64 citations · 210 across the 14 of their papers we have counts for
14 papers
Pseudo Outlier Exposure for Out-of-Distribution Detection using Pretrained Transformers
Jaeyoung Kim, Kyuheon Jung, Dongbin Na +3
For real-world language applications, detecting an out-of-distribution (OOD) sample is helpful to alert users or reject such unreliable samples. However, modern over-parameterized…
Bag of Tricks for In-Distribution Calibration of Pretrained Transformers
Jaeyoung Kim, Dongbin Na, Sungchul Choi +1
While pre-trained language models (PLMs) have become a de-facto standard promoting the accuracy of text classification tasks, recent studies find that PLMs often predict over-confi…
Nonparametric Decoding for Generative Retrieval
Hyunji Lee, Jaeyoung Kim, Hoyeon Chang +5
The generative retrieval model depends solely on the information encoded in its model parameters without external memory, its information capacity is limited and fixed. To overcome…
Contrastive Siamese Network for Semi-supervised Speech Recognition
Soheil Khorram, Jaeyoung Kim, Anshuman Tripathi +3
This paper introduces contrastive siamese (c-siam) network, an architecture for leveraging unlabeled acoustic data in speech recognition. c-siam is the first network that extracts…
Reducing Streaming ASR Model Delay with Self Alignment
Jaeyoung Kim, Han Lu, Anshuman Tripathi +2
Reducing prediction delay for streaming end-to-end ASR models with minimal performance regression is a challenging problem. Constrained alignment is a well-known existing approach…
Deep learning-based citation recommendation system for patents
Jaewoong Choi, Sion Jang, Jaeyoung Kim +3
In this study, we address the challenges in developing a deep learning-based automatic patent citation recommendation system. Although deep learning-based recommendation systems ha…
Transformer Transducer: One Model Unifying Streaming and Non-streaming Speech Recognition
Anshuman Tripathi, Jaeyoung Kim, Qian Zhang +2
In this paper we present a Transformer-Transducer model architecture and a training technique to unify streaming and non-streaming speech recognition models into one model. The mod…
Githru: Visual Analytics for Understanding Software Development History Through Git Metadata Analysis
Youngtaek Kim, Jaeyoung Kim, Hyeon Jeon +4
Git metadata contains rich information for developers to understand the overall context of a large software development project. Thus it can help new developers, managers, and test…
End-to-End Multi-Task Denoising for the Joint Optimization of Perceptual Speech Metrics
Jaeyoung Kim, Mostafa El-Khamy, Jungwon Lee
Although supervised learning based on a deep neural network has recently achieved substantial improvement on speech enhancement, the existing schemes have either of two critical is…
T-GSA: Transformer with Gaussian-weighted self-attention for speech enhancement
Jaeyoung Kim, Mostafa El-Khamy, Jungwon Lee
Transformer neural networks (TNN) demonstrated state-of-art performance on many natural language processing (NLP) tasks, replacing recurrent neural networks (RNNs), such as LSTMs o…
End-to-End Multi-Task Denoising for joint SDR and PESQ Optimization
Jaeyoung Kim, Mostafa El-Khamy, Jungwon Lee
Supervised learning based on a deep neural network recently has achieved substantial improvement on speech enhancement. Denoising networks learn mapping from noisy speech to clean…
Text Classification using Capsules
Jaeyoung Kim, Sion Jang, Sungchul Choi +1
This paper presents an empirical exploration of the use of capsule networks for text classification. While it has been shown that capsule networks are effective for image classific…
BridgeNets: Student-Teacher Transfer Learning Based on Recursive Neural Networks and its Application to Distant Speech Recognition
Jaeyoung Kim, Mostafa El-Khamy, Jungwon Lee
Despite the remarkable progress achieved on automatic speech recognition, recognizing far-field speeches mixed with various noise sources is still a challenging task. In this paper…
Residual LSTM: Design of a Deep Recurrent Architecture for Distant Speech Recognition
Jaeyoung Kim, Mostafa El-Khamy, Jungwon Lee
In this paper, a novel architecture for a deep recurrent neural network, residual LSTM is introduced. A plain LSTM has an internal memory cell that can learn long term dependencies…