Multi-branch feature aggregation based on multiple weighting for speaker verification. (January 2023)

• Record Type: Journal Article
• Authors: Qin, Youcai; Ren, Qinghua; Mao, Qirong; Chen, Jingjing
• Is Part Of: Computer speech & language. Volume 77(2023)
• Publication Date: 2023-01
• Subjects: Speaker verification -- Multi-branch feature aggregation -- Point attention -- Channel attention; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2022.101426
• Languages: English
• ISSNs: 0885-2308

Abstract

Abstract: Multi-branch feature aggregation has recently been introduced and shows superior performance for speaker verification. It is often implemented via simple operations, such as element-wise addition or concatenation, but this might lead to suboptimal results. In this paper, we propose a novel multi-branch feature aggregation method based on multiple weighting (MBFA-MW), which adaptively learns attention weights for each branch to extract discriminative information that is beneficial to speaker verification. This method contains two weighting strategies, point attention and channel attention. Point attention learns a point-wise weight to emphasize salient local information from the time–frequency domain, and channel attention learns a channel-wise weight to enhance the correlation between the key information and the channel from the frequency domain. Combining the time–frequency domain and the frequency domain, the two strategies complement each other and extract informational features from multiple branch. In addition, we compared different multi-branch feature aggregation methods in the same environment. Experimental results on the datasets of Voxceleb and Cnceleb show the proposed method achieves performance improvements compared to other multi-branch feature aggregation methods and other mainstream methods. Highlights: Multi-branch feature aggregation method based on multiple weighting learns attention weights for each branch. Point attention and channel attention aggregate multi-branch features. These two strategies complement each other and extract informational features.