no code implementations • 14 Jun 2023 • Ji Won Yoon, Seok Min Kim, Nam Soo Kim
Self-supervised learning (SSL) has shown significant progress in speech processing tasks.
no code implementations • 14 Jun 2023 • Ji Won Yoon, Sunghwan Ahn, Hyeonseung Lee, Minchan Kim, Seok Min Kim, Nam Soo Kim
We introduce EM-Network, a novel self-distillation approach that effectively leverages target information for supervised sequence-to-sequence (seq2seq) learning.
no code implementations • 1 Feb 2023 • Seong-Eun Moon, Ji Won Yoon, Shinyoung Joo, Yoohyung Kim, Jae Hyun Bae, Seokho Yoon, Haanju Yoo, Young Min Cho
Methods: This paper proposes a novel deep learning model to learn latent representations of biological aging in regard to subjects' morbidity and mortality.
no code implementations • 28 Nov 2022 • Ji Won Yoon, Beom Jun Woo, Sunghwan Ahn, Hyeonseung Lee, Nam Soo Kim
Recently, the advance in deep learning has brought a considerable improvement in the end-to-end speech recognition field, simplifying the traditional pipeline while producing promising results.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • 13 Apr 2022 • Ji Won Yoon, Beom Jun Woo, Nam Soo Kim
Pre-training with self-supervised models, such as Hidden-unit BERT (HuBERT) and wav2vec 2. 0, has brought significant improvements in automatic speech recognition (ASR).
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 5 Nov 2021 • Ji Won Yoon, Hyung Yong Kim, Hyeonseung Lee, Sunghwan Ahn, Nam Soo Kim
Extending this supervised scheme further, we introduce a new type of teacher model for connectionist temporal classification (CTC)-based sequence models, namely Oracle Teacher, that leverages both the source inputs and the output labels as the teacher model's input.
no code implementations • 3 Aug 2020 • Ji Won Yoon, Hyeonseung Lee, Hyung Yong Kim, Won Ik Cho, Nam Soo Kim
To reduce this computational burden, knowledge distillation (KD), which is a popular model compression method, has been used to transfer knowledge from a deep and complex model (teacher) to a shallower and simpler model (student).
no code implementations • 17 May 2020 • Won Ik Cho, Dong-Hyun Kwak, Ji Won Yoon, Nam Soo Kim
We transfer the knowledge from a concrete Transformer-based text LM to an SLU module which can face a data shortage, based on recent cross-modal distillation methodologies.
2 code implementations • 10 Nov 2018 • Won Ik Cho, Hyeon Seung Lee, Ji Won Yoon, Seok Min Kim, Nam Soo Kim
This paper suggests a system which identifies the inherent intention of a spoken utterance given its transcript, in some cases using auxiliary acoustic features.
no code implementations • 3 Jul 2013 • Ji Won Yoon
In order to cluster or partition data, we often use Expectation-and-Maximization (EM) or Variational approximation with a Gaussian Mixture Model (GMM), which is a parametric probability density function represented as a weighted sum of $\hat{K}$ Gaussian component densities.
no code implementations • 7 Jun 2013 • Ji Won Yoon
Single molecule fluorescence microscopy is a powerful technique for uncovering detailed information about biological systems, both in vitro and in vivo.
no code implementations • 5 May 2013 • Ji Won Yoon, Nial Friel
Probabilistic k-nearest neighbour (PKNN) classification has been introduced to improve the performance of original k-nearest neighbour (KNN) classification algorithm by explicitly modelling uncertainty in the classification of each feature vector.