Work

PicoAudio: Enabling Precise Temporal Controllability in Text-to-Audio Generation

Year: 2025

Type: conference-paper

Source: IEEE International Conference on Acoustics Speech and Signal Processing

DOI: 10.1109/icassp49660.2025.10890827

Authors: Zeyu Xie, Xuenan Xu, Zhizheng Wu, Mengyue Wu

Institutions: Shanghai Jiao Tong University, Shanghai Artificial Intelligence Laboratory

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

Funders: Shenzhen Research Institute of Big Data, Research and Development

OpenAlex ID: W4408352609

FWCI: 1.967

Cites: 24

Cited by: 2

Related to: 10