4 papers
Triage knowledge distillation for speaker verification
Ju-ho Kim, Youngmoon Jung, Joon-Young Yang +3
Deploying speaker verification on resource-constrained devices remains challenging due to the computational cost of high-capacity models; knowledge distillation (KD) offers a remed…
DAME: Duration-Aware Matryoshka Embedding for Duration-Robust Speaker Verification
Youngmoon Jung, Joon-Young Yang, Ju-ho Kim +3
Short-utterance speaker verification remains challenging due to limited speaker-discriminative cues in short speech segments. While existing methods focus on enhancing speaker enco…
FedSODA: Federated Fine-tuning of LLMs via Similarity Group Pruning and Orchestrated Distillation Alignment
Manning Zhu, Songtao Guo, Pengzhan Zhou +3
Federated fine-tuning (FFT) of large language models (LLMs) has recently emerged as a promising solution to enable domain-specific adaptation while preserving data privacy. Despite…
Adversarial Deep Metric Learning for Cross-Modal Audio-Text Alignment in Open-Vocabulary Keyword Spotting
Youngmoon Jung, Yong-Hyeok Lee, Myunghun Jung +3
For text enrollment-based open-vocabulary keyword spotting (KWS), acoustic and text embeddings are typically compared at either the phoneme or utterance level. To facilitate this,…