Workshop on Dec 20, 2023: 

Symposium for Celebrating 40 Years of Bayesian Learning in Speech and Language Processing and Beyond

Honorary Committee Chair

Chin-Hui Lee

 

Organizers

Jinyu Li, Chao-Han Huck Yang, Chao Zhang, Hsin-Min Wang, Yu Tsao

 

Invited Speakers

Qiang Huo, Torbjorn Svendsen, Shinji Watanabe, Koichi Shinoda, Jen-Tzung Chien, Sabato Marco Siniscalch

 

Call for Papers and Extended Abstract

We welcome all submissions related to bayesian learning, large language and speech models and generative models, including but not limited to:

• Methods for Bayesian learning and Maximum a Posteriori (MAP) estimation based methods.
• Preliminary evaluation on In-Context learning for Generative Models
• Accent and Multilingual Speech and Language processing
• Large speech and large models and theory
• Multimodal learning: Vision, Speech, and Language Processing
• Multivariate Gaussian Mixture Models
• Test-time Adaptation and Few-Shot Learning

 

Paper Awards

One outstanding paper award and one student paper award will be given based on the novelty and technique depth.

 

Dual-submission policy

We welcome ongoing and unpublished work. We also welcome papers that are under review at the time of submission, or that have been recently accepted.

 

Submissions and accepted papers

Workshop submissions and reviews will be private. The camera-ready version of accepted papers will be shared on the workshop webpage. However, the hosting is not an official proceeding, so the papers can be subsequently / concurrently submitted to other venues.

 

In person presentation

Accepted extended abstracts and papers are expected to be presented in person for best paper award evaluation. Online Presentation is exceptional based on visa difficulties.

 

Submission Site:

https://cmt3.research.microsoft.com/BLSLP2023

 

Latex Template:

https://www.overleaf.com/latex/templates/ieee-asru-23-bayesian-latex-template/npvwtgswdwkt

 

Submission SiteSatelliteEvent Website Home Page: 

https://bayesian40.github.io/

 

Submission Deadline

Oct 4th (WED) AOE Time

 

Workshop on Dec 16, 2023:

Workshop on Speech Foundation Models and their Performance Benchmarks(SPARKS1)

 

Location and Date

2023.12.16 at MK Innovation Hall (學新館), National Taiwan University (NTU).

 

Organizer

Hung-yi Lee (National Taiwan University), Shinji Watanabe (Carnegie Mellon University), David Harwath (UTAustin), Shang-Wen (Daniel) Li (Facebook AI), Karen Livescu (TTI-Chicago), Suwon Shon (ASAPP), Leibny Paola Garcia (Johns Hopkins University), Shu-wen Yang (National Taiwan University), Jiatong Shi (National Taiwan University), Chien-yu Huang (National Taiwan University)

 

Paper Submission

The workshop will concentrate on soliciting papers using the benchmarks above, but submissions addressing the broader themes of speech foundation models technology are also allowed. We particularly encourage the submission of papers originally intended for the ML-SUPERB challenge but not accepted for ASRU 2023. We also invite papers that either propose a new benchmark for the evaluation of speech foundation models or critique the current benchmarks. The format for papers should conform to that of ASRU 2023. The paper format is the same as ASRU 2023.

 

Paper Submission Deadline

October 6th, 2023

 

Paper Acceptance Notification

October 27th, 2023.

 

Website

https://sites.google.com/g.ntu.edu.tw/sparks