• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.111-115
• /
• 2017

목적 지향적 대화 시스템(Goal-oriented dialogue system)은 텍스트나 음성을 통해 특정한 목적을 수행할 수 있는 시스템이다. 최근 RNN(recurrent neural networks)을 기반으로 대화 데이터를 end-to-end learning 방식으로 학습하여 대화 시스템을 구축하는데에 활용한 연구가 있다. End-to-end 방식의 학습은 도메인에 대한 지식 없이 학습 데이터 자체만으로 대화 시스템 구축을 위한 학습이 가능하다는 장점이 있지만 도메인 지식을 학습하기 위해서는 많은 양의 데이터가 필요하다는 단점이 존재한다. 이에 본 논문에서는 도메인 특정 지식을 결합하여 end-to-end learning 방식의 학습이 가능한 Hybrid Code Network 구조를 기반으로 한국어로 구성된 식당 예약에 관련한 대화 데이터셋을 이용하여 식당 예약을 목적으로하는 대화 시스템을 구축하는 방법을 제안한다. 실험 결과 본 시스템은 응답 별 정확도 95%와 대화 별 정확도 63%의 성능을 나타냈다.

• Journal of Internet of Things and Convergence
• /
• v.9 no.1
• /
• pp.65-70
• /
• 2023

In this paper, we propose an autonomous driving system using an end-to-end model to improve lane departure and misrecognition of traffic lights in a vision sensor-based system. End-to-end learning can be extended to a variety of environmental conditions. Driving data is collected using a model car based on a vision sensor. Using the collected data, it is composed of existing data and data with outlayers removed. A class was formed with camera image data as input data and speed and steering data as output data, and data learning was performed using an end-to-end model. The reliability of the trained model was verified. Apply the learned end-to-end model to the model car to predict the steering angle with image data. As a result of the learning of the model car, it can be seen that the model with the outlayer removed is improved than the existing model.

• Proceedings of The KACE
• /
• 2017.08a
• /
• pp.57-59
• /
• 2017

대화 시스템(dialogue system)은 텍스트나 음성을 통해 다양한 분야에서 특정한 목적을 수행할 수 있는 시스템이다. 대화 시스템을 구현하기 위한 방법으로 인공 신경망(neural network)을 기반으로한 end-to-end learning 방식이 제안되었다. End-to-end learning 방식을 이용한 식당 예약 시스템 모델의 학습을 위해 페이스북은 영어로 이루어진 식당 예약에 관련된 학습 대화 데이터셋(The 6 dialog bAbI tasks)을 구축하였다. 하지만 end-to-end learning 방식의 학습은 많은 학습 데이터가 필요하다는 단점이 존재하는데, 액션 템플릿(action template)의 정의를 통해 도메인 지식을 표현함으로써 일반적인 end-to-end learning 방식보다 적은 학습량으로 좋은 성능의 모델을 학습할 수 있는 Hybrid Code Network 구조를 제안한 연구가 있다. 본 논문에서는 Hybrid Code Network 구조를 이용하여 한국어 식당 예약 시스템을 구축할 수 있는 방법을 제안하고, 한국어로 이루어진 식당 예약에 관련한 학습 대화 데이터를 구축하는 방법을 제안한다.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.111-115
• /
• 2017

목적 지향적 대화 시스템(Goal-oriented dialogue system) 은 텍스트나 음성을 통해 특정한 목적을 수행 할 수 있는 시스템이다. 최근 RNN(recurrent neural networks)을 기반으로 대화 데이터를 end-to-end learning 방식으로 학습하여 대화 시스템을 구축하는데에 활용한 연구가 있다. End-to-end 방식의 학습은 도메인에 대한 지식 없이 학습 데이터 자체만으로 대화 시스템 구축을 위한 학습이 가능하다는 장점이 있지만 도메인 지식을 학습하기 위해서는 많은 양의 데이터가 필요하다는 단점이 존재한다. 이에 본 논문에서는 도메인 특정 지식을 결합하여 end-to-end learning 방식의 학습이 가능한 Hybrid Code Network 구조를 기반으로 한국어로 구성된 식당 예약에 관련한 대화 데이터셋을 이용하여 식당 예약을 목적으로하는 대화 시스템을 구축하는 방법을 제안한다. 실험 결과 본 시스템은 응답 별 정확도 95%와 대화 별 정확도 63%의 성능을 나타냈다.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.6
• /
• pp.578-586
• /
• 2021

We propose a semi-supervised learning method based on Variational AutoEncoder (VAE) and Unsupervised Data Augmentation (UDA) to improve the performance of an end-to-end speech recognizer. In the proposed method, first, the VAE-based augmentation model and the baseline end-to-end speech recognizer are trained using the original speech data. Then, the baseline end-to-end speech recognizer is trained again using data augmented from the learned augmentation model. Finally, the learned augmentation model and end-to-end speech recognizer are re-learned using the UDA-based semi-supervised learning method. As a result of the computer simulation, the augmentation model is shown to improve the Word Error Rate (WER) of the baseline end-to-end speech recognizer, and further improve its performance by combining it with the UDA-based learning method.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1171-1172
• /
• 2023

자율주행 기술에서 스테레오 비전과 End-to-End Driving은 많이 사용되는 기술이며 본 연구에서는 이를 신호등 인식과 주행에 적용하였다. 신호등 인식은 좌우 카메라로부터 적색 원을 인식한 후 스테레오 비전을 통해 신호등과의 거리를 추정한다. 주행 시스템은 End-to-End Learning 기반으로 이루어지며, 출력값인 가변저항을 조향각으로 변환하여 제어할 수 있다. 또한 감마 보정을 통한 데이터 증강을 통해 빛에 대해 민감하지 않게 모델을 학습하였다. 추후 신호등 인식 시 HSV 필터가 빛에 민감한 점과 주행 시 가변저항 값이 일정하지 않은 점이 해결된다면 더욱 안정적인 시스템을 구축할 수 있을 것으로 기대된다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1267-1270
• /
• 2021

In this paper, we propose a distributed routing algorithm for mobile ad hoc networks (MANET) where mobile devices can be utilized as relays for communication between remote source-destination nodes. The objective of the proposed algorithm is to minimize the end-to-end communication delay caused by transmission failure with deep channel fading. In each hop, the node needs to select the next relaying node by considering a tradeoff relationship between the link stability and forward link distance. Based on such feature, we formulate the problem with partially observable Markov decision process (MDP) and apply deep reinforcement learning to derive effective routing strategy for the formulated MDP. Simulation results show that the proposed algorithm outperforms other baseline schemes in terms of the average end-to-end delay.

• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1380-1390
• /
• 2021

The video face recognition (FR) is one of the most popular researches in the field of computer vision due to a variety of applications. In particular, research using the attention mechanism is being actively conducted. In video face recognition, attention represents where to focus on by using the input value of the whole or a specific region, or which frame to focus on when there are many frames. In this paper, we propose a novel attention based deep learning method. Main novelties of our method are (1) the use of combining two loss functions, namely weighted Softmax loss function and a Triplet loss function and (2) the feasibility of end-to-end learning which includes the feature embedding network and attention weight computation. The feature embedding network has a positive effect on the attention weight computation by using combined loss function and end-to-end learning. To demonstrate the effectiveness of our proposed method, extensive and comparative experiments have been carried out to evaluate our method on IJB-A dataset with their standard evaluation protocols. Our proposed method represented better or comparable recognition rate compared to other state-of-the-art video FR methods.

• The Journal of Korea Robotics Society
• /
• v.14 no.2
• /
• pp.122-130
• /
• 2019

Collecting a rich but meaningful training data plays a key role in machine learning and deep learning researches for a self-driving vehicle. This paper introduces a detailed overview of existing open-source simulators which could be used for training self-driving vehicles. After reviewing the simulators, we propose a new effective approach to make a synthetic autonomous vehicle simulation platform suitable for learning and training artificial intelligence algorithms. Specially, we develop a synthetic simulator with various realistic situations and weather conditions which make the autonomous shuttle to learn more realistic situations and handle some unexpected events. The virtual environment is the mimics of the activity of a genuine shuttle vehicle on a physical world. Instead of doing the whole experiment of training in the real physical world, scenarios in 3D virtual worlds are made to calculate the parameters and training the model. From the simulator, the user can obtain data for the various situation and utilize it for the training purpose. Flexible options are available to choose sensors, monitor the output and implement any autonomous driving algorithm. Finally, we verify the effectiveness of the developed simulator by implementing an end-to-end CNN algorithm for training a self-driving shuttle.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.48-58
• /
• 2024

This paper presents the development of language tutoring systems for nonnative speakers by leveraging advanced end-to-end automatic speech recognition (ASR) and proficiency evaluation. Given the frequent errors in non-native speech, high-performance spontaneous speech recognition must be applied. Our systems accurately evaluate pronunciation and speaking fluency and provide feedback on errors by relying on precise transcriptions. End-to-end ASR is implemented and enhanced by using diverse non-native speaker speech data for model training. For performance enhancement, we combine semisupervised and transfer learning techniques using labeled and unlabeled speech data. Automatic proficiency evaluation is performed by a model trained to maximize the statistical correlation between the fluency score manually determined by a human expert and a calculated fluency score. We developed an English tutoring system for Korean elementary students called EBS AI Peng-Talk and a Korean tutoring system for foreigners called KSI Korean AI Tutor. Both systems were deployed by South Korean government agencies.