Papers › FDN: Finite Difference Network with Hierarchical Convolutional Features for...

FDN: Finite Difference Network with Hierarchical Convolutional Features for Text-independent Speaker Verification

18 Aug 2021arXiv:2108.07974archive 2025-07-28

Jin Li, Nan Yan, Lan Wang

In recent years, using raw waveforms as input for deep networks has been widely explored for the speaker verification system. For example, RawNet and RawNet2 extracted speaker's feature embeddings from waveforms automatically for recognizing their voice, which can vastly reduce the front-end computation and obtain state-of-the-art performance. However, these models do not consider the speaker's high-level behavioral features, such as intonation, indicating each speaker's universal style, rhythm, \textit{etc}. This paper presents a novel network that can handle the intonation information by computing the finite difference of different speakers' utterance variations. Furthermore, a hierarchical way is also designed to enhance the intonation property from coarse to fine to improve the system accuracy. The high-level intonation features are then fused with the low-level embedding features. Experimental results on official VoxCeleb1 test data, VoxCeleb1-E, and VoxCeleb-H protocols show our method outperforms and robustness existing state-of-the-art systems. To facilitate further research, code is available at https://github.com/happyjin/FDN

PaperPDFCode

Code

happyjin/fdn officialmentioned in paper report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

RhythmSpeaker VerificationText-Independent Speaker Verification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

GRUSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections