{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SYJHUXMKBTTMX3LQ5MSFQLME64","short_pith_number":"pith:SYJHUXMK","schema_version":"1.0","canonical_sha256":"96127a5d8a0ce6cbed70eb24582d84f72427fc23c96379dc0024a1d600c7afe5","source":{"kind":"arxiv","id":"2409.03701","version":2},"attestation_state":"computed","paper":{"title":"LAST: Language Model Aware Speech Tokenization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Arnon Turetzky, Yossi Adi","submitted_at":"2024-09-05T16:57:39Z","abstract_excerpt":"Speech tokenization serves as the foundation of speech language model (LM), enabling them to perform various tasks such as spoken language modeling, text-to-speech, speech-to-text, etc. Most speech tokenizers are trained independently of the LM training process, relying on separate acoustic models and quantization methods. Following such an approach may create a mismatch between the tokenization process and its usage afterward. In this study, we propose a novel approach to training a speech tokenizer by leveraging objectives from pre-trained textual LMs. We advocate for the integration of this"},"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":"2409.03701","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T16:57:39Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"e6c872528333d26220c398208742008ed6c7cfa32bfac3b98ebf58bedb207085","abstract_canon_sha256":"74cc85ac45f2edd735f43c69c4c19f57c996c60d58e36b36141be368f97d45ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:19.075618Z","signature_b64":"0Zs9blh6qPVevMVCuv+C8vgVmNy4kPA+vZPqSR1vhhqTWj3shCx3eBlSRjJP4W58KPF1CLlvawV7a4ioS7CWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96127a5d8a0ce6cbed70eb24582d84f72427fc23c96379dc0024a1d600c7afe5","last_reissued_at":"2026-07-05T09:05:19.075162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:19.075162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LAST: Language Model Aware Speech Tokenization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Arnon Turetzky, Yossi Adi","submitted_at":"2024-09-05T16:57:39Z","abstract_excerpt":"Speech tokenization serves as the foundation of speech language model (LM), enabling them to perform various tasks such as spoken language modeling, text-to-speech, speech-to-text, etc. Most speech tokenizers are trained independently of the LM training process, relying on separate acoustic models and quantization methods. Following such an approach may create a mismatch between the tokenization process and its usage afterward. In this study, we propose a novel approach to training a speech tokenizer by leveraging objectives from pre-trained textual LMs. We advocate for the integration of this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03701","kind":"arxiv","version":2},"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/2409.03701/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":"2409.03701","created_at":"2026-07-05T09:05:19.075218+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.03701v2","created_at":"2026-07-05T09:05:19.075218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03701","created_at":"2026-07-05T09:05:19.075218+00:00"},{"alias_kind":"pith_short_12","alias_value":"SYJHUXMKBTTM","created_at":"2026-07-05T09:05:19.075218+00:00"},{"alias_kind":"pith_short_16","alias_value":"SYJHUXMKBTTMX3LQ","created_at":"2026-07-05T09:05:19.075218+00:00"},{"alias_kind":"pith_short_8","alias_value":"SYJHUXMK","created_at":"2026-07-05T09:05:19.075218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.08528","citing_title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SYJHUXMKBTTMX3LQ5MSFQLME64","json":"https://pith.science/pith/SYJHUXMKBTTMX3LQ5MSFQLME64.json","graph_json":"https://pith.science/api/pith-number/SYJHUXMKBTTMX3LQ5MSFQLME64/graph.json","events_json":"https://pith.science/api/pith-number/SYJHUXMKBTTMX3LQ5MSFQLME64/events.json","paper":"https://pith.science/paper/SYJHUXMK"},"agent_actions":{"view_html":"https://pith.science/pith/SYJHUXMKBTTMX3LQ5MSFQLME64","download_json":"https://pith.science/pith/SYJHUXMKBTTMX3LQ5MSFQLME64.json","view_paper":"https://pith.science/paper/SYJHUXMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.03701&json=true","fetch_graph":"https://pith.science/api/pith-number/SYJHUXMKBTTMX3LQ5MSFQLME64/graph.json","fetch_events":"https://pith.science/api/pith-number/SYJHUXMKBTTMX3LQ5MSFQLME64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SYJHUXMKBTTMX3LQ5MSFQLME64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SYJHUXMKBTTMX3LQ5MSFQLME64/action/storage_attestation","attest_author":"https://pith.science/pith/SYJHUXMKBTTMX3LQ5MSFQLME64/action/author_attestation","sign_citation":"https://pith.science/pith/SYJHUXMKBTTMX3LQ5MSFQLME64/action/citation_signature","submit_replication":"https://pith.science/pith/SYJHUXMKBTTMX3LQ5MSFQLME64/action/replication_record"}},"created_at":"2026-07-05T09:05:19.075218+00:00","updated_at":"2026-07-05T09:05:19.075218+00:00"}