12 citations · 28 across the 11 of their papers we have counts for
12 papers
A Robust framework for sound event localization and detection on real recordings
Jin Sob Kim, Hyun Joon Park, Wooseok Shin +1
This technical report describes the systems submitted to the DCASE2022 challenge task 3: sound event localization and detection (SELD). The task aims to detect occurrences of sound…
Rethinking Leveraging Pre-Trained Multi-Layer Representations for Speaker Verification
Jin Sob Kim, Hyun Joon Park, Wooseok Shin +1
Recent speaker verification studies have achieved notable success by leveraging layer-wise output from pre-trained Transformer models. However, few have explored the advancements i…
WAY: Estimation of Vessel Destination in Worldwide AIS Trajectory
Jin Sob Kim, Hyun Joon Park, Wooseok Shin +2
The Automatic Identification System (AIS) enables data-driven maritime surveillance but suffers from reliability issues and irregular intervals. We address vessel destination estim…
Leveraging Out-of-Distribution Unlabeled Images: Semi-Supervised Semantic Segmentation with an Open-Vocabulary Model
Wooseok Shin, Jisu Kang, Hyeonki Jeong +2
In semi-supervised semantic segmentation, existing studies have shown promising results in academic settings with controlled splits of benchmark datasets. However, the potential be…
RapFlow-TTS: Rapid and High-Fidelity Text-to-Speech with Improved Consistency Flow Matching
Hyun Joon Park, Jeongmin Liu, Jin Sob Kim +3
We introduce RapFlow-TTS, a rapid and high-fidelity TTS acoustic model that leverages velocity consistency constraints in flow matching (FM) training. Although ordinary differentia…
Layer-aware TDNN: Speaker Recognition Using Multi-Layer Features from Pre-Trained Models
Jin Sob Kim, Hyun Joon Park, Wooseok Shin +2
Recent advances in self-supervised learning (SSL) on Transformers have significantly improved speaker verification (SV) by providing domain-general speech representations. However,…
DEX-TTS: Diffusion-based EXpressive Text-to-Speech with Style Modeling on Time Variability
Hyun Joon Park, Jin Sob Kim, Wooseok Shin +1
Expressive Text-to-Speech (TTS) using reference speech has been studied extensively to synthesize natural speech, but there are limitations to obtaining well-represented styles and…
PrevMatch: Revisiting and Maximizing Temporal Knowledge in Semi-Supervised Semantic Segmentation
Wooseok Shin, Hyun Joon Park, Jin Sob Kim +3
In semi-supervised semantic segmentation, the Mean Teacher- and co-training-based approaches are employed to mitigate confirmation bias and coupling problems. However, despite thei…
TriAAN-VC: Triple Adaptive Attention Normalization for Any-to-Any Voice Conversion
Hyun Joon Park, Seok Woo Yang, Jin Sob Kim +2
Voice Conversion (VC) must be achieved while maintaining the content of the source speech and representing the characteristics of the target speaker. The existing methods do not si…
AD-YOLO: You Look Only Once in Training Multiple Sound Event Localization and Detection
Jin Sob Kim, Hyun Joon Park, Wooseok Shin +1
Sound event localization and detection (SELD) combines the identification of sound events with the corresponding directions of arrival (DOA). Recently, event-oriented track output…
Multi-View Attention Transfer for Efficient Speech Enhancement
Wooseok Shin, Hyun Joon Park, Jin Sob Kim +2
Recent deep learning models have achieved high performance in speech enhancement; however, it is still challenging to obtain a fast and low-complexity model without significant per…
MANNER: Multi-view Attention Network for Noise Erasure
Hyun Joon Park, Byung Ha Kang, Wooseok Shin +2
In the field of speech enhancement, time domain methods have difficulties in achieving both high performance and efficiency. Recently, dual-path models have been adopted to represe…