{"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/utterance-level-aggregation-for-speaker","title":"Utterance-level Aggregation For Speaker Recognition In The Wild","arxiv_id":"1902.10107","date":"2019-02-26","proceeding":null,"authors":["Weidi Xie","Arsha Nagrani","Joon Son Chung","Andrew Zisserman"],"abstract":"The objective of this paper is speaker recognition \"in the wild\"-where utterances may be of variable length and also contain irrelevant signals. Crucial elements in the design of deep networks for this task are the type of trunk (frame level) network, and the method of temporal aggregation. We propose a powerful speaker recognition deep network, using a \"thin-ResNet\" trunk architecture, and a dictionary-based NetVLAD or GhostVLAD layer to aggregate features across time, that can be trained end-to-end. We show that our network achieves state of the art performance by a significant margin on the VoxCeleb1 test set for speaker recognition, whilst requiring fewer parameters than previous methods. We also investigate the effect of utterance length on performance, and conclude that for \"in the wild\" data, a longer length is beneficial.","url_abs":"https://arxiv.org/abs/1902.10107v2","url_pdf":"https://arxiv.org/pdf/1902.10107v2.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":"utterance-level-aggregation-for-speaker","repo_url":"https://github.com/WeidiXie/VGG-Speaker-Recognition","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"utterance-level-aggregation-for-speaker","repo_url":"https://github.com/Livefull/SphereDiar","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"utterance-level-aggregation-for-speaker","repo_url":"https://github.com/jkchen79/netvlad-in-speech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"utterance-level-aggregation-for-speaker","repo_url":"https://github.com/khassanoff/Speaker_Verification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"utterance-level-aggregation-for-speaker","repo_url":"https://github.com/mavceleb/mavceleb_baseline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"utterance-level-aggregation-for-speaker","repo_url":"https://github.com/msaadsaeed/FOP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"utterance-level-aggregation-for-speaker","repo_url":"https://github.com/msaadsaeed/sbnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"utterance-level-aggregation-for-speaker","repo_url":"https://github.com/taylorlu/Speaker-Diarization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"utterance-level-aggregation-for-speaker","repo_url":"https://github.com/jackaduma/SpeakerRecognition-ResNet-GhostVLAD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"utterance-level-aggregation-for-speaker","repo_url":"https://github.com/zabir-nabil/tf2-speaker-recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"speaker-recognition","task_name":"Speaker Recognition"},{"task_slug":"text-independent-speaker-verification","task_name":"Text-Independent Speaker Verification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1902.10107","atlas_url":"https://app.syntology.ai/?focus=1902.10107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.10107"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/khassanoff/Speaker_Verification","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/WeidiXie/VGG-Speaker-Recognition","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mavceleb/mavceleb_baseline","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zabir-nabil/tf2-speaker-recognition","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jkchen79/netvlad-in-speech","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jackaduma/SpeakerRecognition-ResNet-GhostVLAD","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/msaadsaeed/FOP","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Livefull/SphereDiar","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/msaadsaeed/sbnet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/taylorlu/Speaker-Diarization","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":10,"ran_fixture":3,"unverified":10},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":22,"ran":13,"repositories":3}},"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":1,"samples":[{"code_sha256_prefix":"1169b496229daf10","entry":"append2dict","repo":"taylorlu/Speaker-Diarization","repo_kind":"listed","path":"speakerDiarization.py","file_url":"https://github.com/taylorlu/Speaker-Diarization/blob/HEAD/speakerDiarization.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1169b496229daf10"}},{"code_sha256_prefix":"fb447405850e532c","entry":"arrangeResult","repo":"taylorlu/Speaker-Diarization","repo_kind":"listed","path":"speakerDiarization.py","file_url":"https://github.com/taylorlu/Speaker-Diarization/blob/HEAD/speakerDiarization.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fb447405850e532c"}},{"code_sha256_prefix":"6a0b276952bdc83b","entry":"compute_sequence_match_accuracy","repo":"taylorlu/Speaker-Diarization","repo_kind":"listed","path":"uisrnn/evals.py","file_url":"https://github.com/taylorlu/Speaker-Diarization/blob/HEAD/uisrnn/evals.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6a0b276952bdc83b"}},{"code_sha256_prefix":"17437f2725b26ae5","entry":"conv_block","repo":"khassanoff/Speaker_Verification","repo_kind":"listed","path":"speech_embedder_net.py","file_url":"https://github.com/khassanoff/Speaker_Verification/blob/HEAD/speech_embedder_net.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"17437f2725b26ae5"}},{"code_sha256_prefix":"8f290b6646c54127","entry":"genMap","repo":"taylorlu/Speaker-Diarization","repo_kind":"listed","path":"speakerDiarization.py","file_url":"https://github.com/taylorlu/Speaker-Diarization/blob/HEAD/speakerDiarization.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8f290b6646c54127"}},{"code_sha256_prefix":"d60a5212d267941e","entry":"get_list_inverse_index","repo":"taylorlu/Speaker-Diarization","repo_kind":"listed","path":"uisrnn/evals.py","file_url":"https://github.com/taylorlu/Speaker-Diarization/blob/HEAD/uisrnn/evals.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d60a5212d267941e"}},{"code_sha256_prefix":"499126ea0fb9fe0a","entry":"get_vggface2_imglist","repo":"taylorlu/Speaker-Diarization","repo_kind":"listed","path":"ghostvlad/toolkits.py","file_url":"https://github.com/taylorlu/Speaker-Diarization/blob/HEAD/ghostvlad/toolkits.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"499126ea0fb9fe0a"}},{"code_sha256_prefix":"ba8e52a6186dbe68","entry":"identity_block","repo":"khassanoff/Speaker_Verification","repo_kind":"listed","path":"speech_embedder_net.py","file_url":"https://github.com/khassanoff/Speaker_Verification/blob/HEAD/speech_embedder_net.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ba8e52a6186dbe68"}},{"code_sha256_prefix":"23bad4461ca9d747","entry":"regularization_loss","repo":"taylorlu/Speaker-Diarization","repo_kind":"listed","path":"uisrnn/loss_func.py","file_url":"https://github.com/taylorlu/Speaker-Diarization/blob/HEAD/uisrnn/loss_func.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"23bad4461ca9d747"}},{"code_sha256_prefix":"35a2331b27bb8ddd","entry":"set_mp","repo":"taylorlu/Speaker-Diarization","repo_kind":"listed","path":"ghostvlad/toolkits.py","file_url":"https://github.com/taylorlu/Speaker-Diarization/blob/HEAD/ghostvlad/toolkits.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"35a2331b27bb8ddd"}},{"code_sha256_prefix":"460d697a4c9ca801","entry":"shortcut","repo":"khassanoff/Speaker_Verification","repo_kind":"listed","path":"speech_embedder_net.py","file_url":"https://github.com/khassanoff/Speaker_Verification/blob/HEAD/speech_embedder_net.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"460d697a4c9ca801"}},{"code_sha256_prefix":"cd29a997e2d51ed2","entry":"sigma2_prior_loss","repo":"taylorlu/Speaker-Diarization","repo_kind":"listed","path":"uisrnn/loss_func.py","file_url":"https://github.com/taylorlu/Speaker-Diarization/blob/HEAD/uisrnn/loss_func.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cd29a997e2d51ed2"}},{"code_sha256_prefix":"720fd03354ee7041","entry":"weighted_mse_loss","repo":"taylorlu/Speaker-Diarization","repo_kind":"listed","path":"uisrnn/loss_func.py","file_url":"https://github.com/taylorlu/Speaker-Diarization/blob/HEAD/uisrnn/loss_func.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"720fd03354ee7041"}},{"code_sha256_prefix":"6518429bdea14293","entry":"amsoftmax_loss","repo":"taylorlu/Speaker-Diarization","repo_kind":"listed","path":"ghostvlad/model.py","file_url":"https://github.com/taylorlu/Speaker-Diarization/blob/HEAD/ghostvlad/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6518429bdea14293"}},{"code_sha256_prefix":"bf118be3e0b08f1e","entry":"amsoftmax_loss","repo":"zabir-nabil/tf2-speaker-recognition","repo_kind":"listed","path":"model.py","file_url":"https://github.com/zabir-nabil/tf2-speaker-recognition/blob/HEAD/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bf118be3e0b08f1e"}},{"code_sha256_prefix":"ba579e59da9e4e3f","entry":"conv_block_2D","repo":"taylorlu/Speaker-Diarization","repo_kind":"listed","path":"ghostvlad/backbone.py","file_url":"https://github.com/taylorlu/Speaker-Diarization/blob/HEAD/ghostvlad/backbone.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ba579e59da9e4e3f"}},{"code_sha256_prefix":"61a6cf5e47d41f7e","entry":"conv_block_2D","repo":"zabir-nabil/tf2-speaker-recognition","repo_kind":"listed","path":"backbone.py","file_url":"https://github.com/zabir-nabil/tf2-speaker-recognition/blob/HEAD/backbone.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"61a6cf5e47d41f7e"}},{"code_sha256_prefix":"43330ce78044b94f","entry":"identity_block_2D","repo":"taylorlu/Speaker-Diarization","repo_kind":"listed","path":"ghostvlad/backbone.py","file_url":"https://github.com/taylorlu/Speaker-Diarization/blob/HEAD/ghostvlad/backbone.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"43330ce78044b94f"}},{"code_sha256_prefix":"c81b6fabb296ede5","entry":"identity_block_2D","repo":"zabir-nabil/tf2-speaker-recognition","repo_kind":"listed","path":"backbone.py","file_url":"https://github.com/zabir-nabil/tf2-speaker-recognition/blob/HEAD/backbone.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c81b6fabb296ede5"}},{"code_sha256_prefix":"d560100c1112033e","entry":"initialize_GPU","repo":"taylorlu/Speaker-Diarization","repo_kind":"listed","path":"ghostvlad/toolkits.py","file_url":"https://github.com/taylorlu/Speaker-Diarization/blob/HEAD/ghostvlad/toolkits.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d560100c1112033e"}},{"code_sha256_prefix":"ea4dfc945d7a3187","entry":"resnet_2D_v1","repo":"taylorlu/Speaker-Diarization","repo_kind":"listed","path":"ghostvlad/backbone.py","file_url":"https://github.com/taylorlu/Speaker-Diarization/blob/HEAD/ghostvlad/backbone.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ea4dfc945d7a3187"}},{"code_sha256_prefix":"4b2de008af319598","entry":"resnet_2D_v1","repo":"zabir-nabil/tf2-speaker-recognition","repo_kind":"listed","path":"backbone.py","file_url":"https://github.com/zabir-nabil/tf2-speaker-recognition/blob/HEAD/backbone.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4b2de008af319598"}},{"code_sha256_prefix":"f8272c80971e5978","entry":"set_result_path","repo":"WeidiXie/VGG-Speaker-Recognition","repo_kind":"official","path":"src/predict.py","file_url":"https://github.com/WeidiXie/VGG-Speaker-Recognition/blob/HEAD/src/predict.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f8272c80971e5978"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}