{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SQCIQHCMV3H2BO3MDYLAKDAFUA","short_pith_number":"pith:SQCIQHCM","schema_version":"1.0","canonical_sha256":"9404881c4caecfa0bb6c1e16050c05a00bab4d2c84bacd4aa3eee899b56917aa","source":{"kind":"arxiv","id":"2409.00800","version":1},"attestation_state":"computed","paper":{"title":"Comparing Discrete and Continuous Space LLMs for Speech Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dong Yu, Jianwei Yu, Shi-Xiong Zhang, Yaoxun Xu, Zhiyong Wu","submitted_at":"2024-09-01T18:29:45Z","abstract_excerpt":"This paper investigates discrete and continuous speech representations in Large Language Model (LLM)-based Automatic Speech Recognition (ASR), organizing them by feature continuity and training approach into four categories: supervised and unsupervised for both discrete and continuous types. We further classify LLMs based on their input and autoregressive feedback into continuous and discrete-space models. Using specialized encoders and comparative analysis with a Joint-Training-From-Scratch Language Model (JTFS LM) and pre-trained LLaMA2-7b, we provide a detailed examination of their effectiv"},"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":"2409.00800","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-01T18:29:45Z","cross_cats_sorted":[],"title_canon_sha256":"e63ff5400eee7446912c2dfbb1dc0adc52c1c6c1fc1a636e20cdc168a69d37e0","abstract_canon_sha256":"e78aac280e6ae2bb81263362bba4636c41fca14ec3087f152992c1746f910c8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:53.604944Z","signature_b64":"FhOyAcByROXyL6tH7t8vp1EnVjKM0oOPr/FJlaNDtiWeo86fLuNxu6b2fgNjn5XCT6Ex7ygSNeWs0BHggTa/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9404881c4caecfa0bb6c1e16050c05a00bab4d2c84bacd4aa3eee899b56917aa","last_reissued_at":"2026-07-05T09:01:53.604534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:53.604534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparing Discrete and Continuous Space LLMs for Speech Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dong Yu, Jianwei Yu, Shi-Xiong Zhang, Yaoxun Xu, Zhiyong Wu","submitted_at":"2024-09-01T18:29:45Z","abstract_excerpt":"This paper investigates discrete and continuous speech representations in Large Language Model (LLM)-based Automatic Speech Recognition (ASR), organizing them by feature continuity and training approach into four categories: supervised and unsupervised for both discrete and continuous types. We further classify LLMs based on their input and autoregressive feedback into continuous and discrete-space models. Using specialized encoders and comparative analysis with a Joint-Training-From-Scratch Language Model (JTFS LM) and pre-trained LLaMA2-7b, we provide a detailed examination of their effectiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00800","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/2409.00800/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":"2409.00800","created_at":"2026-07-05T09:01:53.604592+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00800v1","created_at":"2026-07-05T09:01:53.604592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00800","created_at":"2026-07-05T09:01:53.604592+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQCIQHCMV3H2","created_at":"2026-07-05T09:01:53.604592+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQCIQHCMV3H2BO3M","created_at":"2026-07-05T09:01:53.604592+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQCIQHCM","created_at":"2026-07-05T09:01:53.604592+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10368","citing_title":"Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and Translation","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SQCIQHCMV3H2BO3MDYLAKDAFUA","json":"https://pith.science/pith/SQCIQHCMV3H2BO3MDYLAKDAFUA.json","graph_json":"https://pith.science/api/pith-number/SQCIQHCMV3H2BO3MDYLAKDAFUA/graph.json","events_json":"https://pith.science/api/pith-number/SQCIQHCMV3H2BO3MDYLAKDAFUA/events.json","paper":"https://pith.science/paper/SQCIQHCM"},"agent_actions":{"view_html":"https://pith.science/pith/SQCIQHCMV3H2BO3MDYLAKDAFUA","download_json":"https://pith.science/pith/SQCIQHCMV3H2BO3MDYLAKDAFUA.json","view_paper":"https://pith.science/paper/SQCIQHCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00800&json=true","fetch_graph":"https://pith.science/api/pith-number/SQCIQHCMV3H2BO3MDYLAKDAFUA/graph.json","fetch_events":"https://pith.science/api/pith-number/SQCIQHCMV3H2BO3MDYLAKDAFUA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQCIQHCMV3H2BO3MDYLAKDAFUA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQCIQHCMV3H2BO3MDYLAKDAFUA/action/storage_attestation","attest_author":"https://pith.science/pith/SQCIQHCMV3H2BO3MDYLAKDAFUA/action/author_attestation","sign_citation":"https://pith.science/pith/SQCIQHCMV3H2BO3MDYLAKDAFUA/action/citation_signature","submit_replication":"https://pith.science/pith/SQCIQHCMV3H2BO3MDYLAKDAFUA/action/replication_record"}},"created_at":"2026-07-05T09:01:53.604592+00:00","updated_at":"2026-07-05T09:01:53.604592+00:00"}