Synthesis of Wind Instruments using BiLSTM and Gaussian Mixture Model

Lee YW, Yang HC, Su AWY. Synthesis of Wind Instruments using BiLSTM and Gaussian Mixture Model. In: AES Convention 152. Audio Engineering Society; 2022. Paper 10585. Available from: https://aes.org/publications/elibrary-page/?id=21698

@inproceedings{Lee2022_21698,
  author = {Lee, Yu-Wen and Yang, Hung-Chih and Su, Alvin W.Y.},
  title = {{Synthesis of Wind Instruments using BiLSTM and Gaussian Mixture Model}},
  booktitle = {AES Convention 152},
  note = {Paper 10585},
  year = {2022},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=21698}
}

TY  - CPAPER
TI  - Synthesis of Wind Instruments using BiLSTM and Gaussian Mixture Model
AU  - Lee, Yu-Wen
AU  - Yang, Hung-Chih
AU  - Su, Alvin W.Y.
T2  - AES Convention 152
M1  - Paper 10585
PY  - 2022
DA  - 2022/05/06
UR  - https://aes.org/publications/elibrary-page/?id=21698
PB  - Audio Engineering Society
LA  - en
AB  - In this work, a source filter model incorporating the BiLSTM and the Gaussian Mixture Model (GMM) for the synthesis of woodwind instruments is presented. Magnitude-modulated and pitch-synchronous impulse signals are the sources. The filter is converted by the correspondent DCT coefficients, divided into the low-frequency and high-frequency parts. The high-frequency part is modeled by the GMM. The BiLSTM recurrent networks are used to predict the low-frequency part DCT coefficients of the filters. The proposed method can synthesize realistic and expressive tones and breath noise as well when compared to the conventional Digital Waveguide Filter-based method.
ER  -