skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.


Title: Enhancing Zero-Shot Many to Many Voice Conversion via Self-Attention VAE with Structurally Regularized Layers
Award ID(s):
1854434 1952644
PAR ID:
10443633
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
International Conference on Artificial Intelligence for Industries
Page Range / eLocation ID:
59 to 63
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract For $$G=\textrm{GL}(n,q)$$, the proportion $$P_{n,q}$$ of pairs $$(\chi ,g)$$ in $$\textrm{Irr}(G)\times G$$ with $$\chi (g)\neq 0$$ satisfies $$P_{n,q}\to 0$$ as $$n\to \infty $$. 
    more » « less
  2. Millimeter Wave (mmWave) networks can deliver multi-Gbps wireless links that use extremely narrow directional beams. This provides us with a new opportunity to exploit spatial reuse in order to scale network throughput. Exploiting such spatial reuse, however, requires aligning the beams of all nodes in a network. Aligning the beams is a difficult process which is complicated by indoor multipath, which can create interference, as well as by the inefficiency of carrier sense at detecting interference in directional links. This paper presents BounceNet, the first many-to-many millimeter wave beam alignment protocol that can exploit dense spatial reuse to allow many links to operate in parallel in a confined space and scale the wireless throughput with the number of clients. Results from three millimeter wave testbeds show that BounceNet can scale the throughput with the number of clients to deliver a total network data rate of more than 39 Gbps for 10 clients, which is up to 6.6× higher than current 802.11 mmWave standards. 
    more » « less
  3. Dispersed computing is a new resource-centric computing paradigm, which makes use of idle resources in the network to complete the tasks. Effectively allocating tasks between task nodes and networked computation points (NCPs) is a critical factor for maximizing the performance of dispersed computing. Due to the heterogeneity of nodes and the priority requirements of tasks, it brings great challenges to the task allocation in dispersed computing. In this paper, we propose a task allocation model based on incomplete preference list. The requirements and permissions of task nodes and NCPs are quantitatively measured through the preference list. In the model, the task completion rate, response time, and communication distance are taken as three optimizing parameters. To solve this NP-hard optimization problem, we develop a new many-to-many matching algorithm based on incomplete preference list. The unilateral optimal and stable solution of the model are obtained. Taking into account the needs for location privacy-preserving, we use the planar Laplace mechanism to produce obfuscated locations instead of real locations. The mechanism satisfies ε-differential privacy. Finally, the efficacy of the proposed model is demonstrated through extensive numerical analysis. Particularly, when the number of task nodes and NCPs reaches 1:2, the task completion rate can reach 99.33%. 
    more » « less