{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:T2AZMQ7KTA4MD7UME4GUBKKUXR","short_pith_number":"pith:T2AZMQ7K","schema_version":"1.0","canonical_sha256":"9e819643ea9838c1fe8c270d40a954bc60ad24a042119201c4b76096581ba6f2","source":{"kind":"arxiv","id":"1808.05312","version":1},"attestation_state":"computed","paper":{"title":"Toward domain-invariant speech recognition via large scale training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Ananya Misra, Anshuman Tripathi, Arun Narayanan, Golan Pundak, Khe Chai Sim, Michiel Bacchiani, Mohamed Elfeky, Parisa Haghani, Trevor Strohman","submitted_at":"2018-08-16T00:24:49Z","abstract_excerpt":"Current state-of-the-art automatic speech recognition systems are trained to work in specific `domains', defined based on factors like application, sampling rate and codec. When such recognizers are used in conditions that do not match the training domain, performance significantly drops. This work explores the idea of building a single domain-invariant model for varied use-cases by combining large scale training data from multiple application domains. Our final system is trained using 162,000 hours of speech. Additionally, each utterance is artificially distorted during training to simulate e"},"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":"1808.05312","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-16T00:24:49Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"abbbeb64de5f562154c9379d7310727202a36aeebc665fda77743ab96ede9830","abstract_canon_sha256":"6e05210d434664122a02c969981c91d00d0b477ba25f9df0acc1ecc6ecd7d0af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:14:43.226351Z","signature_b64":"OWj2/H5N8R+PMevnjvO3ojMNd9RB2Sepjmpn2rn7IzG68Y8CPUCXdZg/4Ip2VrNJMnpSqdIoQmwCZ7k8VohSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e819643ea9838c1fe8c270d40a954bc60ad24a042119201c4b76096581ba6f2","last_reissued_at":"2026-07-05T00:14:43.225883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:14:43.225883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward domain-invariant speech recognition via large scale training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Ananya Misra, Anshuman Tripathi, Arun Narayanan, Golan Pundak, Khe Chai Sim, Michiel Bacchiani, Mohamed Elfeky, Parisa Haghani, Trevor Strohman","submitted_at":"2018-08-16T00:24:49Z","abstract_excerpt":"Current state-of-the-art automatic speech recognition systems are trained to work in specific `domains', defined based on factors like application, sampling rate and codec. When such recognizers are used in conditions that do not match the training domain, performance significantly drops. This work explores the idea of building a single domain-invariant model for varied use-cases by combining large scale training data from multiple application domains. Our final system is trained using 162,000 hours of speech. Additionally, each utterance is artificially distorted during training to simulate e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.05312","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/1808.05312/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":"1808.05312","created_at":"2026-07-05T00:14:43.225942+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.05312v1","created_at":"2026-07-05T00:14:43.225942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.05312","created_at":"2026-07-05T00:14:43.225942+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2AZMQ7KTA4M","created_at":"2026-07-05T00:14:43.225942+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2AZMQ7KTA4MD7UM","created_at":"2026-07-05T00:14:43.225942+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2AZMQ7K","created_at":"2026-07-05T00:14:43.225942+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1907.05698","citing_title":"Teach an all-rounder with experts in different domains","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T2AZMQ7KTA4MD7UME4GUBKKUXR","json":"https://pith.science/pith/T2AZMQ7KTA4MD7UME4GUBKKUXR.json","graph_json":"https://pith.science/api/pith-number/T2AZMQ7KTA4MD7UME4GUBKKUXR/graph.json","events_json":"https://pith.science/api/pith-number/T2AZMQ7KTA4MD7UME4GUBKKUXR/events.json","paper":"https://pith.science/paper/T2AZMQ7K"},"agent_actions":{"view_html":"https://pith.science/pith/T2AZMQ7KTA4MD7UME4GUBKKUXR","download_json":"https://pith.science/pith/T2AZMQ7KTA4MD7UME4GUBKKUXR.json","view_paper":"https://pith.science/paper/T2AZMQ7K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.05312&json=true","fetch_graph":"https://pith.science/api/pith-number/T2AZMQ7KTA4MD7UME4GUBKKUXR/graph.json","fetch_events":"https://pith.science/api/pith-number/T2AZMQ7KTA4MD7UME4GUBKKUXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2AZMQ7KTA4MD7UME4GUBKKUXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2AZMQ7KTA4MD7UME4GUBKKUXR/action/storage_attestation","attest_author":"https://pith.science/pith/T2AZMQ7KTA4MD7UME4GUBKKUXR/action/author_attestation","sign_citation":"https://pith.science/pith/T2AZMQ7KTA4MD7UME4GUBKKUXR/action/citation_signature","submit_replication":"https://pith.science/pith/T2AZMQ7KTA4MD7UME4GUBKKUXR/action/replication_record"}},"created_at":"2026-07-05T00:14:43.225942+00:00","updated_at":"2026-07-05T00:14:43.225942+00:00"}