{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TF22HCBSXUPF2BW52QMQZGMCEX","short_pith_number":"pith:TF22HCBS","schema_version":"1.0","canonical_sha256":"9975a38832bd1e5d06ddd4190c998225c6917c4366b0eeaeac77c7d8c24f092d","source":{"kind":"arxiv","id":"2606.02400","version":1},"attestation_state":"computed","paper":{"title":"SoulX-Transcriber: A Robust End-to-End Framework for Multi-Speaker Speech Transcription","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chuang Ding, Hanke Xie, Hanlin Wen, Hao Meng, Haopeng Lin, Jiale Qian, Jun Wu, Lei Xie, Ming Tao, Shunshun Yin, Xinsheng Wang, Yuhang Dai, Zhennan Lin","submitted_at":"2026-06-01T15:47:01Z","abstract_excerpt":"Recent advances in Automatic Speech Recognition (ASR) and Large Language Models (LLMs) have significantly improved speech understanding capabilities. However, multi-speaker speech transcription remains challenging task, constrained by highly similar speaker voices, rapid turn-taking transitions, overlapping utterances and inaccurate speaker boundary segmentation. These challenges become particularly pronounced in real-world conversational audio, where speaker dynamics and acoustic conditions are highly variable. This technical report presents SoulX-Transcriber, a unified multi-speaker transcri"},"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":"2606.02400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-01T15:47:01Z","cross_cats_sorted":[],"title_canon_sha256":"7c1beabc1bff16a874fb9905f247554523e4b1a19718d38923ca17dea47c0b32","abstract_canon_sha256":"5fb761012469097562df57bd25ecb051fae3ad306316199adef6c8fac3b5d4ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:58.176684Z","signature_b64":"LAq56OnLYjdLEgWEdr3h8UUbtahcFkTS4zrszqnn43DBTvjPSOs5OCGX1ypRgJCSkKH4ECgX7h0YHZPIlpNlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9975a38832bd1e5d06ddd4190c998225c6917c4366b0eeaeac77c7d8c24f092d","last_reissued_at":"2026-06-02T03:04:58.176261Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:58.176261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SoulX-Transcriber: A Robust End-to-End Framework for Multi-Speaker Speech Transcription","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chuang Ding, Hanke Xie, Hanlin Wen, Hao Meng, Haopeng Lin, Jiale Qian, Jun Wu, Lei Xie, Ming Tao, Shunshun Yin, Xinsheng Wang, Yuhang Dai, Zhennan Lin","submitted_at":"2026-06-01T15:47:01Z","abstract_excerpt":"Recent advances in Automatic Speech Recognition (ASR) and Large Language Models (LLMs) have significantly improved speech understanding capabilities. However, multi-speaker speech transcription remains challenging task, constrained by highly similar speaker voices, rapid turn-taking transitions, overlapping utterances and inaccurate speaker boundary segmentation. These challenges become particularly pronounced in real-world conversational audio, where speaker dynamics and acoustic conditions are highly variable. This technical report presents SoulX-Transcriber, a unified multi-speaker transcri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02400","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/2606.02400/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":"2606.02400","created_at":"2026-06-02T03:04:58.176325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02400v1","created_at":"2026-06-02T03:04:58.176325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02400","created_at":"2026-06-02T03:04:58.176325+00:00"},{"alias_kind":"pith_short_12","alias_value":"TF22HCBSXUPF","created_at":"2026-06-02T03:04:58.176325+00:00"},{"alias_kind":"pith_short_16","alias_value":"TF22HCBSXUPF2BW5","created_at":"2026-06-02T03:04:58.176325+00:00"},{"alias_kind":"pith_short_8","alias_value":"TF22HCBS","created_at":"2026-06-02T03:04:58.176325+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/TF22HCBSXUPF2BW52QMQZGMCEX","json":"https://pith.science/pith/TF22HCBSXUPF2BW52QMQZGMCEX.json","graph_json":"https://pith.science/api/pith-number/TF22HCBSXUPF2BW52QMQZGMCEX/graph.json","events_json":"https://pith.science/api/pith-number/TF22HCBSXUPF2BW52QMQZGMCEX/events.json","paper":"https://pith.science/paper/TF22HCBS"},"agent_actions":{"view_html":"https://pith.science/pith/TF22HCBSXUPF2BW52QMQZGMCEX","download_json":"https://pith.science/pith/TF22HCBSXUPF2BW52QMQZGMCEX.json","view_paper":"https://pith.science/paper/TF22HCBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02400&json=true","fetch_graph":"https://pith.science/api/pith-number/TF22HCBSXUPF2BW52QMQZGMCEX/graph.json","fetch_events":"https://pith.science/api/pith-number/TF22HCBSXUPF2BW52QMQZGMCEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TF22HCBSXUPF2BW52QMQZGMCEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TF22HCBSXUPF2BW52QMQZGMCEX/action/storage_attestation","attest_author":"https://pith.science/pith/TF22HCBSXUPF2BW52QMQZGMCEX/action/author_attestation","sign_citation":"https://pith.science/pith/TF22HCBSXUPF2BW52QMQZGMCEX/action/citation_signature","submit_replication":"https://pith.science/pith/TF22HCBSXUPF2BW52QMQZGMCEX/action/replication_record"}},"created_at":"2026-06-02T03:04:58.176325+00:00","updated_at":"2026-06-02T03:04:58.176325+00:00"}