{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SKFIYZ7F7F4X3ZHORZCPLJVJJO","short_pith_number":"pith:SKFIYZ7F","canonical_record":{"source":{"id":"2501.09169","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-15T21:43:49Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"9173db829da5267a1c1c04650f125461cffdc0b65b9a54e26bb7debb7a597a82","abstract_canon_sha256":"f37d4185f6c7faec7a4c2b557712b287a2c2b30f66a392e630bc6c1555a4c3cf"},"schema_version":"1.0"},"canonical_sha256":"928a8c67e5f9797de4ee8e44f5a6a94bad8d16fce7a4840947545870ab333e23","source":{"kind":"arxiv","id":"2501.09169","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09169","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09169v1","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09169","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"pith_short_12","alias_value":"SKFIYZ7F7F4X","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"pith_short_16","alias_value":"SKFIYZ7F7F4X3ZHO","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"pith_short_8","alias_value":"SKFIYZ7F","created_at":"2026-07-05T10:01:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SKFIYZ7F7F4X3ZHORZCPLJVJJO","target":"record","payload":{"canonical_record":{"source":{"id":"2501.09169","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-15T21:43:49Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"9173db829da5267a1c1c04650f125461cffdc0b65b9a54e26bb7debb7a597a82","abstract_canon_sha256":"f37d4185f6c7faec7a4c2b557712b287a2c2b30f66a392e630bc6c1555a4c3cf"},"schema_version":"1.0"},"canonical_sha256":"928a8c67e5f9797de4ee8e44f5a6a94bad8d16fce7a4840947545870ab333e23","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:42.960734Z","signature_b64":"shO+sdaM5/f+llVO8RgAsnaj6g4vPpuRTUyLvxYdhu42IWoc7oyztChvelsHHWBJieFI6mRP69alxUJRGQPgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"928a8c67e5f9797de4ee8e44f5a6a94bad8d16fce7a4840947545870ab333e23","last_reissued_at":"2026-07-05T10:01:42.960246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:42.960246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.09169","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":"2026-07-05T10:01:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LR4601yXNDr/V5KQA3DPu3lnyWRRQW0H3RPGyhLq+2AWlsGwKHZxRSwwbmaVIjm5ecH4VzQLYoaDzeVXEISVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T20:32:36.095825Z"},"content_sha256":"40a862e789477e83e8c9ad3acf5e348a20d16df1dbf38ef93705a4f1a2d19cdc","schema_version":"1.0","event_id":"sha256:40a862e789477e83e8c9ad3acf5e348a20d16df1dbf38ef93705a4f1a2d19cdc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SKFIYZ7F7F4X3ZHORZCPLJVJJO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Speaker Identity: Text Guided Target Speech Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Abhinav Jain, Cong Phuoc Huynh, Fanjie Kong, Mingyue Huo, Pichao Wang, Vimal Bhat, Zhu Liu","submitted_at":"2025-01-15T21:43:49Z","abstract_excerpt":"Target Speech Extraction (TSE) traditionally relies on explicit clues about the speaker's identity like enrollment audio, face images, or videos, which may not always be available. In this paper, we propose a text-guided TSE model StyleTSE that uses natural language descriptions of speaking style in addition to the audio clue to extract the desired speech from a given mixture. Our model integrates a speech separation network adapted from SepFormer with a bi-modality clue network that flexibly processes both audio and text clues. To train and evaluate our model, we introduce a new dataset Textr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09169","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/2501.09169/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":"2026-07-05T10:01:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Coo2cOmi8AcIDE/48BgCHdyjt5OXWeQs9tDT1HVBdZEgNpGUfrvzmmjHAJCUGB30eZvdS1RVxR43mXvqPTtGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T20:32:36.096875Z"},"content_sha256":"8a2c070b1f2bd8ad92cdf85ba8f516d42b1fccff0d97a52745a11281237fcf4e","schema_version":"1.0","event_id":"sha256:8a2c070b1f2bd8ad92cdf85ba8f516d42b1fccff0d97a52745a11281237fcf4e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SKFIYZ7F7F4X3ZHORZCPLJVJJO/bundle.json","state_url":"https://pith.science/pith/SKFIYZ7F7F4X3ZHORZCPLJVJJO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SKFIYZ7F7F4X3ZHORZCPLJVJJO/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":"2026-08-12T20:32:36Z","links":{"resolver":"https://pith.science/pith/SKFIYZ7F7F4X3ZHORZCPLJVJJO","bundle":"https://pith.science/pith/SKFIYZ7F7F4X3ZHORZCPLJVJJO/bundle.json","state":"https://pith.science/pith/SKFIYZ7F7F4X3ZHORZCPLJVJJO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SKFIYZ7F7F4X3ZHORZCPLJVJJO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SKFIYZ7F7F4X3ZHORZCPLJVJJO","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":"f37d4185f6c7faec7a4c2b557712b287a2c2b30f66a392e630bc6c1555a4c3cf","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-15T21:43:49Z","title_canon_sha256":"9173db829da5267a1c1c04650f125461cffdc0b65b9a54e26bb7debb7a597a82"},"schema_version":"1.0","source":{"id":"2501.09169","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09169","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09169v1","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09169","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"pith_short_12","alias_value":"SKFIYZ7F7F4X","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"pith_short_16","alias_value":"SKFIYZ7F7F4X3ZHO","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"pith_short_8","alias_value":"SKFIYZ7F","created_at":"2026-07-05T10:01:42Z"}],"graph_snapshots":[{"event_id":"sha256:8a2c070b1f2bd8ad92cdf85ba8f516d42b1fccff0d97a52745a11281237fcf4e","target":"graph","created_at":"2026-07-05T10:01:42Z","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/2501.09169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Target Speech Extraction (TSE) traditionally relies on explicit clues about the speaker's identity like enrollment audio, face images, or videos, which may not always be available. In this paper, we propose a text-guided TSE model StyleTSE that uses natural language descriptions of speaking style in addition to the audio clue to extract the desired speech from a given mixture. Our model integrates a speech separation network adapted from SepFormer with a bi-modality clue network that flexibly processes both audio and text clues. To train and evaluate our model, we introduce a new dataset Textr","authors_text":"Abhinav Jain, Cong Phuoc Huynh, Fanjie Kong, Mingyue Huo, Pichao Wang, Vimal Bhat, Zhu Liu","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-15T21:43:49Z","title":"Beyond Speaker Identity: Text Guided Target Speech Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09169","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":"sha256:40a862e789477e83e8c9ad3acf5e348a20d16df1dbf38ef93705a4f1a2d19cdc","target":"record","created_at":"2026-07-05T10:01:42Z","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":"f37d4185f6c7faec7a4c2b557712b287a2c2b30f66a392e630bc6c1555a4c3cf","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-15T21:43:49Z","title_canon_sha256":"9173db829da5267a1c1c04650f125461cffdc0b65b9a54e26bb7debb7a597a82"},"schema_version":"1.0","source":{"id":"2501.09169","kind":"arxiv","version":1}},"canonical_sha256":"928a8c67e5f9797de4ee8e44f5a6a94bad8d16fce7a4840947545870ab333e23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"928a8c67e5f9797de4ee8e44f5a6a94bad8d16fce7a4840947545870ab333e23","first_computed_at":"2026-07-05T10:01:42.960246Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:01:42.960246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"shO+sdaM5/f+llVO8RgAsnaj6g4vPpuRTUyLvxYdhu42IWoc7oyztChvelsHHWBJieFI6mRP69alxUJRGQPgDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:01:42.960734Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.09169","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40a862e789477e83e8c9ad3acf5e348a20d16df1dbf38ef93705a4f1a2d19cdc","sha256:8a2c070b1f2bd8ad92cdf85ba8f516d42b1fccff0d97a52745a11281237fcf4e"],"state_sha256":"ed60d1d78f69974b53bac841c137bdab38db800706ad5916210d6b2368e6f8c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lctc2A3D70CIUAsX09n0Jfp/0TvdmwPkQNfHPgQe+Z5ccM3PssqNv5zTITS/76qA0KRwU3gtXyYxvE108XXMDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T20:32:36.104864Z","bundle_sha256":"a6e0a1de764bd4bd69df047088578cc8ecd5f314420ea58f9f9ac4900b6eb2dc"}}