Paper: | AASP-L6.3 |
Session: | Music Signal Analysis, Processing and Synthesis |
Session Time: | Thursday, May 16, 08:00 - 10:00 |
Presentation Time: | Thursday, May 16, 08:40 - 09:00 |
Presentation: |
Lecture
|
Topic: |
Audio and Acoustic Signal Processing: Music Signal Analysis, Processing and Synthesis |
Paper Title: |
AUTOMATIC SINGING TRANSCRIPTION BASED ON ENCODER-DECODER RECURRENT NEURAL NETWORKS WITH A WEAKLY-SUPERVISED ATTENTION MECHANISM |
Authors: |
Ryo Nishikimi; Kyoto University | | |
| Eita Nakamura; Kyoto University | | |
| Satoru Fukayama; National Institute of Advanced Industrial Science and Technology (AIST) | | |
| Masataka Goto; National Institute of Advanced Industrial Science and Technology (AIST) | | |
| Kazuyoshi Yoshii; Kyoto University | | |