8 citations · 15 across the 7 of their papers we have counts for
7 papers
Statistical Beamformer Exploiting Non-stationarity and Sparsity with Spatially Constrained ICA for Robust Speech Recognition
Ui-Hyeop Shin, Hyung-Min Park
In this paper, we present a statistical beamforming algorithm as a pre-processing step for robust automatic speech recognition (ASR). By modeling the target speech as a non-station…
Unsupervised Speech Representation Pooling Using Vector Quantization
Jeongkyun Park, Kwanghee Choi, Hyunjun Heo +1
With the advent of general-purpose speech representations from large-scale self-supervised models, applying a single model to multiple downstream tasks is becoming a de-facto appro…
OLKAVS: An Open Large-Scale Korean Audio-Visual Speech Dataset
Jeongkyun Park, Jung-Wook Hwang, Kwanghee Choi +4
Inspired by humans comprehending speech in a multi-modal manner, various audio-visual datasets have been constructed. However, most existing datasets focus on English, induce depen…
Distilling a Pretrained Language Model to a Multilingual ASR Model
Kwanghee Choi, Hyung-Min Park
Multilingual speech data often suffer from long-tailed language distribution, resulting in performance degradation. However, multilingual text data is much easier to obtain, yieldi…
Overcoming label noise in audio event detection using sequential labeling
Jae-Bin Kim, Seongkyu Mun, Myungwoo Oh +3
This paper addresses the noisy label issue in audio event detection (AED) by refining strong labels as sequential labels with inaccurate timestamps removed. In AED, strong labels c…
Unsupervised Speech Domain Adaptation Based on Disentangled Representation Learning for Robust Speech Recognition
Jong-Hyeon Park, Myungwoo Oh, Hyung-Min Park
In general, the performance of automatic speech recognition (ASR) systems is significantly degraded due to the mismatch between training and test environments. Recently, a deep-lea…
BREN: Body Reflection Essence-Neuter Model for Separation of Reflection Components
Changsoo Je, Hyung-Min Park
We propose a novel reflection color model consisting of body essence and (mixed) neuter, and present an effective method for separating dichromatic reflection components using a si…