Date: 6 August 2024
Time: 1:00 PM ET (New York Time)
Presenter(s): Dr. Shinji Watanabe, Dr. Abdelrahman Mohamed
Dr. Karen Livescu, Dr. Hung-yi Lee, Dr. Tara Sainath,
Dr. Katrin Kirchhoff & Dr. Shang-Wen Li
MMSP Reviewer Interest Form
Interested in becoming a MMSP TC Reviewer of papers?
Please fill out the form below and click the submit button.You will be contacted by a Technical Committee member!
(Scroll down till the end of the form to complete it.)
Applications are invited for postdoctoral researcher positions in the general area of optimization and learning of network systems. Competitive financial supports will be provided.
Candidates with a clear interest in the general area of network systems are encouraged to apply.
Specific areas of research include:
Inspired by the capabilities of transformer models, we introduce a novel method named Multivariate Time-Series Imputation with Transformers (MTSIT). This entails an unsupervised autoencoder model featuring a transformer encoder, leveraging unlabeled observed data for simultaneous reconstruction and imputation of multivariate time-series.
Supported by the SPS Challenge Program.
This challenge addresses the global problem of hearing loss, which will affect 1 in 10 people by 2050. Hearing loss can create many issues with music: quieter passages being inaudible; poor and anomalous pitch perception; and difficulties identifying and picking out instruments and lyrics.