Leveraging Laryngograph Data for Robust Voicing Detection in Speech

Author:

Yixuan Zhang, Heming Wang, DeLiang Wang

Keyword:

Electrical Engineering and Systems Science, Audio and Speech Processing, Audio and Speech Processing (eess.AS), Sound (cs.SD)

journal:

date:

2023-12-05 00:00:00

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 is based on a densely-connected convolutional recurrent neural network (DC-CRN), and trained on data with reference voicing decisions extracted from laryngograph data sets. 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.

PDF: Leveraging Laryngograph Data for Robust Voicing Detection in Speech.pdf