25 citations · 38 across the 11 of their papers we have counts for
13 papers
SelFusion: Self-distillation for Diffusion Language Models
Hyeongsoo Lim, Jinyoung Kim, Eunseo Seo +2
Diffusion language models (DLMs) alleviate the inherent latency bottleneck of autoregressive (AR) large language models (LLMs), but their degraded generation quality limits practic…
KoALa-Bench: Evaluating Large Audio Language Models on Korean Speech Understanding and Faithfulness
Jinyoung Kim, Hyeongsoo Lim, Eunseo Seo +4
Recent advances in large audio language models (LALMs) have enabled multilingual speech understanding. However, benchmarks for evaluating LALMs remain scarce for non-English langua…
Semantic-Aware Reconstruction Error for Detecting AI-Generated Images
Ju Yeon Kang, Jaehong Park, Semin Kim +2
Recently, AI-generated image detection has gained increasing attention, as the rapid advancement of image generation technologies has raised serious concerns about their potential…
FADEL: Uncertainty-aware Fake Audio Detection with Evidential Deep Learning
Ju Yeon Kang, Ji Won Yoon, Semin Kim +2
Recently, fake audio detection has gained significant attention, as advancements in speech synthesis and voice conversion have increased the vulnerability of automatic speaker veri…
Towards Maximum Likelihood Training for Transducer-based Streaming Speech Recognition
Hyeonseung Lee, Ji Won Yoon, Sungsoo Kim +1
Transducer neural networks have emerged as the mainstream approach for streaming automatic speech recognition (ASR), offering state-of-the-art performance in balancing accuracy and…
EM-Network: Oracle Guided Self-distillation for Sequence Learning
Ji Won Yoon, Sunghwan Ahn, Hyeonseung Lee +3
We introduce EM-Network, a novel self-distillation approach that effectively leverages target information for supervised sequence-to-sequence (seq2seq) learning. In contrast to con…
MCR-Data2vec 2.0: Improving Self-supervised Speech Pre-training via Model-level Consistency Regularization
Ji Won Yoon, Seok Min Kim, Nam Soo Kim
Self-supervised learning (SSL) has shown significant progress in speech processing tasks. However, despite the intrinsic randomness in the Transformer structure, such as dropout va…
Inter-KD: Intermediate Knowledge Distillation for CTC-Based Automatic Speech Recognition
Ji Won Yoon, Beom Jun Woo, Sunghwan Ahn +2
Recently, the advance in deep learning has brought a considerable improvement in the end-to-end speech recognition field, simplifying the traditional pipeline while producing promi…
HuBERT-EE: Early Exiting HuBERT for Efficient Speech Recognition
Ji Won Yoon, Beom Jun Woo, Nam Soo Kim
Pre-training with self-supervised models, such as Hidden-unit BERT (HuBERT) and wav2vec 2.0, has brought significant improvements in automatic speech recognition (ASR). However, th…
Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models
Ji Won Yoon, Hyung Yong Kim, Hyeonseung Lee +2
Knowledge distillation (KD), best known as an effective method for model compression, aims at transferring the knowledge of a bigger network (teacher) to a much smaller network (st…
TutorNet: Towards Flexible Knowledge Distillation for End-to-End Speech Recognition
Ji Won Yoon, Hyeonseung Lee, Hyung Yong Kim +2
In recent years, there has been a great deal of research in developing end-to-end speech recognition models, which enable simplifying the traditional pipeline and achieving promisi…
Speech to Text Adaptation: Towards an Efficient Cross-Modal Distillation
Won Ik Cho, Donghyun Kwak, Ji Won Yoon +1
Speech is one of the most effective means of communication and is full of information that helps the transmission of utterer's thoughts. However, mainly due to the cumbersome proce…
Speech Intention Understanding in a Head-final Language: A Disambiguation Utilizing Intonation-dependency
Won Ik Cho, Hyeon Seung Lee, Ji Won Yoon +2
For a large portion of real-life utterances, the intention cannot be solely decided by either their semantic or syntactic characteristics. Although not all the sociolinguistic and…