{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KN6WJS7QND3C2IXIKXJ35XT7KH","short_pith_number":"pith:KN6WJS7Q","schema_version":"1.0","canonical_sha256":"537d64cbf068f62d22e855d3bede7f51e82a3a319a7685074086109d4d20b7da","source":{"kind":"arxiv","id":"2111.00610","version":1},"attestation_state":"computed","paper":{"title":"Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alan W Black, Anurag Katakkar","submitted_at":"2021-10-31T22:48:30Z","abstract_excerpt":"Language models (LMs) for text data have been studied extensively for their usefulness in language generation and other downstream tasks. However, language modelling purely in the speech domain is still a relatively unexplored topic, with traditional speech LMs often depending on auxiliary text LMs for learning distributional aspects of the language. For the English language, these LMs treat words as atomic units, which presents inherent challenges to language modelling in the speech domain. In this paper, we propose a novel LSTM-based generative speech LM that is inspired by the CBOW model an"},"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":"2111.00610","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-31T22:48:30Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"10f92294f0a69e638a47448dc518b1f754be37cf4526f278b6c64280b8347a84","abstract_canon_sha256":"7696498449fc1a0507064e49933bd3b703048864be071846bf2fc1c4d93ca94c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:44.898765Z","signature_b64":"p2DaDUtuzA77JZUKjY1FMC4KLqorEQa/LokTXrL/DqDNXV4q8AMBnbe6uItbfiA2cvy40z6vUOpup4TIxi1rAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"537d64cbf068f62d22e855d3bede7f51e82a3a319a7685074086109d4d20b7da","last_reissued_at":"2026-07-05T03:27:44.898221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:44.898221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alan W Black, Anurag Katakkar","submitted_at":"2021-10-31T22:48:30Z","abstract_excerpt":"Language models (LMs) for text data have been studied extensively for their usefulness in language generation and other downstream tasks. However, language modelling purely in the speech domain is still a relatively unexplored topic, with traditional speech LMs often depending on auxiliary text LMs for learning distributional aspects of the language. For the English language, these LMs treat words as atomic units, which presents inherent challenges to language modelling in the speech domain. In this paper, we propose a novel LSTM-based generative speech LM that is inspired by the CBOW model an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00610","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/2111.00610/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":"2111.00610","created_at":"2026-07-05T03:27:44.898277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.00610v1","created_at":"2026-07-05T03:27:44.898277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00610","created_at":"2026-07-05T03:27:44.898277+00:00"},{"alias_kind":"pith_short_12","alias_value":"KN6WJS7QND3C","created_at":"2026-07-05T03:27:44.898277+00:00"},{"alias_kind":"pith_short_16","alias_value":"KN6WJS7QND3C2IXI","created_at":"2026-07-05T03:27:44.898277+00:00"},{"alias_kind":"pith_short_8","alias_value":"KN6WJS7Q","created_at":"2026-07-05T03:27:44.898277+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/KN6WJS7QND3C2IXIKXJ35XT7KH","json":"https://pith.science/pith/KN6WJS7QND3C2IXIKXJ35XT7KH.json","graph_json":"https://pith.science/api/pith-number/KN6WJS7QND3C2IXIKXJ35XT7KH/graph.json","events_json":"https://pith.science/api/pith-number/KN6WJS7QND3C2IXIKXJ35XT7KH/events.json","paper":"https://pith.science/paper/KN6WJS7Q"},"agent_actions":{"view_html":"https://pith.science/pith/KN6WJS7QND3C2IXIKXJ35XT7KH","download_json":"https://pith.science/pith/KN6WJS7QND3C2IXIKXJ35XT7KH.json","view_paper":"https://pith.science/paper/KN6WJS7Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.00610&json=true","fetch_graph":"https://pith.science/api/pith-number/KN6WJS7QND3C2IXIKXJ35XT7KH/graph.json","fetch_events":"https://pith.science/api/pith-number/KN6WJS7QND3C2IXIKXJ35XT7KH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KN6WJS7QND3C2IXIKXJ35XT7KH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KN6WJS7QND3C2IXIKXJ35XT7KH/action/storage_attestation","attest_author":"https://pith.science/pith/KN6WJS7QND3C2IXIKXJ35XT7KH/action/author_attestation","sign_citation":"https://pith.science/pith/KN6WJS7QND3C2IXIKXJ35XT7KH/action/citation_signature","submit_replication":"https://pith.science/pith/KN6WJS7QND3C2IXIKXJ35XT7KH/action/replication_record"}},"created_at":"2026-07-05T03:27:44.898277+00:00","updated_at":"2026-07-05T03:27:44.898277+00:00"}