{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7JL7PVPANAPAVBVVH6OTJGFJVA","short_pith_number":"pith:7JL7PVPA","schema_version":"1.0","canonical_sha256":"fa57f7d5e0681e0a86b53f9d3498a9a8371f641d9299b5d803c4c8ec42b77407","source":{"kind":"arxiv","id":"2208.13321","version":1},"attestation_state":"computed","paper":{"title":"Turn-Taking Prediction for Natural Conversational Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bo Li, Chao Zhang, Qiao Liang, Shuo-yiin Chang, Tara N. Sainath, Trevor Strohman, Yanzhang He","submitted_at":"2022-08-29T01:09:23Z","abstract_excerpt":"While a streaming voice assistant system has been used in many applications, this system typically focuses on unnatural, one-shot interactions assuming input from a single voice query without hesitation or disfluency. However, a common conversational utterance often involves multiple queries with turn-taking, in addition to disfluencies. These disfluencies include pausing to think, hesitations, word lengthening, filled pauses and repeated phrases. This makes doing speech recognition with conversational speech, including one with multiple queries, a challenging task. To better model the convers"},"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":"2208.13321","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-08-29T01:09:23Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"262f53ab6ff20a02c36aa3afa23e321c72575874cca2c5642c0f484148c82363","abstract_canon_sha256":"cbe2b9485229ff4f25de04076c8641b1b414291c8aed81a553c9ccca8f41e2ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:52:07.413955Z","signature_b64":"b+LOcvPk7gcfuQXqcRWwIRpJUwgfmfD5ljUf3kiBjMH+JWNuSsn8jtZlXctcPslset2znBb8jz6Iu0dKqY7NAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa57f7d5e0681e0a86b53f9d3498a9a8371f641d9299b5d803c4c8ec42b77407","last_reissued_at":"2026-07-05T04:52:07.413523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:52:07.413523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Turn-Taking Prediction for Natural Conversational Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bo Li, Chao Zhang, Qiao Liang, Shuo-yiin Chang, Tara N. Sainath, Trevor Strohman, Yanzhang He","submitted_at":"2022-08-29T01:09:23Z","abstract_excerpt":"While a streaming voice assistant system has been used in many applications, this system typically focuses on unnatural, one-shot interactions assuming input from a single voice query without hesitation or disfluency. However, a common conversational utterance often involves multiple queries with turn-taking, in addition to disfluencies. These disfluencies include pausing to think, hesitations, word lengthening, filled pauses and repeated phrases. This makes doing speech recognition with conversational speech, including one with multiple queries, a challenging task. To better model the convers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.13321","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/2208.13321/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":"2208.13321","created_at":"2026-07-05T04:52:07.413588+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.13321v1","created_at":"2026-07-05T04:52:07.413588+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.13321","created_at":"2026-07-05T04:52:07.413588+00:00"},{"alias_kind":"pith_short_12","alias_value":"7JL7PVPANAPA","created_at":"2026-07-05T04:52:07.413588+00:00"},{"alias_kind":"pith_short_16","alias_value":"7JL7PVPANAPAVBVV","created_at":"2026-07-05T04:52:07.413588+00:00"},{"alias_kind":"pith_short_8","alias_value":"7JL7PVPA","created_at":"2026-07-05T04:52:07.413588+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00383","citing_title":"Proactive Conversational Agents with Inner Thoughts","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7JL7PVPANAPAVBVVH6OTJGFJVA","json":"https://pith.science/pith/7JL7PVPANAPAVBVVH6OTJGFJVA.json","graph_json":"https://pith.science/api/pith-number/7JL7PVPANAPAVBVVH6OTJGFJVA/graph.json","events_json":"https://pith.science/api/pith-number/7JL7PVPANAPAVBVVH6OTJGFJVA/events.json","paper":"https://pith.science/paper/7JL7PVPA"},"agent_actions":{"view_html":"https://pith.science/pith/7JL7PVPANAPAVBVVH6OTJGFJVA","download_json":"https://pith.science/pith/7JL7PVPANAPAVBVVH6OTJGFJVA.json","view_paper":"https://pith.science/paper/7JL7PVPA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.13321&json=true","fetch_graph":"https://pith.science/api/pith-number/7JL7PVPANAPAVBVVH6OTJGFJVA/graph.json","fetch_events":"https://pith.science/api/pith-number/7JL7PVPANAPAVBVVH6OTJGFJVA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7JL7PVPANAPAVBVVH6OTJGFJVA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7JL7PVPANAPAVBVVH6OTJGFJVA/action/storage_attestation","attest_author":"https://pith.science/pith/7JL7PVPANAPAVBVVH6OTJGFJVA/action/author_attestation","sign_citation":"https://pith.science/pith/7JL7PVPANAPAVBVVH6OTJGFJVA/action/citation_signature","submit_replication":"https://pith.science/pith/7JL7PVPANAPAVBVVH6OTJGFJVA/action/replication_record"}},"created_at":"2026-07-05T04:52:07.413588+00:00","updated_at":"2026-07-05T04:52:07.413588+00:00"}