Work

DSINet: Towards Real-Time Target Speaker Extraction with Dynamic Speaker Information Fusion

Year: 2025

Type: conference-paper

Source: IEEE International Conference on Acoustics Speech and Signal Processing

DOI: 10.1109/icassp49660.2025.10887817

Authors: Fengyuan Hao, Andong Li, Xiaodong Li, Chengshi Zheng

Institutions: Chinese Academy of Sciences, Institute of Acoustics

Language: English

Topic: Speech and Audio Processing

Subfield: Signal Processing

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

OpenAlex ID: W4408353733

FWCI: 2.931

Cites: 35

Cited by: 3

Related to: 10