A novel source filter model using LSTM/K-means machine learning methods for the synthesis of bowed-string musical instruments

Hung Chih Yang, Yiju Lin, Alvin Su

Research output: Contribution to conferencePaperpeer-review

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.

Original languageEnglish
Publication statusPublished - 2020
Event148th Audio Engineering Society International Convention 2020 - Vienna, Virtual, Online, Austria
Duration: 2020 Jun 22020 Jun 5

Conference

Conference148th Audio Engineering Society International Convention 2020
CountryAustria
CityVienna, Virtual, Online
Period20-06-0220-06-05

All Science Journal Classification (ASJC) codes

  • Modelling and Simulation
  • Acoustics and Ultrasonics

Fingerprint Dive into the research topics of 'A novel source filter model using LSTM/K-means machine learning methods for the synthesis of bowed-string musical instruments'. Together they form a unique fingerprint.

Cite this