Work

SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning

Year: 2025

Type: conference-paper

Source: IEEE International Conference on Acoustics Speech and Signal Processing

DOI: 10.1109/icassp49660.2025.10889205

Authors: Chien-Yu Huang, Min-Han Shih, Ke-Han Lu, Chi-Yuan Hsiao, Hung-Yi Lee

Institutions: National Taiwan University, University of Southern California

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

OpenAlex ID: W4408353373

FWCI: 1.977

Cites: 26

Cited by: 2

Related to: 10