{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KJPA2BYX7S6GPU5ZLRHXA2VSC4","short_pith_number":"pith:KJPA2BYX","schema_version":"1.0","canonical_sha256":"525e0d0717fcbc67d3b95c4f706ab2173776d038313afa8d4504405ab52004e9","source":{"kind":"arxiv","id":"2508.10456","version":1},"attestation_state":"computed","paper":{"title":"Exploring Cross-Utterance Speech Contexts for Conformer-Transducer Speech Recognition Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chengxi Deng, Guinan Li, Jiajun Deng, Jiawen Kang, Mengzhe Geng, Mingyu Cui, Shujie Hu, Tianzi Wang, Xie Chen, Xunying Liu, Zhaoqing Li","submitted_at":"2025-08-14T08:54:01Z","abstract_excerpt":"This paper investigates four types of cross-utterance speech contexts modeling approaches for streaming and non-streaming Conformer-Transformer (C-T) ASR systems: i) input audio feature concatenation; ii) cross-utterance Encoder embedding concatenation; iii) cross-utterance Encoder embedding pooling projection; or iv) a novel chunk-based approach applied to C-T models for the first time. An efficient batch-training scheme is proposed for contextual C-Ts that uses spliced speech utterances within each minibatch to minimize the synchronization overhead while preserving the sequential order of cr"},"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":"2508.10456","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-08-14T08:54:01Z","cross_cats_sorted":[],"title_canon_sha256":"f99ddf08e53324aa39158efb2abd2a0ed6f4f7811697875c7218ee240fd34934","abstract_canon_sha256":"72769fc9a70d4f7b69e450403f777188394c3bd61afa10db2fad3d8463831734"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:56.755664Z","signature_b64":"w+M9FoWD0bxNPEv7iURdyqSFud4RYC/Yg3rUdA0eDvuY6QU5i5G1h2wOvBWDQDKWu8vxhC6h0c995ajNNWf1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"525e0d0717fcbc67d3b95c4f706ab2173776d038313afa8d4504405ab52004e9","last_reissued_at":"2026-07-05T11:53:56.755288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:56.755288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Cross-Utterance Speech Contexts for Conformer-Transducer Speech Recognition Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chengxi Deng, Guinan Li, Jiajun Deng, Jiawen Kang, Mengzhe Geng, Mingyu Cui, Shujie Hu, Tianzi Wang, Xie Chen, Xunying Liu, Zhaoqing Li","submitted_at":"2025-08-14T08:54:01Z","abstract_excerpt":"This paper investigates four types of cross-utterance speech contexts modeling approaches for streaming and non-streaming Conformer-Transformer (C-T) ASR systems: i) input audio feature concatenation; ii) cross-utterance Encoder embedding concatenation; iii) cross-utterance Encoder embedding pooling projection; or iv) a novel chunk-based approach applied to C-T models for the first time. An efficient batch-training scheme is proposed for contextual C-Ts that uses spliced speech utterances within each minibatch to minimize the synchronization overhead while preserving the sequential order of cr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10456","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/2508.10456/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":"2508.10456","created_at":"2026-07-05T11:53:56.755344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10456v1","created_at":"2026-07-05T11:53:56.755344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10456","created_at":"2026-07-05T11:53:56.755344+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJPA2BYX7S6G","created_at":"2026-07-05T11:53:56.755344+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJPA2BYX7S6GPU5Z","created_at":"2026-07-05T11:53:56.755344+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJPA2BYX","created_at":"2026-07-05T11:53:56.755344+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/KJPA2BYX7S6GPU5ZLRHXA2VSC4","json":"https://pith.science/pith/KJPA2BYX7S6GPU5ZLRHXA2VSC4.json","graph_json":"https://pith.science/api/pith-number/KJPA2BYX7S6GPU5ZLRHXA2VSC4/graph.json","events_json":"https://pith.science/api/pith-number/KJPA2BYX7S6GPU5ZLRHXA2VSC4/events.json","paper":"https://pith.science/paper/KJPA2BYX"},"agent_actions":{"view_html":"https://pith.science/pith/KJPA2BYX7S6GPU5ZLRHXA2VSC4","download_json":"https://pith.science/pith/KJPA2BYX7S6GPU5ZLRHXA2VSC4.json","view_paper":"https://pith.science/paper/KJPA2BYX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10456&json=true","fetch_graph":"https://pith.science/api/pith-number/KJPA2BYX7S6GPU5ZLRHXA2VSC4/graph.json","fetch_events":"https://pith.science/api/pith-number/KJPA2BYX7S6GPU5ZLRHXA2VSC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJPA2BYX7S6GPU5ZLRHXA2VSC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJPA2BYX7S6GPU5ZLRHXA2VSC4/action/storage_attestation","attest_author":"https://pith.science/pith/KJPA2BYX7S6GPU5ZLRHXA2VSC4/action/author_attestation","sign_citation":"https://pith.science/pith/KJPA2BYX7S6GPU5ZLRHXA2VSC4/action/citation_signature","submit_replication":"https://pith.science/pith/KJPA2BYX7S6GPU5ZLRHXA2VSC4/action/replication_record"}},"created_at":"2026-07-05T11:53:56.755344+00:00","updated_at":"2026-07-05T11:53:56.755344+00:00"}