Data augmentation strategies for neural network F0 estimation

No Thumbnail Available

Access rights

openAccess
acceptedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2019-05-01

Major/Subject

Mcode

Degree programme

Language

en

Pages

5

Series

44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019; Brighton; United Kingdom; 12-17 May 2019 : Proceedings, pp. 6485 - 6489, IEEE International Conference on Acoustics Speech and Signal Processing

Abstract

This study explores various speech data augmentation methods for the task of noise-robust fundamental frequency (F0) estimation with neural networks. The explored augmentation strategies are split into additive noise and channel -based augmentation and into vocoder-based augmentation methods. In vocoder-based augmentation, a glottal vocoder is used to enhance the accuracy of ground truth F0 used for training of the neural network, as well as to expand the training data diversity in terms of F0 patterns and vocal tract lengths of the talkers. Evaluations on the PTDB-TUG corpus indicate that noise and channel augmentation can be used to greatly increase the noise robustness of trained models, and that vocoder-based ground truth enhancement further increases model performance. For smaller datasets, vocoder-based diversity augmentation can also be used to increase performance. The best-performing proposed method greatly outperformed the compared F0 estimation methods in terms of noise robustness.

Description

Keywords

Other note

Citation

Airaksinen, M, Juvela, L, Alku, P & Räsänen, O 2019, Data augmentation strategies for neural network F0 estimation. in 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019; Brighton; United Kingdom; 12-17 May 2019 : Proceedings., 8683041, IEEE International Conference on Acoustics Speech and Signal Processing, IEEE, pp. 6485 - 6489, IEEE International Conference on Acoustics, Speech, and Signal Processing, Brighton, United Kingdom, 12/05/2019. https://doi.org/10.1109/ICASSP.2019.8683041