If you're submitting to #ICASSP2025 and are wondering why your tables at the top of a column are too low, it's because the template adds a \vskip above the caption.
Easiest fix is to add \vspace{-6pt} just before the \caption to make it flush with the text.
You're welcome🤗

Excited to have been part of #ICASSP2025!

🎶 Our researchers shared work on modeling musical surprisal in audio, zero-shot stem retrieval for music production, and #Music2Latent2, a new audio compression method.

Thanks to all who joined!
www.sony.com/en/SonyInfo/...

#MusicTech #AudioResearch #AI

#ICASSP2025 was pretty fun! Lots of good conversations and connections. Jet lag totally killed my sleep for the whole week, but now I know you can survive on 15 hours of sleep over 5 days, and at least I'm still almost on Boston time🤗

Diagram of meta-training procedure for proposed environment-adaptive Meta-SELD

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, Yin Cao, Ming Wu, Qiuqiang Kong, Feiran Yang, P, Jun Yang
AAM
openresearch.surrey.ac.uk/esploro/outp...

Table showing DCASE Challenge statistics (2013-2023), and figure showing number of publications related to DCASE Challenge Tasks since 2010.

Talk at #ICASSP2025 this pm:
Apr 11: 2:30pm-2:45pm
A decade of DCASE: Achievements, practices, evaluations and future challenges
@annamariamesaros.bsky.social @rserizel.bsky.social Tuomas Virtanen, P
AASP-SS6-L7: 50 years of Audio and Acoustic Signal Processing
Preprint: arxiv.org/abs/2410.04951

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

Our paper at #ICASSP2025 today:
Yi Yuan et al: "Sound-VECaps: Improving Audio Generation With Visual Enhanced Captions"
Apr 10, 5:00pm-6:30 pm
AASP-P22: Audio Captioning, Retrieval, and Understanding I
Preprint/code/dataset/demos: yyua8222.github.io/Sound-VECaps...
// @peoplecentredai.bsky.social

Our pick of the week by @zhihangxie.bsky.social: "Bridging Speech and Text Foundation Models with ReShape Attention" by Takatomo Kano, @wanchichen.bsky.social, @shinjiw.bsky.social, et al. #ICASSP2025

ieeexplore.ieee.org/document/108...

#FoundationModel #SpeechProcessing

Vision Transformers for X-ray Diffraction Patterns Analysis Understanding materials properties depends largely on the ability to determine its components, and in particular its mineral phases. Powder X-ray diffraction (XRD) is a powerful tool for such purposes...

This morning I will present our #icassp2025 🇮🇳 paper "Vision Transformers for X-ray Diffraction Patterns Analysis", joint work with my former PhD student Titouan Simonnet (IDP & BRGM), Diarra Fall (IDP, Univ. Orléans) and Sylvain Grangeon (BRGM) doi.org/10.1109/ICAS...
Poster 1G at 8:30 am.

2025 IEEE ICASSP, April 6-11, Hyderabad, India

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, Haohe Liu, Mark D. Plumbley, Wenwu Wang
AASP-P4: Audio Source Separation I (Room: Poster 2B)
More at: audio-agi.github.io/FlowSep_demo/

Akshay Rangamani akshay rangamani homepage

I'm hiring one PhD student for my group at #NJIT Data science. If you're at #ICASSP2025 and are interested in understanding deep learning and applications to signal processing, hit me up (emails or DM).

More info at akshay-r.github.io (Please share to spread the word!)

#signalproc #DLTheory

Low Rank and Sparse Fourier Structure in Recurrent Networks Trained on Modular Addition Modular addition tasks serve as a useful test bed for observing empirical phenomena in deep learning, including the phenomenon of \emph{grokking}. Prior work has shown that one-layer transformer archi...

I'm in Hyd for #ICASSP2025! I'm presenting some recent work on understanding how RNN language models represent modular addition circuits (arxiv.org/abs/2503.22059)
🗓️ Wed, Apr 9th
🕑 8:30 AM - 10 AM IST
🎙️ MRG.02

Please hit me up at ICASSP to talk about the science of DL!

🔥Visit our talks and posters at #ICASSP2025! 👀

Music2Latent2: Audio Compression with Summary Embeddings and Autoregressive Decoding
M. Pasini, S. Lattner, G. Fazekas
Wednesday, April 9 ( pm): Deep generative models I

Google at ICASSP 2025

Google is a Diamond Patron at #ICASSP2025. Drop by the Google booth (B1) to talk w/ researchers, network w/ recruiters, and attend a demo or Q&A session. You can find the full schedule of our booth activities along with details of Google's participation at this site:

research.google/conferences-...

Will present our paper, "Investigating Training Objectives for Generative Speech Enhancement" at #ICASSP2025!
🗓 Wed, 5:00-6:30 PM (AASP-P12)
🔊 Discussing diffusion bridges (Schrödinger bridge) & connections to score-based models—let’s chat!

In India, Hyderabad for #ICASSP2025 this week, presenting this work! If you are also interested in the use of diffusion models for real-time sensory applications, happy to chat!

PROGRESS Workshop – 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing

I will join the PROGRESS Workshop at #ICASSP2025 on Monday as a panelist.

2025.ieeeicassp.org/progress-wor...

On my way to Hyderabad and #ICASSP2025. Looking forward to catching up with many friends! Sadly not as many as usual given that <50% of participants could get a visa 😅
I'm chairing 3 sessions (SLP-P3, AASP-P8, AASP-L6) and presenting 1 paper (in AASP-L3), good places to find me if you want to chat🤗

About to begin my journey to India!

Excited to be involved at this year's ICASSP as follows (see thread).

Hope to see you there, titans!

#ICASSP2025

ESP is heading to #ICASSP2025!

We'll be presenting our paper, Biodenoising, at the Bio Acoustic III poster session on 4/11 at 8:30am. Looking forward to sharing this work & connecting with teams in Hyderabad 🌟

Demo: earthspecies.github.io/biodenoising/

cc: Marius Miron & @mhagiwara.bsky.social

ADASP at ICASSP 2025: 12 papers & a keynote! We are excited to share that the ADASP group will be presenting 12 papers and 1 keynote at the International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2025) in Hyderabad on April...

The ADASP group of Telecom Paris will be presenting 12 papers & 1 keynote next week at #ICASSP2025 🇮🇳.

Unfortunately, due to a visa issue, I won’t attend #ICASSP2025 in person - but I’ll share my work here! 😀

Excited to share my first ICASSP paper: ‘Uncovering the Visual Contribution in Audio-Visual Speech Recognition’ 📄

🔗https://ieeexplore.ieee.org/abstract/document/10888423

[1/8] 🧵

Attending #ICASSP2025 next week at Hyderabad from April 7th. Ping me if you want to meet in person! 🤗

I'm presenting two papers ⬇️⬇️⬇️

Dear @interspeech.bsky.social, is it true that the author rebuttal period was moved forward to April 4-11? This is #ICASSP2025 week, please reconsider 🥺

@interspeech.bsky.social just changed its rebuttal period to April 4-11, which overlaps with #ICASSP.

Given the overlap in research communities, I believe many researchers who submitted to #Interspeech2025 will also be attending #ICASSP2025. Could it be at least a week later?

Biodenoising—A Novel Method for Noise Reduction In Animal Vocalizations - Earth Species Project Biodenoising, a novel method for animal vocalization denoising that does not require access to clean data, was recently accepted to ICASSP 2025. Read more about it and start using it today.

One of our latest papers, Biodenoising, has been accepted to #ICASSP2025!

Biodenoising is our newest method to tackle one of ethology & bioacoustics' biggest data analysis challenges – background noise! 🧵👇🏻

www.earthspecies.org/blog/biodeno...

#ICASSP2025 registration is now open!!
2025.ieeeicassp.org/registration/
(10 seconds later)
Wait, I spoke too fast 🤣🤣🤣🤣🤣

📣 📣 TWO challenges at the Generative Data Augmentation (GenDA) workshop at ICASSP 2025! 📣 📣
#ICASSP2025

NeuroIncept Decoder for High-Fidelity Speech Reconstruction from Neural Activity This paper introduces a novel algorithm designed for speech synthesis from neural activity recordings obtained using invasive electroencephalography (EEG) techniques. The proposed system offers a prom...

🎉 Exciting news! 🎉

Our paper, "NeuroIncept Decoder for High-Fidelity Speech Reconstruction from Neural Activity", has been accepted at ICASSP 2025! 🌟

We’ll present this work in Hyderabad, India, April 6-11. Check out the preprint: arxiv.org/abs/2501.03757

#ICASSP2025 #AI #SignalProcessing

Single-stage TTS with Masked Audio Token Modeling and Semantic Knowledge Distillation Audio token modeling has become a powerful framework for speech synthesis, with two-stage approaches employing semantic tokens remaining prevalent. In this paper, we aim to simplify this process by in...

Wishing everyone a Happy New Year! Stay tuned for this work to be presented at #ICASSP2025.

arxiv.org/abs/2409.11003