Search Results for author: Gwantae Kim

Found 7 papers, 1 papers with code

Gated Low-rank Adaptation for personalized Code-Switching Automatic Speech Recognition on the low-spec devices

no code implementations24 Apr 2024 Gwantae Kim, Bokyeung Lee, Donghyeon Kim, Hanseok Ko

To tackle this problem, we propose code-switching speech recognition models that incorporate fine-tuned monolingual and multilingual speech recognition models.

Automatic Speech Recognition speech-recognition +1

Towards Multi-domain Face Landmark Detection with Synthetic Data from Diffusion model

no code implementations24 Jan 2024 Yuanming Li, Gwantae Kim, Jeong-gi Kwak, Bon-hwa Ku, Hanseok Ko

Finally, we fine-tuned a pre-trained face landmark detection model on the synthetic dataset to achieve multi-domain face landmark detection.

Caricature Face Generation +1

MPE4G: Multimodal Pretrained Encoder for Co-Speech Gesture Generation

no code implementations25 May 2023 Gwantae Kim, Seonghyeok Noh, Insung Ham, Hanseok Ko

Through the series of experiments and human evaluation, the proposed method renders realistic co-speech gestures not only when all input modalities are given but also when the input modalities are missing or noisy.

Gesture Generation Self-Supervised Learning

3d human motion generation from the text via gesture action classification and the autoregressive model

no code implementations18 Nov 2022 Gwantae Kim, Youngsuk Ryu, Junyeop Lee, David K. Han, Jeongmin Bae, Hanseok Ko

To achieve the goal, the proposed method predicts expression from the sentences using a text classification model based on a pretrained language model and generates gestures using the gate recurrent unit-based autoregressive model.

Action Classification Action Recognition +4

Efficient dynamic filter for robust and low computational feature extraction

no code implementations3 May 2022 Donghyeon Kim, Gwantae Kim, Bokyeung Lee, Jeong-gi Kwak, David K. Han, Hanseok Ko

However, the performance of the dynamic filter might be degraded since simple feature pooling is used to reduce the computational resource in the IDF part.

Keyword Spotting Speaker Verification

Cannot find the paper you are looking for? You can Submit a new open access paper.