Efficient synthesis of violin sounds using a bilstm network based source filter model

Yi Ren Dai, Hung Chih Yang, Alvin W.Y. Su

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

The dynamic changes in playing skills generated from bow-string interaction make synthesizing bowed string instrument sounds a difficult task. Recently, a source filter model incorporating the LSTM predictor and the granular wavetables gives encouraging results. However, the prediction error is still large and the model hasn't caught the nuance caused by the constantly changing characteristics of a playing violin. In this paper, the granular wavetable is represented of DCT coefficients and a new training strategy is proposed to reduce the predictor error. In addition, we analyze the difference between the original violin tone and the corresponding synthesis tone. A random pitch perturbation and a DCT coefficient shaping method are proposed to imitate the changing characteristics since results sound regular.

Original languageEnglish
Title of host publication150th Audio Engineering Society Convention, AES 2021
PublisherAudio Engineering Society
ISBN (Electronic)9781713830672
Publication statusPublished - 2021
Event150th Audio Engineering Society Convention, AES 2021 - Virtual, Online
Duration: 2021 May 252021 May 28

Publication series

Name150th Audio Engineering Society Convention, AES 2021

Conference

Conference150th Audio Engineering Society Convention, AES 2021
CityVirtual, Online
Period21-05-2521-05-28

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Modelling and Simulation
  • Acoustics and Ultrasonics

Fingerprint

Dive into the research topics of 'Efficient synthesis of violin sounds using a bilstm network based source filter model'. Together they form a unique fingerprint.

Cite this