Welcome to ICASSP 2020

45th International Conference on Acoustics, Speech, and Signal Processing

On behalf of the IEEE Signal Processing Society, the organizing committee is delighted to invite you to the 45th International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, to be held fully virtually, between May 4 and May 8, 2020! ICASSP is the world’s largest and most comprehensive technical conference focused on signal processing and its applications. The 2020 conference will feature world-class presentations by internationally renowned speakers, cutting-edge session topics and provide a fantastic opportunity to network with like-minded professionals from around the world.
We are excited for the opportunity to innovate by creating an engaging virtual conference that will be rewarding for both presenters and attendees. Immediate guidance for authors, with full details will be announced soon. So far, please follow the instructions in the message on Covid-19 in this webpage.

Reminder: IEEE Event Privacy & Code of Conduct

When attending the live sessions, you may be prompted by Zoom to re-enter your name and email address. Please ensure you are inserting accurate information that matches your event registration or you could be breaching the IEEE code of conduct and will preventively be removed from the session.

Additionally, all participants agree to the IEEE Event Code of Conduct. All participants have the right to pursue shared interests without harassment or discrimination in an environment that supports diversity and inclusion. Participants are expected to adhere to these principles and respect the rights of others. Click here to view the full IEEE Event Terms & Conditions.

Registration

Registration is closed!

Plenary Speakers

Yonina Eldar

Yonina Eldar

From compressed sensing to deep learning: tasks, structures, and models

The famous Shannon-Nyquist theorem has become a landmark in the development of digital signal and image processing. However, in many modern applications, the signal bandwidths have increased tremendously, while the acquisition capabilities have not scaled sufficiently fast. Consequently, conversion to digital has become a serious bottleneck. In this talk, we present a framework for sampling and processing a large class of wideband analog signals at rates far below Nyquist in space, time and frequency, which allows to dramatically reduce the number of antennas, sampling rates and band occupancy.

Yoshua Bengio

Yoshua Bengio

Deep Representation Learning

A crucial ingredient of deep learning is that of learning representations, more specifically with the objective to discover higher-level representations which capture and disentangle explanatory factors. This is a very ambitious goal and current state-of-the-art techniques still fall short, often capturing mostly superficial features of the data, which leaves them vulnerable to adversarial attacks and insufficient out-of-distribution robustness. This talk will review these original objectives, supervised and unsupervised approaches, and outline research ideas towards better representation learning.

Georgios Giannakis

Georgios Giannakis

Gauss-Fourier-Wiener-Kalman Ensembles for Adaptivity and Robustness

Inference of functions from data is ubiquitous in Signal Processing and Statistical Learning. This talk deals with Gaussian process (GP) based approaches that not only learn over a class of nonlinear functions, but also quantify the associated uncertainty. To cope with the curse of dimensionality, random feature Fourier (RF) vectors lead to parametric GP-RF function models, that offer scalable forms of Wiener’s minimum mean-square error approach. The talk will next touch upon deep GP architectures, and further focus on ensembles (E) of GP-RF learners, each with a distinct kernel belonging to a prescribed dictionary, and jointly learning a much richer class of functions. Whether in batch or online forms, EGPs remain robust to dynamics captured by adaptive Kalman filters. Their performance will be benchmarked using regret analysis. Broader applicability will be also demonstrated for policy evaluation in reinforcement learning. Case studies will highlight the merits of EGPs, and pay tribute to the ensemble of SP giants, namely Gauss, Fourier, Wiener, and Kalman.

Björn Ottersten

Björn Ottersten

Multiantenna Precoding in Wireless Communication Systems

The advent of spatial processing in multiantenna wireless communications has transformed the design of mobile networks allowing us to meet the tremendous demands for data and services in mobile applications. Signal processing techniques implemented in base-band transceivers enables the efficient exploitation of radio spectrum, increased gain to improve coverage, more reliable and secure transmissions and improved energy efficiency. We will focus on the challenges of spatial precoding techniques implemented on the transmit side of wireless systems. Early developments on transmit beamforming and spatial division multiple access will be reviewed as well as space-time coding and more recent developments on symbol-level precoding.

Mari Ostendorf

Mari Ostendorf

Conversational Systems and the Marriage of Speech and Language

Dramatic advances in language processing, speech recognition and synthesis technology have opened up a range of applications that involve understanding speech. This talk describes the challenges, methods and opportunities for integrating speech and language technology with an emphasis on conversational speech, the next frontier for speech systems. Conveniently, both speech and language processing now leverage neural representations, including similar algorithms. However, conversational speech is quite different from the written text that underlies most language technology. It lacks punctuation and is often disfluent. Handling these issues, and recognizing speaker intent and sentiment, requires attending to the intonation and timing of words and phrases, which links speech to conversational understanding.

Patrons

Diamond Patron

Platinum Patron

Silver Patron

Bronze Patron

Exhibitors

Other Sponsorships

About ICASSP

ICASSP is the world’s largest and most comprehensive technical conference focused on signal processing and its applications. The 2020 conference will feature world-class presentations by internationally renowned speakers, cutting-edge session topics and provide a fantastic opportunity to network with like-minded professionals from around the world.

ICASSP 2020 is going to have over 8000 participants which make this year’s event the largest ever ICASSP conference over the past 45 years. This will provide a great opportunity and arena for industry participation and exhibition. During this conference, you will visit the world largest international companies and publishers who will also sponsor a number of prestigious awards.

News

Keep in touch with latest news!

Author Video Instructions

We uploaded the instructions for video recording of your presentation. Please, follow the instructions described in the Author Video Instructions page. More info here.

2020 IEEE Awards

We are so honoured to announce the 2020 IEEE Awards: 2020 IEEE JAMES L. FLANAGAN SPEECH AND AUDIO PROCESSING AWARD to HYNEK HERMANSKY, for contributions to speech processing and feature extraction for robust speech recognition. Read more…

Industry Program Available

We have released the industry program. You will find speakers, panels, special sessions and speaker sessions. More information at Industry Program.

More news...

Update: COVID-19 Notices

Our thoughts are with those affected by the COVID-19 outbreak. We have prepared an engaging innovative and safe ICASSP. The health and safety of our members and participants are our first priority.

Please, download the latest update from the following link.

Read Update

Follow us in social media

Twitter
Facebook

Send us an e-mail

You can drop an e-mail to

icassp2020info@cttc.es

Contact Us