{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:J2EL2EHQODVPNKLTUN52LOKRRX","short_pith_number":"pith:J2EL2EHQ","schema_version":"1.0","canonical_sha256":"4e88bd10f070eaf6a973a37ba5b9518dd5d5e998aa414e7a1af92294f3074a54","source":{"kind":"arxiv","id":"2309.10707","version":1},"attestation_state":"computed","paper":{"title":"Corpus Synthesis for Zero-shot ASR domain Adaptation using Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Gautam Varma Mantena, Hema Swetha Koppula, Hsuan Su, Jen-Hao Rick Chang, Karren Yang, Oncel Tuzel, Raviteja Vemulapalli, Ting-Yao Hu","submitted_at":"2023-09-18T15:43:08Z","abstract_excerpt":"While Automatic Speech Recognition (ASR) systems are widely used in many real-world applications, they often do not generalize well to new domains and need to be finetuned on data from these domains. However, target-domain data usually are not readily available in many scenarios. In this paper, we propose a new strategy for adapting ASR models to new target domains without any text or speech from those domains. To accomplish this, we propose a novel data synthesis pipeline that uses a Large Language Model (LLM) to generate a target domain text corpus, and a state-of-the-art controllable speech"},"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":"2309.10707","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-18T15:43:08Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"19b933ed69b2c6e39bfc4b9e27de9282aa8f93307d95c33af743ce0ff12bf99f","abstract_canon_sha256":"6d1a84cae9011f37670cf1cc44ca3eab61658f5521e09b5d0ddf22bc7e96657a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:15.762379Z","signature_b64":"uPWiWyuvtVlItvQuU/Q1CKviiOmv9HAnCruo1DRrYgf50o9Gjzg5skotqBFVFA3K0g6by2K6K1fXyFxA86LXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e88bd10f070eaf6a973a37ba5b9518dd5d5e998aa414e7a1af92294f3074a54","last_reissued_at":"2026-07-05T06:52:15.761877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:15.761877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Corpus Synthesis for Zero-shot ASR domain Adaptation using Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Gautam Varma Mantena, Hema Swetha Koppula, Hsuan Su, Jen-Hao Rick Chang, Karren Yang, Oncel Tuzel, Raviteja Vemulapalli, Ting-Yao Hu","submitted_at":"2023-09-18T15:43:08Z","abstract_excerpt":"While Automatic Speech Recognition (ASR) systems are widely used in many real-world applications, they often do not generalize well to new domains and need to be finetuned on data from these domains. However, target-domain data usually are not readily available in many scenarios. In this paper, we propose a new strategy for adapting ASR models to new target domains without any text or speech from those domains. To accomplish this, we propose a novel data synthesis pipeline that uses a Large Language Model (LLM) to generate a target domain text corpus, and a state-of-the-art controllable speech"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10707","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/2309.10707/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":"2309.10707","created_at":"2026-07-05T06:52:15.761936+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.10707v1","created_at":"2026-07-05T06:52:15.761936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10707","created_at":"2026-07-05T06:52:15.761936+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2EL2EHQODVP","created_at":"2026-07-05T06:52:15.761936+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2EL2EHQODVPNKLT","created_at":"2026-07-05T06:52:15.761936+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2EL2EHQ","created_at":"2026-07-05T06:52:15.761936+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/J2EL2EHQODVPNKLTUN52LOKRRX","json":"https://pith.science/pith/J2EL2EHQODVPNKLTUN52LOKRRX.json","graph_json":"https://pith.science/api/pith-number/J2EL2EHQODVPNKLTUN52LOKRRX/graph.json","events_json":"https://pith.science/api/pith-number/J2EL2EHQODVPNKLTUN52LOKRRX/events.json","paper":"https://pith.science/paper/J2EL2EHQ"},"agent_actions":{"view_html":"https://pith.science/pith/J2EL2EHQODVPNKLTUN52LOKRRX","download_json":"https://pith.science/pith/J2EL2EHQODVPNKLTUN52LOKRRX.json","view_paper":"https://pith.science/paper/J2EL2EHQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.10707&json=true","fetch_graph":"https://pith.science/api/pith-number/J2EL2EHQODVPNKLTUN52LOKRRX/graph.json","fetch_events":"https://pith.science/api/pith-number/J2EL2EHQODVPNKLTUN52LOKRRX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2EL2EHQODVPNKLTUN52LOKRRX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2EL2EHQODVPNKLTUN52LOKRRX/action/storage_attestation","attest_author":"https://pith.science/pith/J2EL2EHQODVPNKLTUN52LOKRRX/action/author_attestation","sign_citation":"https://pith.science/pith/J2EL2EHQODVPNKLTUN52LOKRRX/action/citation_signature","submit_replication":"https://pith.science/pith/J2EL2EHQODVPNKLTUN52LOKRRX/action/replication_record"}},"created_at":"2026-07-05T06:52:15.761936+00:00","updated_at":"2026-07-05T06:52:15.761936+00:00"}