AES E-Library

H. Yang, Y. Lin, and A. Su, "A Novel Source Filter Model using LSTM/K-means Machine Learning Methods for the Synthesis of Bowed-String Musical Instruments," Paper 10368, (2020 May.). doi: H. Yang, Y. Lin, and A. Su, "A Novel Source Filter Model using LSTM/K-means Machine Learning Methods for the Synthesis of Bowed-String Musical Instruments," Paper 10368, (2020 May.). doi:
Abstract: 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.

@article{yang2020a,
author={yang, hung-chih and lin, yiju and su, alvin},
journal={journal of the audio engineering society},
title={a novel source filter model using lstm/k-means machine learning methods for the synthesis of bowed-string musical instruments},
year={2020},
volume={},
number={},
pages={},
doi={},
month={may},} @article{yang2020a,
author={yang, hung-chih and lin, yiju and su, alvin},
journal={journal of the audio engineering society},
title={a novel source filter model using lstm/k-means machine learning methods for the synthesis of bowed-string musical instruments},
year={2020},
volume={},
number={},
pages={},
doi={},
month={may},
abstract={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.},}

TY - paper
TI - A Novel Source Filter Model using LSTM/K-means Machine Learning Methods for the Synthesis of Bowed-String Musical Instruments
SP - EP -
AU - Yang, Hung-Chih
AU - Lin, Yiju
AU - Su, Alvin
PY - 2020
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2020 TY - paper
TI - A Novel Source Filter Model using LSTM/K-means Machine Learning Methods for the Synthesis of Bowed-String Musical Instruments
SP - EP -
AU - Yang, Hung-Chih
AU - Lin, Yiju
AU - Su, Alvin
PY - 2020
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2020
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.