{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DSBWBMSGKZXH2BIYBE5CADLSBG","short_pith_number":"pith:DSBWBMSG","schema_version":"1.0","canonical_sha256":"1c8360b246566e7d0518093a200d7209926c98a2528b2c6a557c9e6da21b6150","source":{"kind":"arxiv","id":"2406.12428","version":2},"attestation_state":"computed","paper":{"title":"PSLM: Parallel Generation of Text and Speech with LLMs for Low-Latency Spoken Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Kei Sawada, Kentaro Mitsui, Koh Mitsuda, Toshiaki Wakatsuki, Yukiya Hono","submitted_at":"2024-06-18T09:23:54Z","abstract_excerpt":"Multimodal language models that process both text and speech have a potential for applications in spoken dialogue systems. However, current models face two major challenges in response generation latency: (1) generating a spoken response requires the prior generation of a written response, and (2) speech sequences are significantly longer than text sequences. This study addresses these issues by extending the input and output sequences of the language model to support the parallel generation of text and speech. Our experiments on spoken question answering tasks demonstrate that our approach im"},"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":"2406.12428","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T09:23:54Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"d43326e50f375a6dd0e68ad131b1a1a5dc303a68174759f73763a429228423a7","abstract_canon_sha256":"2350bd0db8fcd9a9f129194a974d417629303bd2f699682ff3f383972793f58b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:11.791560Z","signature_b64":"NQCB4HzhsYo6/TVt5ksM9z5lWxuItOVDbjHnVm9Si1un8UdsdNubVkiCh/qsFzy7SriKmSu0YNYdq88M6kmeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c8360b246566e7d0518093a200d7209926c98a2528b2c6a557c9e6da21b6150","last_reissued_at":"2026-07-05T09:15:11.791132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:11.791132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PSLM: Parallel Generation of Text and Speech with LLMs for Low-Latency Spoken Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Kei Sawada, Kentaro Mitsui, Koh Mitsuda, Toshiaki Wakatsuki, Yukiya Hono","submitted_at":"2024-06-18T09:23:54Z","abstract_excerpt":"Multimodal language models that process both text and speech have a potential for applications in spoken dialogue systems. However, current models face two major challenges in response generation latency: (1) generating a spoken response requires the prior generation of a written response, and (2) speech sequences are significantly longer than text sequences. This study addresses these issues by extending the input and output sequences of the language model to support the parallel generation of text and speech. Our experiments on spoken question answering tasks demonstrate that our approach im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12428","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/2406.12428/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":"2406.12428","created_at":"2026-07-05T09:15:11.791188+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12428v2","created_at":"2026-07-05T09:15:11.791188+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12428","created_at":"2026-07-05T09:15:11.791188+00:00"},{"alias_kind":"pith_short_12","alias_value":"DSBWBMSGKZXH","created_at":"2026-07-05T09:15:11.791188+00:00"},{"alias_kind":"pith_short_16","alias_value":"DSBWBMSGKZXH2BIY","created_at":"2026-07-05T09:15:11.791188+00:00"},{"alias_kind":"pith_short_8","alias_value":"DSBWBMSG","created_at":"2026-07-05T09:15:11.791188+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":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DSBWBMSGKZXH2BIYBE5CADLSBG","json":"https://pith.science/pith/DSBWBMSGKZXH2BIYBE5CADLSBG.json","graph_json":"https://pith.science/api/pith-number/DSBWBMSGKZXH2BIYBE5CADLSBG/graph.json","events_json":"https://pith.science/api/pith-number/DSBWBMSGKZXH2BIYBE5CADLSBG/events.json","paper":"https://pith.science/paper/DSBWBMSG"},"agent_actions":{"view_html":"https://pith.science/pith/DSBWBMSGKZXH2BIYBE5CADLSBG","download_json":"https://pith.science/pith/DSBWBMSGKZXH2BIYBE5CADLSBG.json","view_paper":"https://pith.science/paper/DSBWBMSG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12428&json=true","fetch_graph":"https://pith.science/api/pith-number/DSBWBMSGKZXH2BIYBE5CADLSBG/graph.json","fetch_events":"https://pith.science/api/pith-number/DSBWBMSGKZXH2BIYBE5CADLSBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DSBWBMSGKZXH2BIYBE5CADLSBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DSBWBMSGKZXH2BIYBE5CADLSBG/action/storage_attestation","attest_author":"https://pith.science/pith/DSBWBMSGKZXH2BIYBE5CADLSBG/action/author_attestation","sign_citation":"https://pith.science/pith/DSBWBMSGKZXH2BIYBE5CADLSBG/action/citation_signature","submit_replication":"https://pith.science/pith/DSBWBMSGKZXH2BIYBE5CADLSBG/action/replication_record"}},"created_at":"2026-07-05T09:15:11.791188+00:00","updated_at":"2026-07-05T09:15:11.791188+00:00"}