{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:J3W5P7EA6NYOA5U4BDXK4JUZDK","short_pith_number":"pith:J3W5P7EA","schema_version":"1.0","canonical_sha256":"4eedd7fc80f370e0769c08eeae26991aaebf70a3323553732f42297d787bd829","source":{"kind":"arxiv","id":"1906.10876","version":1},"attestation_state":"computed","paper":{"title":"Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Kenji Nagamatsu, Naoyuki Kanda, Ryoichi Takashima, Shinji Watanabe, Shota Horiguchi, Yusuke Fujita","submitted_at":"2019-06-26T07:09:57Z","abstract_excerpt":"In this paper, we propose a novel auxiliary loss function for target-speaker automatic speech recognition (ASR). Our method automatically extracts and transcribes target speaker's utterances from a monaural mixture of multiple speakers speech given a short sample of the target speaker. The proposed auxiliary loss function attempts to additionally maximize interference speaker ASR accuracy during training. This will regularize the network to achieve a better representation for speaker separation, thus achieving better accuracy on the target-speaker ASR. We evaluated our proposed method using tw"},"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":"1906.10876","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-26T07:09:57Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"ceba865646b485e411c52c0d823fed93cf50d5f7710a2712d39aaf56e2f4edf4","abstract_canon_sha256":"4669838fa59e27d9a0933ce584f0a95866c5adcfd086b0d294eebaece7b54144"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:12.959943Z","signature_b64":"rSJAzV/VjYdJ9NnVjtyW1e8JkpScJxCrhiwkeswHTvfrKHB6JnT3bOHTIbll81wcARUp/5DlOuU+3CH7HeneCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4eedd7fc80f370e0769c08eeae26991aaebf70a3323553732f42297d787bd829","last_reissued_at":"2026-05-17T23:42:12.959133Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:12.959133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Kenji Nagamatsu, Naoyuki Kanda, Ryoichi Takashima, Shinji Watanabe, Shota Horiguchi, Yusuke Fujita","submitted_at":"2019-06-26T07:09:57Z","abstract_excerpt":"In this paper, we propose a novel auxiliary loss function for target-speaker automatic speech recognition (ASR). Our method automatically extracts and transcribes target speaker's utterances from a monaural mixture of multiple speakers speech given a short sample of the target speaker. The proposed auxiliary loss function attempts to additionally maximize interference speaker ASR accuracy during training. This will regularize the network to achieve a better representation for speaker separation, thus achieving better accuracy on the target-speaker ASR. We evaluated our proposed method using tw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10876","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1906.10876","created_at":"2026-05-17T23:42:12.959364+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.10876v1","created_at":"2026-05-17T23:42:12.959364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10876","created_at":"2026-05-17T23:42:12.959364+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3W5P7EA6NYO","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3W5P7EA6NYOA5U4","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3W5P7EA","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J3W5P7EA6NYOA5U4BDXK4JUZDK","json":"https://pith.science/pith/J3W5P7EA6NYOA5U4BDXK4JUZDK.json","graph_json":"https://pith.science/api/pith-number/J3W5P7EA6NYOA5U4BDXK4JUZDK/graph.json","events_json":"https://pith.science/api/pith-number/J3W5P7EA6NYOA5U4BDXK4JUZDK/events.json","paper":"https://pith.science/paper/J3W5P7EA"},"agent_actions":{"view_html":"https://pith.science/pith/J3W5P7EA6NYOA5U4BDXK4JUZDK","download_json":"https://pith.science/pith/J3W5P7EA6NYOA5U4BDXK4JUZDK.json","view_paper":"https://pith.science/paper/J3W5P7EA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.10876&json=true","fetch_graph":"https://pith.science/api/pith-number/J3W5P7EA6NYOA5U4BDXK4JUZDK/graph.json","fetch_events":"https://pith.science/api/pith-number/J3W5P7EA6NYOA5U4BDXK4JUZDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3W5P7EA6NYOA5U4BDXK4JUZDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3W5P7EA6NYOA5U4BDXK4JUZDK/action/storage_attestation","attest_author":"https://pith.science/pith/J3W5P7EA6NYOA5U4BDXK4JUZDK/action/author_attestation","sign_citation":"https://pith.science/pith/J3W5P7EA6NYOA5U4BDXK4JUZDK/action/citation_signature","submit_replication":"https://pith.science/pith/J3W5P7EA6NYOA5U4BDXK4JUZDK/action/replication_record"}},"created_at":"2026-05-17T23:42:12.959364+00:00","updated_at":"2026-05-17T23:42:12.959364+00:00"}