{"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/deep-speaker-an-end-to-end-neural-speaker","title":"Deep Speaker: an End-to-End Neural Speaker Embedding System","arxiv_id":"1705.02304","date":"2017-05-05","proceeding":null,"authors":["Chao Li","Xiaokong Ma","Bing Jiang","Xiangang Li","Xuewei Zhang","Xiao Liu","Ying Cao","Ajay Kannan","Zhenyao Zhu"],"abstract":"We present Deep Speaker, a neural speaker embedding system that maps\nutterances to a hypersphere where speaker similarity is measured by cosine\nsimilarity. The embeddings generated by Deep Speaker can be used for many\ntasks, including speaker identification, verification, and clustering. We\nexperiment with ResCNN and GRU architectures to extract the acoustic features,\nthen mean pool to produce utterance-level speaker embeddings, and train using\ntriplet loss based on cosine similarity. Experiments on three distinct datasets\nsuggest that Deep Speaker outperforms a DNN-based i-vector baseline. For\nexample, Deep Speaker reduces the verification equal error rate by 50%\n(relatively) and improves the identification accuracy by 60% (relatively) on a\ntext-independent dataset. We also present results that suggest adapting from a\nmodel trained with Mandarin can improve accuracy for English speaker\nrecognition.","url_abs":"http://arxiv.org/abs/1705.02304v1","url_pdf":"http://arxiv.org/pdf/1705.02304v1.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":"deep-speaker-an-end-to-end-neural-speaker","repo_url":"https://github.com/Aurora11111/speaker-recognition-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"deep-speaker-an-end-to-end-neural-speaker","repo_url":"https://github.com/Aurora11111/voiceprint","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"deep-speaker-an-end-to-end-neural-speaker","repo_url":"https://github.com/MainRo/deep-speaker","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-speaker-an-end-to-end-neural-speaker","repo_url":"https://github.com/Siomarry/Audio_recognition_","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"deep-speaker-an-end-to-end-neural-speaker","repo_url":"https://github.com/Siomarry/Siomarry","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"deep-speaker-an-end-to-end-neural-speaker","repo_url":"https://github.com/Walleclipse/Deep-Speaker_speaker-recognition-system","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"deep-speaker-an-end-to-end-neural-speaker","repo_url":"https://github.com/Walleclipse/Deep_Speaker-speaker_recognition_system","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"deep-speaker-an-end-to-end-neural-speaker","repo_url":"https://github.com/andabi/voice-vector","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"deep-speaker-an-end-to-end-neural-speaker","repo_url":"https://github.com/dodoproptit99/deep-speaker","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"deep-speaker-an-end-to-end-neural-speaker","repo_url":"https://github.com/philipperemy/deep-speaker","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"deep-speaker-an-end-to-end-neural-speaker","repo_url":"https://github.com/prajual/Deep_Speaker","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"deep-speaker-an-end-to-end-neural-speaker","repo_url":"https://github.com/qqueing/DeepSpeaker-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-speaker-an-end-to-end-neural-speaker","repo_url":"https://github.com/vohoaiviet/voice-vector","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"deep-speaker-an-end-to-end-neural-speaker","repo_url":"https://github.com/wangleiai/dVectorSpeakerRecognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"deep-speaker-an-end-to-end-neural-speaker","repo_url":"https://github.com/zhudu/LOL-Recongnition-by-Deep-Speaker","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"speaker-identification","task_name":"Speaker Identification"},{"task_slug":"speaker-recognition","task_name":"Speaker Recognition"},{"task_slug":null,"task_name":"Triplet"}],"methods":[{"method_slug":"gru","method_name":"GRU"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1705.02304","atlas_url":"https://app.syntology.ai/?focus=1705.02304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.02304"}},"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/prajual/Deep_Speaker","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Aurora11111/voiceprint","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Aurora11111/speaker-recognition-pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/philipperemy/deep-speaker","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhudu/LOL-Recongnition-by-Deep-Speaker","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vohoaiviet/voice-vector","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dodoproptit99/deep-speaker","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MainRo/deep-speaker","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Walleclipse/Deep_Speaker-speaker_recognition_system","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Siomarry/Audio_recognition_","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Walleclipse/Deep-Speaker_speaker-recognition-system","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qqueing/DeepSpeaker-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/andabi/voice-vector","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Siomarry/Siomarry","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wangleiai/dVectorSpeakerRecognition","reach":null}],"summary":{"ran_honours":2,"ran_draft_wrong":4,"ran_fixture":1,"unverified":2},"by_repo_kind":{"listed":{"samples":7,"ran":5,"repositories":4}},"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":5,"samples":[{"code_sha256_prefix":"f975336b5d5f1a80","entry":"calculate_accuracy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f975336b5d5f1a80"}},{"code_sha256_prefix":"625877b8d181dc24","entry":"calculate_roc","repo":"qqueing/DeepSpeaker-pytorch","repo_kind":"listed","path":"eval_metrics.py","file_url":"https://github.com/qqueing/DeepSpeaker-pytorch/blob/HEAD/eval_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"625877b8d181dc24"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"2cbf4ce7e0235a0d","entry":"get","repo":"prajual/Deep_Speaker","repo_kind":"listed","path":"models.py","file_url":"https://github.com/prajual/Deep_Speaker/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2cbf4ce7e0235a0d"}},{"code_sha256_prefix":"cbc4d3a4f90e8027","entry":"getwavPathAndwavLabel","repo":"wangleiai/dVectorSpeakerRecognition","repo_kind":"listed","path":"kersaSoftmax/dnnTrain.py","file_url":"https://github.com/wangleiai/dVectorSpeakerRecognition/blob/HEAD/kersaSoftmax/dnnTrain.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cbc4d3a4f90e8027"}},{"code_sha256_prefix":"9e35c18ce8eaf604","entry":"getwavPathAndwavLabel","repo":"wangleiai/dVectorSpeakerRecognition","repo_kind":"listed","path":"kersaSoftmax/gruTrain.py","file_url":"https://github.com/wangleiai/dVectorSpeakerRecognition/blob/HEAD/kersaSoftmax/gruTrain.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9e35c18ce8eaf604"}},{"code_sha256_prefix":"6a6418cda28d6455","entry":"normalize_scores","repo":"Walleclipse/Deep_Speaker-speaker_recognition_system","repo_kind":"listed","path":"test_model.py","file_url":"https://github.com/Walleclipse/Deep_Speaker-speaker_recognition_system/blob/HEAD/test_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6a6418cda28d6455"}},{"code_sha256_prefix":"d74d2593f3b8926c","entry":"create_optimizer","repo":"qqueing/DeepSpeaker-pytorch","repo_kind":"listed","path":"train_triplet.py","file_url":"https://github.com/qqueing/DeepSpeaker-pytorch/blob/HEAD/train_triplet.py","link_basis":"first_harvest_node","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":"d74d2593f3b8926c"}},{"code_sha256_prefix":"1283b5c46e6830d4","entry":"evaluate","repo":"qqueing/DeepSpeaker-pytorch","repo_kind":"listed","path":"eval_metrics.py","file_url":"https://github.com/qqueing/DeepSpeaker-pytorch/blob/HEAD/eval_metrics.py","link_basis":"first_harvest_node","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":"1283b5c46e6830d4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}