arXiv subjects

Ji Won Yoon

Publications and source records attributed to Ji Won Yoon.

25 records · Page 2Linked to original sources

arXiv2021

TutorNet: Towards Flexible Knowledge Distillation for End-to-End Speech Recognition

In recent years, there has been a great deal of research in developing end-to-end speech recognition models, which enable simplifying the traditional pipeline and achieving promising results. Despite their remarkable performance improvements, end-to-end models typically require expensive computational cost to show successful performance. 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). Previous KD approaches have commonly designed the architecture of the student model by reducing the width per layer or the number of layers of the teacher model. This structural reduction scheme might limit the flexibility of model selection since the student model structure should be similar to that of the given teacher. To cope with this limitation, we propose a new KD method for end-to-end speech recognition, namely TutorNet, that can transfer knowledge across different types of neural networks at the hidden representation-level as well as the output-level. For concrete realizations, we firstly apply representation-level knowledge distillation (RKD) during the initialization step, and then apply the softmax-level knowledge distillation (SKD) combined with the original task learning. When the student is trained with RKD, we make use of frame weighting that points out the frames to which the teacher model pays more attention. Through a number of experiments on LibriSpeech dataset, it is verified that the proposed method not only distills the knowledge between networks with different topologies but also significantly contributes to improving the word error rate (WER) performance of the distilled student. Interestingly, TutorNet allows the student model to surpass its teacher's performance in some particular cases.

eess.AS↗

arXiv2020

Speech to Text Adaptation: Towards an Efficient Cross-Modal Distillation

Speech is one of the most effective means of communication and is full of information that helps the transmission of utterer's thoughts. However, mainly due to the cumbersome processing of acoustic features, phoneme or word posterior probability has frequently been discarded in understanding the natural language. Thus, some recent spoken language understanding (SLU) modules have utilized end-to-end structures that preserve the uncertainty information. This further reduces the propagation of speech recognition error and guarantees computational efficiency. We claim that in this process, the speech comprehension can benefit from the inference of massive pre-trained language models (LMs). 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. We demonstrate the validity of our proposal upon the performance on Fluent Speech Command, an English SLU benchmark. Thereby, we experimentally verify our hypothesis that the knowledge could be shared from the top layer of the LM to a fully speech-based module, in which the abstracted speech is expected to meet the semantic representation.

cs.CL↗

arXiv2013

An Efficient Model Selection for Gaussian Mixture Model in a Bayesian Framework

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. However, model selection to find underlying $\hat{K}$ is one of the key concerns in GMM clustering, since we can obtain the desired clusters only when $\hat{K}$ is known. In this paper, we propose a new model selection algorithm to explore $\hat{K}$ in a Bayesian framework. The proposed algorithm builds the density of the model order which any information criterions such as AIC and BIC basically fail to reconstruct. In addition, this algorithm reconstructs the density quickly as compared to the time-consuming Monte Carlo simulation.

cs.LG↗

arXiv2013

Statistical Denoising for single molecule fluorescence microscopic images

Single molecule fluorescence microscopy is a powerful technique for uncovering detailed information about biological systems, both in vitro and in vivo. In such experiments, the inherently low signal to noise ratios mean that accurate algorithms to separate true signal and background noise are essential to generate meaningful results. To this end, we have developed a new and robust method to reduce noise in single molecule fluorescence images by using a Gaussian Markov Random Field (GMRF) prior in a Bayesian framework. Two different strategies are proposed to build the prior - an intrinsic GMRF, with a stationary relationship between pixels and a heterogeneous intrinsic GMRF, with a differently weighted relationship between pixels classified as molecules and background. Testing with synthetic and real experimental fluorescence images demonstrates that the heterogeneous intrinsic GMRF is superior to other conventional de-noising approaches.

cs.CV↗

arXiv2013

Efficient Estimation of the number of neighbours in Probabilistic K Nearest Neighbour Classification

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. However, an issue common to both KNN and PKNN is to select the optimal number of neighbours, $k$. The contribution of this paper is to incorporate the uncertainty in $k$ into the decision making, and in so doing use Bayesian model averaging to provide improved classification. Indeed the problem of assessing the uncertainty in $k$ can be viewed as one of statistical model selection which is one of the most important technical issues in the statistics and machine learning domain. In this paper, a new functional approximation algorithm is proposed to reconstruct the density of the model (order) without relying on time consuming Monte Carlo simulations. In addition, this algorithm avoids cross validation by adopting Bayesian framework. The performance of this algorithm yielded very good performance on several real experimental datasets.

cs.LG↗

arXiv2009

How to Compare the Scientific Contributions between Research Groups

We present a method to analyse the scientific contributions between research groups. Given multiple research groups, we construct their journal/proceeding graphs and then compute the similarity/gap between them using network analysis. This analysis can be used for measuring similarity/gap of the topics/qualities between research groups' scientific contributions. We demonstrate the practicality of our method by comparing the scientific contributions by Korean researchers with those by the global researchers for information security in 2006 - 2008. The empirical analysis shows that the current security research in South Korea has been isolated from the global research trend.

cs.IR↗

arXiv2009

Hybrid Spam Filtering for Mobile Communication

Spam messages are an increasing threat to mobile communication. Several mitigation techniques have been proposed, including white and black listing, challenge-response and content-based filtering. However, none are perfect and it makes sense to use a combination rather than just one. We propose an anti-spam framework based on the hybrid of content-based filtering and challenge-response. There is the trade-offs between accuracy of anti-spam classifiers and the communication overhead. Experimental results show how, depending on the proportion of spam messages, different filtering %%@ parameters should be set.

cs.CR↗