{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/attention-back-end-for-automatic-speaker","title":"Attention Back-end for Automatic Speaker Verification with Multiple Enrollment Utterances","arxiv_id":"2104.01541","date":"2021-04-04","proceeding":null,"authors":["Chang Zeng","Xin Wang","Erica Cooper","Xiaoxiao Miao","Junichi Yamagishi"],"abstract":"Probabilistic linear discriminant analysis (PLDA) or cosine similarity have been widely used in traditional speaker verification systems as back-end techniques to measure pairwise similarities. To make better use of multiple enrollment utterances, we propose a novel attention back-end model, which can be used for both text-independent (TI) and text-dependent (TD) speaker verification, and employ scaled-dot self-attention and feed-forward self-attention networks as architectures that learn the intra-relationships of the enrollment utterances. In order to verify the proposed attention back-end, we conduct a series of experiments on CNCeleb and VoxCeleb datasets by combining it with several sate-of-the-art speaker encoders including TDNN and ResNet. Experimental results using multiple enrollment utterances on CNCeleb show that the proposed attention back-end model leads to lower EER and minDCF score than the PLDA and cosine similarity counterparts for each speaker encoder and an experiment on VoxCeleb indicate that our model can be used even for single enrollment case.","url_abs":"https://arxiv.org/abs/2104.01541v2","url_pdf":"https://arxiv.org/pdf/2104.01541v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"attention-back-end-for-automatic-speaker","repo_url":"https://github.com/nii-yamagishilab/Attention_Backend_for_ASV","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"speaker-verification","task_name":"Speaker Verification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speaker-verification-on-cn-celeb","task":"Speaker Verification","dataset":"CN-CELEB","model":"X-Vectors with Attention Backend","rank_in_archive_order":1,"of":2,"metrics":{"EER":"10.12"},"uses_additional_data":false},{"leaderboard":"/sota/speaker-verification-on-cn-celeb","task":"Speaker Verification","dataset":"CN-CELEB","model":"ResNet with Attention Backend","rank_in_archive_order":2,"of":2,"metrics":{"EER":"10.77"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.01541","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.01541"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nii-yamagishilab/Attention_Backend_for_ASV","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"74f233e6392c3134","entry":"mean","repo":"nii-yamagishilab/Attention_Backend_for_ASV","repo_kind":"official","path":"model.py","file_url":"https://github.com/nii-yamagishilab/Attention_Backend_for_ASV/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"74f233e6392c3134"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}