{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DRXXS2YUM2MNHGGJVGC2UQJYVF","short_pith_number":"pith:DRXXS2YU","schema_version":"1.0","canonical_sha256":"1c6f796b146698d398c9a985aa4138a968d6e8053d602c63fd17ee2489a0e48a","source":{"kind":"arxiv","id":"2409.12042","version":1},"attestation_state":"computed","paper":{"title":"ASR Benchmarking: Need for a More Representative Conversational Dataset","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dmitry Ivanov, Gaurav Maheshwari, Kevin El Haddad, Th\\'eo Johannet","submitted_at":"2024-09-18T15:03:04Z","abstract_excerpt":"Automatic Speech Recognition (ASR) systems have achieved remarkable performance on widely used benchmarks such as LibriSpeech and Fleurs. However, these benchmarks do not adequately reflect the complexities of real-world conversational environments, where speech is often unstructured and contains disfluencies such as pauses, interruptions, and diverse accents. In this study, we introduce a multilingual conversational dataset, derived from TalkBank, consisting of unstructured phone conversation between adults. Our results show a significant performance drop across various state-of-the-art ASR m"},"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":"2409.12042","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-18T15:03:04Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"29022f256e6090eb59754ea2531b0ee670ee28b2c8e0810992ff8b53022ddef6","abstract_canon_sha256":"6ee2149c12557675d021dca286b47ae60ac93fd2f6c9d3e65dde1a2be53e095d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:41.644243Z","signature_b64":"zEK+DHZGDflGb7DZ4XazXWjodd6B/zErsuvNwhko1t6g/DP+jW8/PVccAzjTdZJoxgakuBkBmuRMdCBkNb8rDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c6f796b146698d398c9a985aa4138a968d6e8053d602c63fd17ee2489a0e48a","last_reissued_at":"2026-07-05T09:08:41.643708Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:41.643708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ASR Benchmarking: Need for a More Representative Conversational Dataset","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dmitry Ivanov, Gaurav Maheshwari, Kevin El Haddad, Th\\'eo Johannet","submitted_at":"2024-09-18T15:03:04Z","abstract_excerpt":"Automatic Speech Recognition (ASR) systems have achieved remarkable performance on widely used benchmarks such as LibriSpeech and Fleurs. However, these benchmarks do not adequately reflect the complexities of real-world conversational environments, where speech is often unstructured and contains disfluencies such as pauses, interruptions, and diverse accents. In this study, we introduce a multilingual conversational dataset, derived from TalkBank, consisting of unstructured phone conversation between adults. Our results show a significant performance drop across various state-of-the-art ASR m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12042","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/2409.12042/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":"2409.12042","created_at":"2026-07-05T09:08:41.643785+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.12042v1","created_at":"2026-07-05T09:08:41.643785+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12042","created_at":"2026-07-05T09:08:41.643785+00:00"},{"alias_kind":"pith_short_12","alias_value":"DRXXS2YUM2MN","created_at":"2026-07-05T09:08:41.643785+00:00"},{"alias_kind":"pith_short_16","alias_value":"DRXXS2YUM2MNHGGJ","created_at":"2026-07-05T09:08:41.643785+00:00"},{"alias_kind":"pith_short_8","alias_value":"DRXXS2YU","created_at":"2026-07-05T09:08:41.643785+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/DRXXS2YUM2MNHGGJVGC2UQJYVF","json":"https://pith.science/pith/DRXXS2YUM2MNHGGJVGC2UQJYVF.json","graph_json":"https://pith.science/api/pith-number/DRXXS2YUM2MNHGGJVGC2UQJYVF/graph.json","events_json":"https://pith.science/api/pith-number/DRXXS2YUM2MNHGGJVGC2UQJYVF/events.json","paper":"https://pith.science/paper/DRXXS2YU"},"agent_actions":{"view_html":"https://pith.science/pith/DRXXS2YUM2MNHGGJVGC2UQJYVF","download_json":"https://pith.science/pith/DRXXS2YUM2MNHGGJVGC2UQJYVF.json","view_paper":"https://pith.science/paper/DRXXS2YU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.12042&json=true","fetch_graph":"https://pith.science/api/pith-number/DRXXS2YUM2MNHGGJVGC2UQJYVF/graph.json","fetch_events":"https://pith.science/api/pith-number/DRXXS2YUM2MNHGGJVGC2UQJYVF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DRXXS2YUM2MNHGGJVGC2UQJYVF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DRXXS2YUM2MNHGGJVGC2UQJYVF/action/storage_attestation","attest_author":"https://pith.science/pith/DRXXS2YUM2MNHGGJVGC2UQJYVF/action/author_attestation","sign_citation":"https://pith.science/pith/DRXXS2YUM2MNHGGJVGC2UQJYVF/action/citation_signature","submit_replication":"https://pith.science/pith/DRXXS2YUM2MNHGGJVGC2UQJYVF/action/replication_record"}},"created_at":"2026-07-05T09:08:41.643785+00:00","updated_at":"2026-07-05T09:08:41.643785+00:00"}