177 citations · 509 across the 26 of their papers we have counts for
28 papers
Yet Another Generative Model For Room Impulse Response Estimation
Sungho Lee, Hyeong-Seok Choi, Kyogu Lee
Recent neural room impulse response (RIR) estimators typically comprise an encoder for reference audio analysis and a generator for RIR synthesis. Especially, it is the performance…
Exploiting Negative Preference in Content-based Music Recommendation with Contrastive Learning
Minju Park, Kyogu Lee
Advanced music recommendation systems are being introduced along with the development of machine learning. However, it is essential to design a music recommendation system that can…
Differentiable Artificial Reverberation
Sungho Lee, Hyeong-Seok Choi, Kyogu Lee
Artificial reverberation (AR) models play a central role in various audio applications. Therefore, estimating the AR model parameters (ARPs) of a reference reverberation is a cruci…
Room adaptive conditioning method for sound event classification in reverberant environments
Jaejun Lee, Donmoon Lee, Hyeong-Seok Choi +1
Ensuring performance robustness for a variety of situations that can occur in real-world environments is one of the challenging tasks in sound event classification. One of the unpr…
Reverb Conversion of Mixed Vocal Tracks Using an End-to-end Convolutional Deep Neural Network
Junghyun Koo, Seungryeol Paik, Kyogu Lee
Reverb plays a critical role in music production, where it provides listeners with spatial realization, timbre, and texture of the music. Yet, it is challenging to reproduce the mu…
Real-time Denoising and Dereverberation with Tiny Recurrent U-Net
Hyeong-Seok Choi, Sungjin Park, Jie Hwan Lee +3
Modern deep learning-based models have seen outstanding performance improvement with speech enhancement tasks. The number of parameters of state-of-the-art models, however, is ofte…
Neural Audio Fingerprint for High-specific Audio Retrieval based on Contrastive Learning
Sungkyun Chang, Donmoon Lee, Jeongsoo Park +4
Most of existing audio fingerprinting systems have limitations to be used for high-specific audio retrieval at scale. In this work, we generate a low-dimensional representation fro…
Exploiting Multi-Modal Features From Pre-trained Networks for Alzheimer's Dementia Recognition
Junghyun Koo, Jie Hwan Lee, Jaewoo Pyo +2
Collecting and accessing a large amount of medical data is very time-consuming and laborious, not only because it is difficult to find specific patients but also because it is requ…
Exploring Aligned Lyrics-Informed Singing Voice Separation
Chang-Bin Jeon, Hyeong-Seok Choi, Kyogu Lee
In this paper, we propose a method of utilizing aligned lyrics as additional information to improve the performance of singing voice separation. We have combined the highway networ…
Phase-aware Single-stage Speech Denoising and Dereverberation with U-Net
Hyeong-Seok Choi, Hoon Heo, Jie Hwan Lee +1
In this work, we tackle a denoising and dereverberation problem with a single-stage framework. Although denoising and dereverberation may be considered two separate challenging tas…
From Inference to Generation: End-to-end Fully Self-supervised Generation of Human Face from Speech
Hyeong-Seok Choi, Changdae Park, Kyogu Lee
This work seeks the possibility of generating the human face from voice solely based on the audio-visual data without any human-labeled annotations. To this end, we propose a multi…
Disentangling Timbre and Singing Style with Multi-singer Singing Synthesis System
Juheon Lee, Hyeong-Seok Choi, Junghyun Koo +1
In this study, we define the identity of the singer with two independent concepts - timbre and singing style - and propose a multi-singer singing synthesis system that can model th…
Audio query-based music source separation
Jie Hwan Lee, Hyeong-Seok Choi, Kyogu Lee
In recent years, music source separation has been one of the most intensively studied research areas in music information retrieval. Improvements in deep learning lead to a big pro…
Adversarially Trained End-to-end Korean Singing Voice Synthesis System
Juheon Lee, Hyeong-Seok Choi, Chang-Bin Jeon +2
In this paper, we propose an end-to-end Korean singing voice synthesis system from lyrics and a symbolic melody using the following three novel approaches: 1) phonetic enhancement…
Phase-aware Speech Enhancement with Deep Complex U-Net
Hyeong-Seok Choi, Jang-Hyun Kim, Jaesung Huh +3
Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction.…
Enhancing Music Features by Knowledge Transfer from User-item Log Data
Donmoon Lee, Jaejun Lee, Jeongsoo Park +1
In this paper, we propose a novel method that exploits music listening log data for general-purpose music feature extraction. Despite the wealth of information available in the log…
Sequential Skip Prediction with Few-shot in Streamed Music Contents
Sungkyun Chang, Seungjin Lee, Kyogu Lee
This paper provides an outline of the algorithms submitted for the WSDM Cup 2019 Spotify Sequential Skip Prediction Challenge (team name: mimbres). In the challenge, complete infor…
Listen to Dance: Music-driven choreography generation using Autoregressive Encoder-Decoder Network
Juheon Lee, Seohyun Kim, Kyogu Lee
Automatic choreography generation is a challenging task because it often requires an understanding of two abstract concepts - music and dance - which are realized in the two differ…
Content-based feature exploration for transparent music recommendation using self-attentive genre classification
Seungjin Lee, Juheon Lee, Kyogu lee
Interpretation of retrieved results is an important issue in music recommender systems, particularly from a user perspective. In this study, we investigate the methods for providin…
Music Source Separation Using Stacked Hourglass Networks
Sungheon Park, Taehoon Kim, Kyogu Lee +1
In this paper, we propose a simple yet effective method for multiple music source separation using convolutional neural networks. Stacked hourglass network, which was originally de…
Separation of Instrument Sounds using Non-negative Matrix Factorization with Spectral Envelope Constraints
Jeongsoo Park, Jaeyoung Shin, Kyogu Lee
Spectral envelope is one of the most important features that characterize the timbre of an instrument sound. However, it is difficult to use spectral information in the framework o…
Chord Generation from Symbolic Melody Using BLSTM Networks
Hyungui Lim, Seungyeon Rhyu, Kyogu Lee
Generating a chord progression from a monophonic melody is a challenging problem because a chord progression requires a series of layered notes played simultaneously. This paper pr…
Audio Cover Song Identification using Convolutional Neural Network
Sungkyun Chang, Juheon Lee, Sang Keun Choe +1
In this paper, we propose a new approach to cover song identification using a CNN (convolutional neural network). Most previous studies extract the feature vectors that characteriz…
Lyrics-to-Audio Alignment by Unsupervised Discovery of Repetitive Patterns in Vowel Acoustics
Sungkyun Chang, Kyogu Lee
Most of the previous approaches to lyrics-to-audio alignment used a pre-developed automatic speech recognition (ASR) system that innately suffered from several difficulties to adap…