ملخص
Synthesizers are widely used electronic musical instruments. Given an input sound, inferring the underlying synthesizer's parameters to reproduce it is a difficult task known as sound-matching. In this work, we tackle the problem of automatic sound matching, which is otherwise performed manually by professional audio experts. The novelty of our work stems from the introduction of a novel differentiable synthesizer-proxy that enables gradient-based optimization by comparing the input and reproduced audio signals. Additionally, we introduce a novel self-supervised finetuning mechanism that further refines the prediction at inference time. Both contributions lead to state-of-the-art results, outperforming previous methods across various metrics. Our code is available at: https://github.com/inversynth/ InverSynth2.
اللغة الأصلية | الإنجليزيّة |
---|---|
عنوان منشور المضيف | 24th International Society for Music Information Retrieval Conference, ISMIR 2023 - Proceedings |
المحررون | Augusto Sarti, Fabio Antonacci, Mark Sandler, Paolo Bestagini, Simon Dixon, Beici Liang, Gael Richard, Johan Pauwels |
ناشر | International Society for Music Information Retrieval |
الصفحات | 642-648 |
عدد الصفحات | 7 |
رقم المعيار الدولي للكتب (الإلكتروني) | 9781732729933 |
حالة النشر | نُشِر - 2023 |
الحدث | 24th International Society for Music Information Retrieval Conference, ISMIR 2023 - Milan, إيطاليا المدة: ٥ نوفمبر ٢٠٢٣ → ٩ نوفمبر ٢٠٢٣ |
سلسلة المنشورات
الاسم | 24th International Society for Music Information Retrieval Conference, ISMIR 2023 - Proceedings |
---|
!!Conference
!!Conference | 24th International Society for Music Information Retrieval Conference, ISMIR 2023 |
---|---|
الدولة/الإقليم | إيطاليا |
المدينة | Milan |
المدة | ٥/١١/٢٣ → ٩/١١/٢٣ |
ملاحظة ببليوغرافية
Publisher Copyright:© Barkan et al.