. ICASSP’s main theme this year will be “Signal Processing: The Foundation for True Intelligence,” acknowledging the fundamental contributions of signal processing to Intelligence and bridging the creative synergy between signal processing and Artificial Intelligence.

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

Sony Booth

Please visit the Sony booth and ask us anything.

Location: P1 @ Hall D2
Sony Booth Open Hours:
- Tuesday, April 16 | 10:00 AM – 6:00 PM (UTC+9)
- Wednesday, April 17 | 10:00 AM – 6:00 PM (UTC+9)
- Thursday, April 18 | 10:00 AM – 6:00 PM (UTC+9)
- Friday, April 19 | 10:00 AM – 4:00 PM (UTC+9)

Technology Presentations / Information Sessions

We will have technology presentations and information sessions.
* This schedule is subject to change (The latest schedule is always available at Sony Booth)

Technical Programs at ICASSP 2024

Poster Session

●AASP-P1: Audio events detection and classification; Music Information Retrieval 1

AASP-P1.11: Timbre-Trap: A Low-Resource Framework for Instrument-Agnostic Music Transcription

- Authors : Frank Cwitkowitz (University of Rochester); Kin-Wai Cheuk (Sony AI), Woosung Choi (Sony AI), Marco A. Martínez-Ramírez (Sony AI), Keisuke Toyama (Sony Group Corporation), Wei-Hsiang Liao (Sony AI), Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time : Tuesday, April 16 | 1:10 PM - 3:10 PM (UTC+9)
- Location : Poster Zone 1A

●AASP-P7: Dereverberation and RIR estimation 1; Speech enhancement and restoration

AASP-P7.8: VRDMG: Vocal Restoration via Diffusion Posterior Sampling with Multiple Guidance

- Authors : Carlos Hernandez-Olivan (University of Zaragoza), Koichi Saito (Sony AI), Naoki Murata (Sony AI), Chieh-Hsin Lai (Sony AI), Marco A. Martínez-Ramirez (Sony AI), Wei-Hsiang Liao (Sony AI), Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time : Wednesday, April 17 | 1:10 PM – 3:10 PM (UTC+9)
- Location : Poster Zone 2A

●AASP-P10: Anomaly detection; Sound event detection and localization

AASP-P10.10: Zero- and Few-shot Sound Event Localization and Detection

- Authors : Kazuki Shimada (Sony AI/Kyoto University), Kengo Uchida (Sony AI), Yuichiro Koyama (Sony Group Corporation), Takashi Shibuya (Sony AI), Shusuke Takahashi (Sony Group Corporation), Yuki Mitsufuji (Sony AI/Sony Group Corporation), Tatsuya Kawahara (Kyoto University)
- Date/Time : Wednesday, April 17 | 4:30 PM – 6:30 PM (UTC+9)
- Location : Poster Zone 6A

Lecture

●SS-L3: Generative Semantic Communication: How Generative Models Enhance Semantic Communications

SS-L3.1: Diffusion-Based Speech Enhancement with Joint Generative and Predictive Decoders

- Authors : Hao Shi (Kyoto University), Kazuki Shimada (Sony AI), Masato Hirano (Sony Group Corporation), Takashi Shibuya (Sony AI), Yuichiro Koyama (Sony Group Corporation), Zhi Zhong (Sony Group Corporation), Shusuke Takahashi (Sony Group Corporation), Tatsuya Kawahara (Kyoto University), Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time : Wednesday, April 17 | 8:20 AM – 8:40 AM (UTC+9)
- Location : Room 205B

SS-L3.2: Enhancing Semantic Communication with Deep Generative Models – An ICASSP Special Session Overview

- Authors : Eleonora Grassucci (Sapienza University of Rome), Yuki Mitsufuji (Sony Group Corporation), Ping Zhang (Beijing University of Posts and Telecommunications), Danilo Comminiello (Sapienza University of Rome)
- Date/Time : Wednesday, April 17 | 8:40 AM – 9:00 AM (UTC+9)
- Location : Room 205B

●SLP-L13: Text-based customization for speech-to-text

SLP-L13.3: Phoneme-aware Encoding for Prefix-tree-based Contextual ASR

- Authors : Hayato Futami (Sony Group Corporation), Emiru Tsunoo (Sony Group Corporation), Yosuke Kashiwagi (Sony Group Corporation), Hiroaki Ogawa (Sony Group Corporation), Siddhant Arora (CMU), Shinji Watanabe (CMU)
- Date/Time : Wednesday, April 17 | 1:50 PM - 2:10 PM (UTC+9)
- Location : Room 102

●SLP-L18: Text to Speech Generation -O2

SLP-L18.3: BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network

- Authors : Takashi Shibuya (Sony AI), Yuhta Takida (Sony AI), Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time : Thursday, April 18 | 9:00 AM - 9:20 AM (UTC+9)
- Location : Room 103

Workshop

●WS-3: Self-supervision in Audio, Speech and Beyond (SASB) / Workshop Website

SKILL: Similarity-aware Knowledge Distillation For Speech Self-supervised Learning

- Authors : Luca Zampierin (Sony Europe B.V., EPFL) , Ghouthi Boukli Hacene (Sony Europe B.V.) , Bac Nguyen (Sony Europe B.V.) , Mirco Ravanelli (MILA)
- Date/Time : Sunday, April 14 | 8:30 AM - 5:30 PM (UTC+9)
- Location : Room 104

Recruiting 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 to our career site, consider joining to ICASSP Student Job Fair and Luncheon and/or visiting the Sony Information Desk at Sony booth P1 at the ICASSP exhibition hall (Hall D2) to know more about Sony Group.

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

Student Job Fair and Luncheon (Corporate Information)
Thursday, April 18 | 11:40 AM - 1:40 PM (UTC+9)
Rooms E5-E6 | COEX Convention & Exhibition

* * * * *

Applications are currently open for the Sony Women in Technology Award with Nature which will honor three outstanding women who are advancing technology for a positive impact. Sony launched this program in partnership with Nature, known globally for advancing scientific discovery by providing recognition, support, and resources to researchers and research-based organizations worldwide. We invite eligible ICASSP2024 participants currently engaged in technology research to apply.

Three early to mid-career women researchers will receive a prize of $250,000 USD each. Learn more and submit your application by May 31 at
https://womenintechnology.sony.com/