YLYoushin Lim

Youshin Lim

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Youshin Lim has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    That's What I Said: Fully-Controllable Talking Face Generation

    by Youngjoon Jang, Kyeongha Rho, Jongbin Woo, Hyeongkeun Lee, Jihwan Park, Youshin Lim, Byeong-Yeol Kim, Joon Son Chung


  • ASBERT: ASR-Specific Self-Supervised Learning with Self-Training

    by Hyung Yong Kim, Byeong-Yeol Kim, Seung Woo Yoo, Youshin Lim, Yunkyu Lim, Hanbin Lee

    Pre-training of self-supervised learning (SSL) generally shows a good performance on various speech processing tasks. However, this pre-training scheme may lead to a sub-optimal solution for fine-tuning a specific task, such as automatic speech recognition (ASR). In order to provide a more optimal pre-trained model for ASR, we introduce an ASR-Specific hidden-unit BERT with self-training, namely ASBERT. Motivated by self-training, we extract linguistic-related pseudo labels from the fine-tuned model, and these labels are used in the next pre-training procedure. Experimental results on LibriSpeech test-clean and test-other datasets show that ASBERT without language model (LM) outperforms the conventional SSL and self-training model, achieving a 6.3/2.0% and 15.4/13.2% relatively word error rate reduction (RERR). Moreover, without using pseudo-transcription, ASBERT yields comparable performance to the conventional self-training method.


  • Open Access

    Metric Learning for User-defined Keyword Spotting

    by Jaemin Jung, Youkyum Kim, Jihwan Park, Youshin Lim, Byeong-Yeol Kim, Youngjoon Jang, Joon Son Chung

    The goal of this work is to detect new spoken terms defined by users. While most previous works address Keyword Spotting (KWS) as a closed-set classification problem, this limits their transferability to unseen terms. The ability to define custom keywords has advantages in terms of user experience. In this paper, we propose a metric learning-based training strategy for user-defined keyword spotting. In particular, we make the following contributions: (1) we construct a large-scale keyword dataset with an existing speech corpus and propose a filtering method to remove data that degrade model training; (2) we propose a metric learning-based two-stage training strategy, and demonstrate that the proposed method improves the performance on the user-defined keyword spotting task by enriching their representations; (3) to facilitate the fair comparison in the user-defined KWS field, we propose unified evaluation protocol and metrics. Our proposed system does not require an incremental training on the user-defined keywords, and outperforms previous works by a significant margin on the Google Speech Commands dataset using the proposed as well as the existing metrics.