{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XM2MVCYJIGMUJZ5CZ6NSHILO6N","short_pith_number":"pith:XM2MVCYJ","schema_version":"1.0","canonical_sha256":"bb34ca8b09419944e7a2cf9b23a16ef37e90656b51870bf29d956ece893875f7","source":{"kind":"arxiv","id":"2303.00332","version":3},"attestation_state":"computed","paper":{"title":"CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Masking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hui Wang, Luyao Cheng, Qian Chen, Siqi Zheng, Yafeng Chen","submitted_at":"2023-03-01T08:50:31Z","abstract_excerpt":"Time delay neural network (TDNN) has been proven to be efficient for speaker verification. One of its successful variants, ECAPA-TDNN, achieved state-of-the-art performance at the cost of much higher computational complexity and slower inference speed. This makes it inadequate for scenarios with demanding inference rate and limited computational resources. We are thus interested in finding an architecture that can achieve the performance of ECAPA-TDNN and the efficiency of vanilla TDNN. In this paper, we propose an efficient network based on context-aware masking, namely CAM++, which uses dens"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2303.00332","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-03-01T08:50:31Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"c09a3681c76a7e1ae255a0c0650516b639ef93cc7698fc8775c82745b91f8d88","abstract_canon_sha256":"df39df7e3cfb917cf12f289c79e279757764942aadb1723bbabe69381b1b87ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:15.951215Z","signature_b64":"NGgIX53kAuZ8FcXBt+TPTo9RSKn6+ZlVsglKncUkN+cWdugw0iPcfKfH6PVH2WjbbeO9iA1PQYXVZ1c+BlBWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb34ca8b09419944e7a2cf9b23a16ef37e90656b51870bf29d956ece893875f7","last_reissued_at":"2026-07-05T06:21:15.950798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:15.950798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Masking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hui Wang, Luyao Cheng, Qian Chen, Siqi Zheng, Yafeng Chen","submitted_at":"2023-03-01T08:50:31Z","abstract_excerpt":"Time delay neural network (TDNN) has been proven to be efficient for speaker verification. One of its successful variants, ECAPA-TDNN, achieved state-of-the-art performance at the cost of much higher computational complexity and slower inference speed. This makes it inadequate for scenarios with demanding inference rate and limited computational resources. We are thus interested in finding an architecture that can achieve the performance of ECAPA-TDNN and the efficiency of vanilla TDNN. In this paper, we propose an efficient network based on context-aware masking, namely CAM++, which uses dens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00332","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.00332/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2303.00332","created_at":"2026-07-05T06:21:15.950861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.00332v3","created_at":"2026-07-05T06:21:15.950861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00332","created_at":"2026-07-05T06:21:15.950861+00:00"},{"alias_kind":"pith_short_12","alias_value":"XM2MVCYJIGMU","created_at":"2026-07-05T06:21:15.950861+00:00"},{"alias_kind":"pith_short_16","alias_value":"XM2MVCYJIGMUJZ5C","created_at":"2026-07-05T06:21:15.950861+00:00"},{"alias_kind":"pith_short_8","alias_value":"XM2MVCYJ","created_at":"2026-07-05T06:21:15.950861+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25369","citing_title":"Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01729","citing_title":"DRL-CLBA: A Clean Label Backdoor Attack for Speech Classification via DDPG Reinforcement Learning","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01702","citing_title":"Pmeta-TLA: Backdoor Attacks for Speech Classification Models via Meta-Learning with Timbre Leakage Attack","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07015","citing_title":"Towards Unified Song Generation and Singing Voice Conversion with Accompaniment Co-Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30993","citing_title":"SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2504.13102","citing_title":"A Multi-task Learning Balanced Attention Convolutional Neural Network Model for Few-shot Underwater Acoustic Target Recognition","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09677","citing_title":"Logics-Parsing-Omni Technical Report","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06765","citing_title":"VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05526","citing_title":"Controllable Singing Style Conversion with Boundary-Aware Information Bottleneck","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XM2MVCYJIGMUJZ5CZ6NSHILO6N","json":"https://pith.science/pith/XM2MVCYJIGMUJZ5CZ6NSHILO6N.json","graph_json":"https://pith.science/api/pith-number/XM2MVCYJIGMUJZ5CZ6NSHILO6N/graph.json","events_json":"https://pith.science/api/pith-number/XM2MVCYJIGMUJZ5CZ6NSHILO6N/events.json","paper":"https://pith.science/paper/XM2MVCYJ"},"agent_actions":{"view_html":"https://pith.science/pith/XM2MVCYJIGMUJZ5CZ6NSHILO6N","download_json":"https://pith.science/pith/XM2MVCYJIGMUJZ5CZ6NSHILO6N.json","view_paper":"https://pith.science/paper/XM2MVCYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.00332&json=true","fetch_graph":"https://pith.science/api/pith-number/XM2MVCYJIGMUJZ5CZ6NSHILO6N/graph.json","fetch_events":"https://pith.science/api/pith-number/XM2MVCYJIGMUJZ5CZ6NSHILO6N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XM2MVCYJIGMUJZ5CZ6NSHILO6N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XM2MVCYJIGMUJZ5CZ6NSHILO6N/action/storage_attestation","attest_author":"https://pith.science/pith/XM2MVCYJIGMUJZ5CZ6NSHILO6N/action/author_attestation","sign_citation":"https://pith.science/pith/XM2MVCYJIGMUJZ5CZ6NSHILO6N/action/citation_signature","submit_replication":"https://pith.science/pith/XM2MVCYJIGMUJZ5CZ6NSHILO6N/action/replication_record"}},"created_at":"2026-07-05T06:21:15.950861+00:00","updated_at":"2026-07-05T06:21:15.950861+00:00"}