A Novel Source Filter Model using LSTM/K-means Machine Learning Methods for the Synthesis of Bowed-String Musical Instruments

Yang HC, Lin Y, Su A. A Novel Source Filter Model using LSTM/K-means Machine Learning Methods for the Synthesis of Bowed-String Musical Instruments. In: AES Convention 148. Audio Engineering Society; 2020. Paper 10368. Available from: https://aes.org/publications/elibrary-page/?id=20785

@inproceedings{Yang2020_20785,
  author = {Yang, Hung-Chih and Lin, Yiju and Su, Alvin},
  title = {{A Novel Source Filter Model using LSTM/K-means Machine Learning Methods for the Synthesis of Bowed-String Musical Instruments}},
  booktitle = {AES Convention 148},
  note = {Paper 10368},
  year = {2020},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=20785}
}

TY  - CPAPER
TI  - A Novel Source Filter Model using LSTM/K-means Machine Learning Methods for the Synthesis of Bowed-String Musical Instruments
AU  - Yang, Hung-Chih
AU  - Lin, Yiju
AU  - Su, Alvin
T2  - AES Convention 148
M1  - Paper 10368
PY  - 2020
DA  - 2020/05/06
UR  - https://aes.org/publications/elibrary-page/?id=20785
PB  - Audio Engineering Society
LA  - en
AB  - Synthesis of realistic bowed-string instrument sound is a difficult task due to the diversified playing techniques and the ever-changing dynamics which cause rapidly varying characteristics. The noise part closely related to the dynamic bow-string interaction is also regarded as an indispensable part of the musical sound. Neural networks have been applied to sound synthesis for years. In this paper, a source filter synthesis model combined with a Long-Short-Term-Memory (LSTM) RNN predictor and a self-organized granular wavetable is proposed. The synthesis sound can be close to the recorded tones of a target bowed-string instrument. The timbre and the noise are both well preserved. Changes of pitch and dynamics can be easily achieved in real time, too.
ER  -