← Search

Stevan Rudinac

2 accepted papers

2026

A Novel Automatic Framework for Speaker Drift Detection in Synthesized Speech

ICASSP 2026poster

Recent diffusion-based text-to-speech (TTS) models achieve high naturalness and expressiveness, yet often suffer from speaker drift, a subtle, gradual shift in perceived speaker identity within a single utterance. This underexplored phenomenon undermines the coherence of synthetic speech, especially…

Cited by 0SourcePDFScholar
2025

Gradient Weight-normalized Low-rank Projection for Efficient LLM Training

AAAI 2025technical

Large Language Models (LLMs) have shown remarkable performance across various tasks, but the escalating demands on computational resources pose significant challenges, particularly in the extensive utilization of full fine-tuning for downstream tasks. To address this, parameter-efficient fine-tuning…