SoundBeam: Target Sound Extraction Conditioned on Sound-Class Labels and Enrollment Clues for Increased Performance and Continuous Learning-Reference-Cited by-同舟云学术

SoundBeam: Target Sound Extraction Conditioned on Sound-Class Labels and Enrollment Clues for Increased Performance and Continuous Learning

Author:

Delcroix Marc¹^ORCID,Vazquez Jorge Bennasar¹,Ochiai Tsubasa¹,Kinoshita Keisuke¹,Ohishi Yasunori¹^ORCID,Araki Shoko¹^ORCID

Affiliation:

1. NTT Corporation, Seikacho, Sorakugun, Kyoto, Tokyo, Japan

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Acoustics and Ultrasonics,Computer Science (miscellaneous),Computational Mathematics

Link

Reference62 articles.

1. The sound of pixels;zhao;Proc Eur Conf Comput Vis,0

3. Sound event detection in multisource environments using source separation;heittola;Proc First CHiME Workshop Mach Listening Multisource Environ,0

Cited by 9 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Improving Target Sound Extraction with Timestamp Knowledge Distillation;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

2. Audio Prompt Tuning for Universal Sound Separation;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

3. Online Target Sound Extraction with Knowledge Distillation from Partially Non-Causal Teacher;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

4. Human Speech Extraction from Composite Audio Signal in Real-Time using Deep Neural Network;2024 11th International Conference on Signal Processing and Integrated Networks (SPIN);2024-03-21