{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LE762K262EPUFUSVBSR55PYYR4","short_pith_number":"pith:LE762K26","schema_version":"1.0","canonical_sha256":"593fed2b5ed11f42d2550ca3debf188f114a9a946117faa779e5be95c9f75822","source":{"kind":"arxiv","id":"2406.05547","version":1},"attestation_state":"computed","paper":{"title":"Exploring the Benefits of Tokenization of Discrete Acoustic Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Avihu Dekel, Raul Fernandez","submitted_at":"2024-06-08T18:34:28Z","abstract_excerpt":"Tokenization algorithms that merge the units of a base vocabulary into larger, variable-rate units have become standard in natural language processing tasks. This idea, however, has been mostly overlooked when the vocabulary consists of phonemes or Discrete Acoustic Units (DAUs), an audio-based representation that is playing an increasingly important role due to the success of discrete language-modeling techniques. In this paper, we showcase the advantages of tokenization of phonetic units and of DAUs on three prediction tasks: grapheme-to-phoneme, grapheme-to-DAUs, and unsupervised speech gen"},"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":"2406.05547","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-08T18:34:28Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"5e62443fbd72b70fd6d0f28edb4e2301ee6d33819f8da8d32590c6b1174eac17","abstract_canon_sha256":"b74ef006749ed3ff3c8efd20cb559e000a97702cb37db58910bda69cade303c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:29.702569Z","signature_b64":"bgOOsqIDurN+J7Aj1XYEIVqUBZDCXTPvkCYfFJn5OKE4figeKv0g5bpMkvFvmHfYcKfsIZ9mMVJ9rldCxk90CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"593fed2b5ed11f42d2550ca3debf188f114a9a946117faa779e5be95c9f75822","last_reissued_at":"2026-07-05T08:29:29.702146Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:29.702146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring the Benefits of Tokenization of Discrete Acoustic Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Avihu Dekel, Raul Fernandez","submitted_at":"2024-06-08T18:34:28Z","abstract_excerpt":"Tokenization algorithms that merge the units of a base vocabulary into larger, variable-rate units have become standard in natural language processing tasks. This idea, however, has been mostly overlooked when the vocabulary consists of phonemes or Discrete Acoustic Units (DAUs), an audio-based representation that is playing an increasingly important role due to the success of discrete language-modeling techniques. In this paper, we showcase the advantages of tokenization of phonetic units and of DAUs on three prediction tasks: grapheme-to-phoneme, grapheme-to-DAUs, and unsupervised speech gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05547","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/2406.05547/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":"2406.05547","created_at":"2026-07-05T08:29:29.702201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.05547v1","created_at":"2026-07-05T08:29:29.702201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05547","created_at":"2026-07-05T08:29:29.702201+00:00"},{"alias_kind":"pith_short_12","alias_value":"LE762K262EPU","created_at":"2026-07-05T08:29:29.702201+00:00"},{"alias_kind":"pith_short_16","alias_value":"LE762K262EPUFUSV","created_at":"2026-07-05T08:29:29.702201+00:00"},{"alias_kind":"pith_short_8","alias_value":"LE762K26","created_at":"2026-07-05T08:29:29.702201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.17863","citing_title":"Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LE762K262EPUFUSVBSR55PYYR4","json":"https://pith.science/pith/LE762K262EPUFUSVBSR55PYYR4.json","graph_json":"https://pith.science/api/pith-number/LE762K262EPUFUSVBSR55PYYR4/graph.json","events_json":"https://pith.science/api/pith-number/LE762K262EPUFUSVBSR55PYYR4/events.json","paper":"https://pith.science/paper/LE762K26"},"agent_actions":{"view_html":"https://pith.science/pith/LE762K262EPUFUSVBSR55PYYR4","download_json":"https://pith.science/pith/LE762K262EPUFUSVBSR55PYYR4.json","view_paper":"https://pith.science/paper/LE762K26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.05547&json=true","fetch_graph":"https://pith.science/api/pith-number/LE762K262EPUFUSVBSR55PYYR4/graph.json","fetch_events":"https://pith.science/api/pith-number/LE762K262EPUFUSVBSR55PYYR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LE762K262EPUFUSVBSR55PYYR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LE762K262EPUFUSVBSR55PYYR4/action/storage_attestation","attest_author":"https://pith.science/pith/LE762K262EPUFUSVBSR55PYYR4/action/author_attestation","sign_citation":"https://pith.science/pith/LE762K262EPUFUSVBSR55PYYR4/action/citation_signature","submit_replication":"https://pith.science/pith/LE762K262EPUFUSVBSR55PYYR4/action/replication_record"}},"created_at":"2026-07-05T08:29:29.702201+00:00","updated_at":"2026-07-05T08:29:29.702201+00:00"}