Variational Autoencoder for Personalized Pathological Speech Enhancement
원문 초록
The generalizability of speech enhancement (SE) models across speaker conditions remains largely unexplored, despite its critical importance for broader applicability. This paper investigates the performance of the hybrid variational autoencoder (VAE)-non-negative matrix factorization (NMF) model for SE, focusing primarily on its generalizability to pathological speakers with Parkinson's disease. We show that VAE models trained on large neurotypical datasets perform poorly on pathological speech. While fine-tuning these pre-trained models with pathological speech improves performance, a performance gap remains between neurotypical and pathological speakers. To address this gap, we propose using personalized SE models derived from fine-tuning pre-trained models with only a few seconds of clean data from each speaker. Our results demonstrate that personalized models considerably enhance performance for all speakers, achieving comparable results for both neurotypical and pathological speakers.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Robust One-step Speech Enhancement via Consistency Distillation
MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement
Efficient Speech Enhancement via Embeddings from Pre-trained Generative Audioencoders
Lessons Learned from the URGENT 2024 Speech Enhancement Challenge
FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching
Training-Free Multi-Step Audio Source Separation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.