paper-with-me

Papers

Bypassing Optimization Complexity through Transfer Learning & Deep Neural Nets for Speech Intelligibility Improvement

2021-12-01 · ICON 2021 12 · Ritujoy Biswas

This extended abstract highlights the research ventures and findings in the domain of speech intelligibility improvement. Till this point, an effort has been to simulate the Lombard effect, which is the deliberate human attempt to make a speech more intelligible when speaking in the presence of interfering background noise. To that end, an attempt has been made to shift the formants away from the noisy regions in spectrum both sub-optimally and optimally. The sub-optimal shifting methods were based upon Kalman filtering and EM approach. The optimal shifting involved the use of optimization to maximize an objective intelligibility index after shifting the formants. A transfer learning framework was also set up to bring down the computational complexity.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Transfer Learning

Similar Papers 제목 키워드 기반

Exploration through Generation: Applying GFlowNets to Structured Search

2025-10-23 · Mark Phillip Matovic arxiv

This work applies Generative Flow Networks (GFlowNets) to three graph optimization problems: the Traveling Salesperson Problem, Minimum Spanning Tree, and Shortest Path. GFlowNets are generative models that learn to samp…

Graph-Theoretic Analysis of Phase Optimization Complexity in Variational Wave Functions for Heisenberg Antiferromagnets

2026-02-04 · Mahmud Ashraf Shamim, Md Moshiur Rahman Raj, Mohamed Hibat-Allah, Paulo T Araujo arxiv

We study the computational complexity of learning the ground state phase structure of Heisenberg antiferromagnets. Representing Hilbert space as a weighted graph, the variational energy defines a weighted XY model that, …

Generative Flow Networks: a Markov Chain Perspective

2023-07-04 · Tristan Deleu, Yoshua Bengio

While Markov chain Monte Carlo methods (MCMC) provide a general framework to sample from a probability distribution defined up to normalization, they often suffer from slow convergence to the target distribution when the…

Decision MakingSequential Decision Making

Technical Report: Combining knowledge from Transfer Learning during training and Wide Resnets

2022-06-20 · Wolfgang Fuhl

In this report, we combine the idea of Wide ResNets and transfer learning to optimize the architecture of deep neural networks. The first improvement of the architecture is the use of all layers as information source for…

Data AugmentationTransfer Learning

MixFaceNets: Extremely Efficient Face Recognition Networks

2021-07-27 · Fadi Boutros, Naser Damer, Meiling Fang, Florian Kirchbuchner 외

In this paper, we present a set of extremely efficient and high throughput models for accurate face verification, MixFaceNets which are inspired by Mixed Depthwise Convolutional Kernels. Extensive experiment evaluations …

Face RecognitionFace VerificationLightweight Face Recognition