Acoustic Scene Classification Based on a Large-margin Factorized CNN

no code implementations • 14 Oct 2019 • Janghoon Cho, Sungrack Yun, Hyoungwoo Park, Jungyun Eum, Kyuwoong Hwang

With this loss function, the samples from the same audio scene are clustered independently of the environment, and thus we can get the classifier with better generalization ability in an unseen environment.

Acoustic Scene Classification Classification +2

Weakly Labeled Sound Event Detection Using Tri-training and Adversarial Learning

no code implementations • 14 Oct 2019 • Hyoungwoo Park, Sungrack Yun, Jungyun Eum, Janghoon Cho, Kyuwoong Hwang

This paper considers a semi-supervised learning framework for weakly labeled polyphonic sound event detection problems for the DCASE 2019 challenge's task4 by combining both the tri-training and adversarial learning.

Event Detection Sound Event Detection

An End-to-End Text-independent Speaker Verification Framework with a Keyword Adversarial Network

no code implementations • 6 Aug 2019 • Sungrack Yun, Janghoon Cho, Jungyun Eum, Wonil Chang, Kyuwoong Hwang

In training our speaker verification framework, we consider both the triplet loss minimization and adversarial gradient of the ASR network to obtain more discriminative and text-independent speaker embedding vectors.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2