Search Results for author: Hyung-Min Park

Found 7 papers, 5 papers with code

NeXt-TDNN: Modernizing Multi-Scale Temporal Convolution Backbone for Speaker Verification

1 code implementation14 Dec 2023 Hyun-Jun Heo, Ui-Hyeop Shin, Ran Lee, YoungJu Cheon, Hyung-Min Park

Meanwhile, in vision tasks, ConvNet structures have been modernized by referring to Transformer, resulting in improved performance.

Speaker Verification

Distilling a Pretrained Language Model to a Multilingual ASR Model

1 code implementation25 Jun 2022 Kwanghee Choi, Hyung-Min Park

Hence, we are motivated to distill the rich knowledge embedded inside a well-trained teacher text model to the student speech model.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

BREN: Body Reflection Essence-Neuter Model for Separation of Reflection Components

no code implementations25 Aug 2015 Changsoo Je, Hyung-Min Park

We propose a novel reflection color model consisting of body essence and (mixed) neuter, and present an effective method for separating dichromatic reflection components using a single image.

Cannot find the paper you are looking for? You can Submit a new open access paper.