← Search

Seung Woo Yu

2 accepted papers

2024

Learning Contextualized Representation on Discrete Space Via Hierarchical Product Quantization

ICASSP 2024accepted

Self-supervised learning has recently demonstrated significant success in various speech processing applications. Recent studies report that pre-training with contextualized continuous targets plays a crucial role in fine-tuning for better speech downstream tasks. However, unlike the continuous targ…

Cited by 0SourceScholar
2023

Masked Token Similarity Transfer for Compressing Transformer-Based ASR Models

ICASSP 2023accepted

Recent self-supervised automatic speech recognition (ASR) models based on transformers are showing best performance, but their footprint is too large to be trained on low-resource environments or deployed to edge devices. Knowledge distillation (KD) can be employed to reduce the model size. However,…

Cited by 0SourceScholar