Error message

  • Deprecated function: Required parameter $context follows optional parameter $feed_nid in include_once() (line 1389 of /home/aggregate/public_html/includes/bootstrap.inc).
  • Deprecated function: Required parameter $options follows optional parameter $data in require_once() (line 341 of /home/aggregate/public_html/includes/module.inc).
  • Deprecated function: Required parameter $name follows optional parameter $data in require_once() (line 341 of /home/aggregate/public_html/includes/module.inc).
  • Deprecated function: Required parameter $options follows optional parameter $data in require_once() (line 341 of /home/aggregate/public_html/includes/module.inc).
  • Deprecated function: Required parameter $name follows optional parameter $data in require_once() (line 341 of /home/aggregate/public_html/includes/module.inc).
  • Deprecated function: Required parameter $entity_type follows optional parameter $file in require_once() (line 341 of /home/aggregate/public_html/includes/module.inc).
  • Deprecated function: Required parameter $entity_type follows optional parameter $entity in require_once() (line 341 of /home/aggregate/public_html/includes/module.inc).
  • Deprecated function: Required parameter $entity_type follows optional parameter $values in require_once() (line 341 of /home/aggregate/public_html/includes/module.inc).
  • Deprecated function: Required parameter $entity_type follows optional parameter $view_mode in require_once() (line 341 of /home/aggregate/public_html/includes/module.inc).

Student Seminar – Sonal Joshi “Classify and Detect Adversarial Attacks Against Speaker and Speech Recognition Systems”

Abstract
Adversarial attacks deceive neural network systems by adding carefully crafted perturbations to benign signals. Being almost imperceptible to humans, these attacks pose a severe security threat to the state-of-the-art speech and speaker recognition systems, making it vital to propose countermeasures against them. In this talk, we focus on 1) classification of a given adversarial attack into attack algorithm type, threat model type, and signal-to-adversarial-noise ratios, 2) developing a novel speech denoising solution to further improve the classification performance. 

Chin-Fu Liu Dissertation

<p>Dissertation Title: Developing Integrated MachineLearning Models for Automatic Computer-Aided Diagnosis in MRI Associated withIschemic Acute Stroke.&nbsp;&nbsp;</p><p>Join Zoom Meeting<br></p><p><a href="https://JHUBlueJays.zoom.us/j/92357295752?pwd=TGc4SDI5akE4WnpMQXhZOUgwel... id="ow629" __is_owner="true">

Daniel Khashabi (Allen Institute for Artificial Intelligence) “The Quest Toward Generality in Natural Language Understanding”

Abstract
As AI-driven language interfaces (such as chat-bots) become more integrated into our lives, they need to become more versatile and reliable in their communication with human users. How can we make progress toward building more “general” models that are capable of understanding a broader spectrum of language commands, given practical constraints such as the limited availability of labeled data?

Student Seminar – Saurabhchand Bhati “Segmental Contrastive Predictive Coding for Unsupervised Acoustic Segmentation”

Abstract

Automatic discovery of phone or word-like units is one of the core objectives in zero-resource speech processing. Recent attempts employ contrastive predictive coding (CPC), where the model learns representations by predicting the next frame given past context. However, CPC only looks at the audio signal’s structure at the frame level. The speech structure exists beyond frame-level, i.e., at phone level or even higher. We propose a segmental contrastive predictive coding (SCPC) framework to learn from the signal structure at both the frame and phone levels.

Pages

Subscribe to aggregate.pendari.com RSS