{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:O3NCPHVF4DNFBTBJYIJPI7WJKS","short_pith_number":"pith:O3NCPHVF","canonical_record":{"source":{"id":"2404.11275","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-04-17T11:31:16Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"1326f97bb06febf40575a80ec547d70cfdb3e2b130ee18d4c5512a3c030d66ed","abstract_canon_sha256":"2a5f071f5f91ae9c8640f9e5e11bb981325477923387b85b4a65881d615210ec"},"schema_version":"1.0"},"canonical_sha256":"76da279ea5e0da50cc29c212f47ec954b24396fd26a41c173c15a38d2620187a","source":{"kind":"arxiv","id":"2404.11275","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.11275","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"arxiv_version","alias_value":"2404.11275v1","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11275","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"pith_short_12","alias_value":"O3NCPHVF4DNF","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"pith_short_16","alias_value":"O3NCPHVF4DNFBTBJ","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"pith_short_8","alias_value":"O3NCPHVF","created_at":"2026-07-05T08:09:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:O3NCPHVF4DNFBTBJYIJPI7WJKS","target":"record","payload":{"canonical_record":{"source":{"id":"2404.11275","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-04-17T11:31:16Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"1326f97bb06febf40575a80ec547d70cfdb3e2b130ee18d4c5512a3c030d66ed","abstract_canon_sha256":"2a5f071f5f91ae9c8640f9e5e11bb981325477923387b85b4a65881d615210ec"},"schema_version":"1.0"},"canonical_sha256":"76da279ea5e0da50cc29c212f47ec954b24396fd26a41c173c15a38d2620187a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:06.882261Z","signature_b64":"bGrPCaWefQZcKZtmqHvpgPzQHAcKAst+0oYLSaLPJlFgsgRw4d681Pa6/55qQ7yX7vG1q7Cnj+6aa8BqQUZsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76da279ea5e0da50cc29c212f47ec954b24396fd26a41c173c15a38d2620187a","last_reissued_at":"2026-07-05T08:09:06.881875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:06.881875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.11275","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:09:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wV7kfpxiVTyLnt5AoIrq7DQIssk7ihQZxuZpe08VZ8jmz9i4giJCISzHmD6gYK88kmFMl0zAEMZxVF8ujeQ+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:10:21.238335Z"},"content_sha256":"a05a5c846d5ce7fba010b75f5d811d7d0926438dbbd4ce7814f47e994b7ace6f","schema_version":"1.0","event_id":"sha256:a05a5c846d5ce7fba010b75f5d811d7d0926438dbbd4ce7814f47e994b7ace6f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:O3NCPHVF4DNFBTBJYIJPI7WJKS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Jointly Recognizing Speech and Singing Voices Based on Multi-Task Audio Source Separation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenxing Li, Hao Li, Xiaorui Wang, Ye Bai, Yuanyuan Zhao","submitted_at":"2024-04-17T11:31:16Z","abstract_excerpt":"In short video and live broadcasts, speech, singing voice, and background music often overlap and obscure each other. This complexity creates difficulties in structuring and recognizing the audio content, which may impair subsequent ASR and music understanding applications. This paper proposes a multi-task audio source separation (MTASS) based ASR model called JRSV, which Jointly Recognizes Speech and singing Voices. Specifically, the MTASS module separates the mixed audio into distinct speech and singing voice tracks while removing background music. The CTC/attention hybrid recognition module"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11275","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.11275/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:09:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yH2S/5xfylcwRQxESt3/d3/mYJe3be/1Ho7WrNM18ZCtAOpiKXt84WdURhY3oWDX2GBluvfbj3SS3oiWxBheCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:10:21.239077Z"},"content_sha256":"85adf1543183aad9d6822c47f6d92080ba4c86b23c1fe7043c05cd8dfc1d3b02","schema_version":"1.0","event_id":"sha256:85adf1543183aad9d6822c47f6d92080ba4c86b23c1fe7043c05cd8dfc1d3b02"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O3NCPHVF4DNFBTBJYIJPI7WJKS/bundle.json","state_url":"https://pith.science/pith/O3NCPHVF4DNFBTBJYIJPI7WJKS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O3NCPHVF4DNFBTBJYIJPI7WJKS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T23:10:21Z","links":{"resolver":"https://pith.science/pith/O3NCPHVF4DNFBTBJYIJPI7WJKS","bundle":"https://pith.science/pith/O3NCPHVF4DNFBTBJYIJPI7WJKS/bundle.json","state":"https://pith.science/pith/O3NCPHVF4DNFBTBJYIJPI7WJKS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O3NCPHVF4DNFBTBJYIJPI7WJKS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O3NCPHVF4DNFBTBJYIJPI7WJKS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2a5f071f5f91ae9c8640f9e5e11bb981325477923387b85b4a65881d615210ec","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-04-17T11:31:16Z","title_canon_sha256":"1326f97bb06febf40575a80ec547d70cfdb3e2b130ee18d4c5512a3c030d66ed"},"schema_version":"1.0","source":{"id":"2404.11275","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.11275","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"arxiv_version","alias_value":"2404.11275v1","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11275","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"pith_short_12","alias_value":"O3NCPHVF4DNF","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"pith_short_16","alias_value":"O3NCPHVF4DNFBTBJ","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"pith_short_8","alias_value":"O3NCPHVF","created_at":"2026-07-05T08:09:06Z"}],"graph_snapshots":[{"event_id":"sha256:85adf1543183aad9d6822c47f6d92080ba4c86b23c1fe7043c05cd8dfc1d3b02","target":"graph","created_at":"2026-07-05T08:09:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.11275/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In short video and live broadcasts, speech, singing voice, and background music often overlap and obscure each other. This complexity creates difficulties in structuring and recognizing the audio content, which may impair subsequent ASR and music understanding applications. This paper proposes a multi-task audio source separation (MTASS) based ASR model called JRSV, which Jointly Recognizes Speech and singing Voices. Specifically, the MTASS module separates the mixed audio into distinct speech and singing voice tracks while removing background music. The CTC/attention hybrid recognition module","authors_text":"Chenxing Li, Hao Li, Xiaorui Wang, Ye Bai, Yuanyuan Zhao","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-04-17T11:31:16Z","title":"Jointly Recognizing Speech and Singing Voices Based on Multi-Task Audio Source Separation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11275","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a05a5c846d5ce7fba010b75f5d811d7d0926438dbbd4ce7814f47e994b7ace6f","target":"record","created_at":"2026-07-05T08:09:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2a5f071f5f91ae9c8640f9e5e11bb981325477923387b85b4a65881d615210ec","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-04-17T11:31:16Z","title_canon_sha256":"1326f97bb06febf40575a80ec547d70cfdb3e2b130ee18d4c5512a3c030d66ed"},"schema_version":"1.0","source":{"id":"2404.11275","kind":"arxiv","version":1}},"canonical_sha256":"76da279ea5e0da50cc29c212f47ec954b24396fd26a41c173c15a38d2620187a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76da279ea5e0da50cc29c212f47ec954b24396fd26a41c173c15a38d2620187a","first_computed_at":"2026-07-05T08:09:06.881875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:09:06.881875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bGrPCaWefQZcKZtmqHvpgPzQHAcKAst+0oYLSaLPJlFgsgRw4d681Pa6/55qQ7yX7vG1q7Cnj+6aa8BqQUZsAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:09:06.882261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.11275","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a05a5c846d5ce7fba010b75f5d811d7d0926438dbbd4ce7814f47e994b7ace6f","sha256:85adf1543183aad9d6822c47f6d92080ba4c86b23c1fe7043c05cd8dfc1d3b02"],"state_sha256":"3193955f6a02eb05e00fb850dd814ec2d562579872aa9ce8ae6b86f8da8845d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Sjok0P4MnSRVkvcql++ypq11D3xW1c7FVaaWAZVpNSEM/+JsxBwCzFcZaH3JRlkqAyDT2U/47ry/fZkMIXhBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T23:10:21.244636Z","bundle_sha256":"4d2147121373d350876f3b20fd4cbe874b7995ff925974e5b10c6344d3bd5338"}}