collaborators

5 papers

stat.ML2026

Federated LoRA Fine-Tuning for LLMs via Collaborative Alignment

Shuaida He, Liwen Chen, Long Feng

Low-rank adaptation (LoRA) has emerged as a powerful tool for parameter-efficient fine-tuning of large language models (LLMs). This paper studies LoRA under a federated learning se…

cs.LG2025

DiceHuBERT: Distilling HuBERT with a Self-Supervised Learning Objective

Hyung Gun Chi, Zakaria Aldeneh, Tatiana Likhomanenko +5

We introduce DiceHuBERT, a knowledge distillation framework for compressing HuBERT, a widely used self-supervised learning (SSL)-based speech foundation model. Unlike existing dist…

cs.CL2025

A Variational Framework for Improving Naturalness in Generative Spoken Language Models

Li-Wei Chen, Takuya Higuchi, Zakaria Aldeneh +2

The success of large language models in text processing has inspired their adaptation to speech modeling. However, since speech is continuous and complex, it is often discretized f…

eess.AS2025

Speaker-IPL: Unsupervised Learning of Speaker Characteristics with i-Vector based Pseudo-Labels

Zakaria Aldeneh, Takuya Higuchi, Jee-weon Jung +6

Iterative self-training, or iterative pseudo-labeling (IPL) -- using an improved model from the current iteration to provide pseudo-labels for the next iteration -- has proven to b…

eess.AS2025

Exploring Prediction Targets in Masked Pre-Training for Speech Foundation Models

Li-Wei Chen, Takuya Higuchi, He Bai +6

Speech foundation models, such as HuBERT and its variants, are pre-trained on large amounts of unlabeled speech data and then used for a range of downstream tasks. These models use…