DATA AUGMENTATION STRATEGIES FOR NEURAL NETWORK F0 ESTIMATION

Show full item record



Permalink

http://hdl.handle.net/10138/306497

Citation

Airaksinen , M , Juvela , L , Alku , P & Rasanen , O 2019 , DATA AUGMENTATION STRATEGIES FOR NEURAL NETWORK F0 ESTIMATION . in 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) . International Conference on Acoustics Speech and Signal Processing ICASSP , IEEE , pp. 6485-6489 , 44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , Brighton , 12/05/2019 . https://doi.org/10.1109/icassp.2019.8683041

Title: DATA AUGMENTATION STRATEGIES FOR NEURAL NETWORK F0 ESTIMATION
Author: Airaksinen, Manu; Juvela, Lauri; Alku, Paavo; Rasanen, Okko
Contributor: University of Helsinki, Department of Neurosciences
Publisher: IEEE
Date: 2019
Language: eng
Number of pages: 5
Belongs to series: 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
Belongs to series: International Conference on Acoustics Speech and Signal Processing ICASSP
ISBN: 978-1-4799-8131-1
URI: http://hdl.handle.net/10138/306497
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.
Subject: Speech analysis
F0 estimation
noise robustness
data augmentation
deep learning
SPEECH RECOGNITION
3124 Neurology and psychiatry
6121 Languages
Rights:


Files in this item

Total number of downloads: Loading...

Files Size Format View
untitled.pdf 263.6Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record