{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QXFA426CSRJK6DQOHHZSXPQIXW","short_pith_number":"pith:QXFA426C","schema_version":"1.0","canonical_sha256":"85ca0e6bc29452af0e0e39f32bbe08bda2ba5cc23df1684f964f5c6d11f1eb1c","source":{"kind":"arxiv","id":"2406.09345","version":1},"attestation_state":"computed","paper":{"title":"DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Karen Livescu, Kwangyoun Kim, Prashant Sridhar, Shinji Watanabe, Suwon Shon, Yi-Te Hsu","submitted_at":"2024-06-13T17:28:13Z","abstract_excerpt":"The integration of pre-trained text-based large language models (LLM) with speech input has enabled instruction-following capabilities for diverse speech tasks. This integration requires the use of a speech encoder, a speech adapter, and an LLM, trained on diverse tasks. We propose the use of discrete speech units (DSU), rather than continuous-valued speech encoder outputs, that are converted to the LLM token embedding space using the speech adapter. We generate DSU using a self-supervised speech encoder followed by k-means clustering. The proposed model shows robust performance on speech inpu"},"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":"2406.09345","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T17:28:13Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"ccb92ae8d756fd0faa2b0aa753ed6114f2bdf181d79b80d2711aae1d29ac3f75","abstract_canon_sha256":"cf4c88825fa817137d9fadcb8976dc65298327ac0e6794a687e08907ce60124b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:31.615468Z","signature_b64":"JHdyrQYvm3EMBebX0SC244zw38wHRsVBjA+Q6/uUbSgGi93AdMSwBVxi0JS+5xLvDdOsW08fWtsB52ZbGOlyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85ca0e6bc29452af0e0e39f32bbe08bda2ba5cc23df1684f964f5c6d11f1eb1c","last_reissued_at":"2026-07-05T08:31:31.614970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:31.614970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Karen Livescu, Kwangyoun Kim, Prashant Sridhar, Shinji Watanabe, Suwon Shon, Yi-Te Hsu","submitted_at":"2024-06-13T17:28:13Z","abstract_excerpt":"The integration of pre-trained text-based large language models (LLM) with speech input has enabled instruction-following capabilities for diverse speech tasks. This integration requires the use of a speech encoder, a speech adapter, and an LLM, trained on diverse tasks. We propose the use of discrete speech units (DSU), rather than continuous-valued speech encoder outputs, that are converted to the LLM token embedding space using the speech adapter. We generate DSU using a self-supervised speech encoder followed by k-means clustering. The proposed model shows robust performance on speech inpu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09345","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/2406.09345/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":"2406.09345","created_at":"2026-07-05T08:31:31.615026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09345v1","created_at":"2026-07-05T08:31:31.615026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09345","created_at":"2026-07-05T08:31:31.615026+00:00"},{"alias_kind":"pith_short_12","alias_value":"QXFA426CSRJK","created_at":"2026-07-05T08:31:31.615026+00:00"},{"alias_kind":"pith_short_16","alias_value":"QXFA426CSRJK6DQO","created_at":"2026-07-05T08:31:31.615026+00:00"},{"alias_kind":"pith_short_8","alias_value":"QXFA426C","created_at":"2026-07-05T08:31:31.615026+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":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QXFA426CSRJK6DQOHHZSXPQIXW","json":"https://pith.science/pith/QXFA426CSRJK6DQOHHZSXPQIXW.json","graph_json":"https://pith.science/api/pith-number/QXFA426CSRJK6DQOHHZSXPQIXW/graph.json","events_json":"https://pith.science/api/pith-number/QXFA426CSRJK6DQOHHZSXPQIXW/events.json","paper":"https://pith.science/paper/QXFA426C"},"agent_actions":{"view_html":"https://pith.science/pith/QXFA426CSRJK6DQOHHZSXPQIXW","download_json":"https://pith.science/pith/QXFA426CSRJK6DQOHHZSXPQIXW.json","view_paper":"https://pith.science/paper/QXFA426C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09345&json=true","fetch_graph":"https://pith.science/api/pith-number/QXFA426CSRJK6DQOHHZSXPQIXW/graph.json","fetch_events":"https://pith.science/api/pith-number/QXFA426CSRJK6DQOHHZSXPQIXW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QXFA426CSRJK6DQOHHZSXPQIXW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QXFA426CSRJK6DQOHHZSXPQIXW/action/storage_attestation","attest_author":"https://pith.science/pith/QXFA426CSRJK6DQOHHZSXPQIXW/action/author_attestation","sign_citation":"https://pith.science/pith/QXFA426CSRJK6DQOHHZSXPQIXW/action/citation_signature","submit_replication":"https://pith.science/pith/QXFA426CSRJK6DQOHHZSXPQIXW/action/replication_record"}},"created_at":"2026-07-05T08:31:31.615026+00:00","updated_at":"2026-07-05T08:31:31.615026+00:00"}