Employing Huber and TAP Losses to Improve Inter-SubNet in Speech Enhancement

Jeih-Weih Hung (), Pin-Chen Huang and Li-Yin Li
Additional contact information
Jeih-Weih Hung: Department of Electrical Engineering, National Chi Nan University, No. 301, University Rd., Puli Township, Nantou County 545, Taiwan
Pin-Chen Huang: Department of Electrical Engineering, National Chi Nan University, No. 301, University Rd., Puli Township, Nantou County 545, Taiwan
Li-Yin Li: Department of Electrical Engineering, National Chi Nan University, No. 301, University Rd., Puli Township, Nantou County 545, Taiwan

Future Internet, 2024, vol. 16, issue 10, 1-15

Abstract: In this study, improvements are made to Inter-SubNet, a state-of-the-art speech enhancement method. Inter-SubNet is a single-channel speech enhancement framework that enhances the sub-band spectral model by integrating global spectral information, such as cross-band relationships and patterns. Despite the success of Inter-SubNet, one crucial aspect probably overlooked by Inter-SubNet is the unequal perceptual weighting of different spectral regions by the human ear, as it employs MSE as its loss function. In addition, MSE loss has a potential convergence concern for model learning due to gradient explosion. Hence, we propose further enhancing Inter-SubNet by either integrating perceptual loss with MSE loss or modifying MSE loss directly in the learning process. Among various types of perceptual loss, we adopt the temporal acoustic parameter (TAP) loss, which provides detailed estimation for low-level acoustic descriptors, thereby offering a comprehensive evaluation of speech signal distortion. In addition, we leverage Huber loss, a combination of L1 and L2 (MSE) loss, to avoid the potential convergence issue for the training of Inter-SubNet. By the evaluation conducted on the VoiceBank-DEMAND database and task, we see that Inter-SubNet with the modified loss function reveals improvements in speech enhancement performance. Specifically, replacing MSE loss with Huber loss results in increases of 0.057 and 0.38 in WB-PESQ and SI-SDR metrics, respectively. Additionally, integrating TAP loss with MSE loss yields improvements of 0.115 and 0.196 in WB-PESQ and CSIG metrics.

Keywords: Inter-SubNet; Huber loss; TAP loss; speech enhancement (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/16/10/360/pdf (application/pdf)
https://www.mdpi.com/1999-5903/16/10/360/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:16:y:2024:i:10:p:360-:d:1492093

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().