{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IVSU7ZQLIAKOWGTL3PXREHSCUN","short_pith_number":"pith:IVSU7ZQL","schema_version":"1.0","canonical_sha256":"45654fe60b4014eb1a6bdbef121e42a37b772af465216333d8c2c385d64c6597","source":{"kind":"arxiv","id":"2305.18096","version":2},"attestation_state":"computed","paper":{"title":"Improving Textless Spoken Language Understanding with Discrete Units as Intermediate Target","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Guan-Ting Lin, Guan-Wei Wu, Hung-yi Lee, Shang-Wen Li","submitted_at":"2023-05-29T14:00:24Z","abstract_excerpt":"Spoken Language Understanding (SLU) is a task that aims to extract semantic information from spoken utterances. Previous research has made progress in end-to-end SLU by using paired speech-text data, such as pre-trained Automatic Speech Recognition (ASR) models or paired text as intermediate targets. However, acquiring paired transcripts is expensive and impractical for unwritten languages. On the other hand, Textless SLU extracts semantic information from speech without utilizing paired transcripts. However, the absence of intermediate targets and training guidance for textless SLU often resu"},"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":"2305.18096","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-29T14:00:24Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"02f8d610d593ab2614d88e85b6ad5b761639a57d696bdaad41f392418c8cc858","abstract_canon_sha256":"d54aa88da7c2b3e1b4e166977e1bf1e8bb88d79f151967db405860fbce980449"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:02.046157Z","signature_b64":"rTu4nGYCU8QARhb2327hWDVrX1OhVKz6Dz1sGn6+jMBkVO61N/p53FfEssV0g7/pkv4LKTXo9HLuew2yGXbVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45654fe60b4014eb1a6bdbef121e42a37b772af465216333d8c2c385d64c6597","last_reissued_at":"2026-07-05T06:29:02.045696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:02.045696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Textless Spoken Language Understanding with Discrete Units as Intermediate Target","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Guan-Ting Lin, Guan-Wei Wu, Hung-yi Lee, Shang-Wen Li","submitted_at":"2023-05-29T14:00:24Z","abstract_excerpt":"Spoken Language Understanding (SLU) is a task that aims to extract semantic information from spoken utterances. Previous research has made progress in end-to-end SLU by using paired speech-text data, such as pre-trained Automatic Speech Recognition (ASR) models or paired text as intermediate targets. However, acquiring paired transcripts is expensive and impractical for unwritten languages. On the other hand, Textless SLU extracts semantic information from speech without utilizing paired transcripts. However, the absence of intermediate targets and training guidance for textless SLU often resu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18096","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/2305.18096/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":"2305.18096","created_at":"2026-07-05T06:29:02.045757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18096v2","created_at":"2026-07-05T06:29:02.045757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18096","created_at":"2026-07-05T06:29:02.045757+00:00"},{"alias_kind":"pith_short_12","alias_value":"IVSU7ZQLIAKO","created_at":"2026-07-05T06:29:02.045757+00:00"},{"alias_kind":"pith_short_16","alias_value":"IVSU7ZQLIAKOWGTL","created_at":"2026-07-05T06:29:02.045757+00:00"},{"alias_kind":"pith_short_8","alias_value":"IVSU7ZQL","created_at":"2026-07-05T06:29:02.045757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.11598","citing_title":"Representing Speech Through Autoregressive Prediction of Cochlear Tokens","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IVSU7ZQLIAKOWGTL3PXREHSCUN","json":"https://pith.science/pith/IVSU7ZQLIAKOWGTL3PXREHSCUN.json","graph_json":"https://pith.science/api/pith-number/IVSU7ZQLIAKOWGTL3PXREHSCUN/graph.json","events_json":"https://pith.science/api/pith-number/IVSU7ZQLIAKOWGTL3PXREHSCUN/events.json","paper":"https://pith.science/paper/IVSU7ZQL"},"agent_actions":{"view_html":"https://pith.science/pith/IVSU7ZQLIAKOWGTL3PXREHSCUN","download_json":"https://pith.science/pith/IVSU7ZQLIAKOWGTL3PXREHSCUN.json","view_paper":"https://pith.science/paper/IVSU7ZQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18096&json=true","fetch_graph":"https://pith.science/api/pith-number/IVSU7ZQLIAKOWGTL3PXREHSCUN/graph.json","fetch_events":"https://pith.science/api/pith-number/IVSU7ZQLIAKOWGTL3PXREHSCUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IVSU7ZQLIAKOWGTL3PXREHSCUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IVSU7ZQLIAKOWGTL3PXREHSCUN/action/storage_attestation","attest_author":"https://pith.science/pith/IVSU7ZQLIAKOWGTL3PXREHSCUN/action/author_attestation","sign_citation":"https://pith.science/pith/IVSU7ZQLIAKOWGTL3PXREHSCUN/action/citation_signature","submit_replication":"https://pith.science/pith/IVSU7ZQLIAKOWGTL3PXREHSCUN/action/replication_record"}},"created_at":"2026-07-05T06:29:02.045757+00:00","updated_at":"2026-07-05T06:29:02.045757+00:00"}