View in EDS

Leveraging laryngograph data for robust voicing detection in speech.

Saved in:
Bibliographic Details
Title: Leveraging laryngograph data for robust voicing detection in speech.
Authors: Zhang, Yixuan1 (AUTHOR) zhang.7388@osu.edu, Wang, Heming1 (AUTHOR) wang.11401@osu.edu, Wang, DeLiang1,2 (AUTHOR) dwang@cse.ohio-state.edu
Source: Journal of the Acoustical Society of America. Nov2024, Vol. 156 Issue 5, p3502-3513. 12p.
Subjects: Machine learning, Signal processing, Source code, Data recorders & recording, Generalization, Deep learning
Abstract: Accurately detecting voiced intervals in speech signals is a critical step in pitch tracking and has numerous applications. While conventional signal processing methods and deep learning algorithms have been proposed for this task, their need to fine-tune threshold parameters for different datasets and limited generalization restrict their utility in real-world applications. To address these challenges, this study proposes a supervised voicing detection model that leverages recorded laryngograph data. The model, adapted from a recently developed CrossNet architecture, is trained using reference voicing decisions derived from laryngograph datasets. Pretraining is also investigated to improve the generalization ability of the model. The proposed model produces robust voicing detection results, outperforming other strong baseline methods, and generalizes well to unseen datasets. The source code of the proposed model with pretraining is provided along with the list of used laryngograph datasets to facilitate further research in this area. [ABSTRACT FROM AUTHOR]
Copyright of Journal of the Acoustical Society of America is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:Accurately detecting voiced intervals in speech signals is a critical step in pitch tracking and has numerous applications. While conventional signal processing methods and deep learning algorithms have been proposed for this task, their need to fine-tune threshold parameters for different datasets and limited generalization restrict their utility in real-world applications. To address these challenges, this study proposes a supervised voicing detection model that leverages recorded laryngograph data. The model, adapted from a recently developed CrossNet architecture, is trained using reference voicing decisions derived from laryngograph datasets. Pretraining is also investigated to improve the generalization ability of the model. The proposed model produces robust voicing detection results, outperforming other strong baseline methods, and generalizes well to unseen datasets. The source code of the proposed model with pretraining is provided along with the list of used laryngograph datasets to facilitate further research in this area. [ABSTRACT FROM AUTHOR]
ISSN:00014966
DOI:10.1121/10.0034445