{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MNZEIT74ZTVOBBPFZRALECHCB4","short_pith_number":"pith:MNZEIT74","schema_version":"1.0","canonical_sha256":"6372444ffccceae085e5cc40b208e20f1d4208ffea06db0a1368002ad0f9af87","source":{"kind":"arxiv","id":"2307.07468","version":2},"attestation_state":"computed","paper":{"title":"SGGNet$^2$: Speech-Scene Graph Grounding Network for Speech-guided Navigation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Daehyung Park, Dohyun Kim, Jaehwi Jang, Minjae Song, Woojin Choi, Yeseung Kim","submitted_at":"2023-07-14T16:48:53Z","abstract_excerpt":"The spoken language serves as an accessible and efficient interface, enabling non-experts and disabled users to interact with complex assistant robots. However, accurately grounding language utterances gives a significant challenge due to the acoustic variability in speakers' voices and environmental noise. In this work, we propose a novel speech-scene graph grounding network (SGGNet$^2$) that robustly grounds spoken utterances by leveraging the acoustic similarity between correctly recognized and misrecognized words obtained from automatic speech recognition (ASR) systems. To incorporate the "},"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":"2307.07468","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2023-07-14T16:48:53Z","cross_cats_sorted":[],"title_canon_sha256":"2764292f7fc22a0acb794737e7de012bf832667aee3b4c0d2c47e49b436082bd","abstract_canon_sha256":"39d35a094555047c384b1fbbb6ece81e8dca3680813b45a148ea355559c71fe4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:57.253304Z","signature_b64":"4yt1G/uy3x09yFzkeOhLYdGCyx3tzUqDQE1gPkZVVInvdmmMuiHKGJE+FHEczujnEV8ji69CZt+rOL6tNmVGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6372444ffccceae085e5cc40b208e20f1d4208ffea06db0a1368002ad0f9af87","last_reissued_at":"2026-07-05T08:07:57.252878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:57.252878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SGGNet$^2$: Speech-Scene Graph Grounding Network for Speech-guided Navigation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Daehyung Park, Dohyun Kim, Jaehwi Jang, Minjae Song, Woojin Choi, Yeseung Kim","submitted_at":"2023-07-14T16:48:53Z","abstract_excerpt":"The spoken language serves as an accessible and efficient interface, enabling non-experts and disabled users to interact with complex assistant robots. However, accurately grounding language utterances gives a significant challenge due to the acoustic variability in speakers' voices and environmental noise. In this work, we propose a novel speech-scene graph grounding network (SGGNet$^2$) that robustly grounds spoken utterances by leveraging the acoustic similarity between correctly recognized and misrecognized words obtained from automatic speech recognition (ASR) systems. To incorporate the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07468","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/2307.07468/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":"2307.07468","created_at":"2026-07-05T08:07:57.252951+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.07468v2","created_at":"2026-07-05T08:07:57.252951+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07468","created_at":"2026-07-05T08:07:57.252951+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNZEIT74ZTVO","created_at":"2026-07-05T08:07:57.252951+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNZEIT74ZTVOBBPF","created_at":"2026-07-05T08:07:57.252951+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNZEIT74","created_at":"2026-07-05T08:07:57.252951+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MNZEIT74ZTVOBBPFZRALECHCB4","json":"https://pith.science/pith/MNZEIT74ZTVOBBPFZRALECHCB4.json","graph_json":"https://pith.science/api/pith-number/MNZEIT74ZTVOBBPFZRALECHCB4/graph.json","events_json":"https://pith.science/api/pith-number/MNZEIT74ZTVOBBPFZRALECHCB4/events.json","paper":"https://pith.science/paper/MNZEIT74"},"agent_actions":{"view_html":"https://pith.science/pith/MNZEIT74ZTVOBBPFZRALECHCB4","download_json":"https://pith.science/pith/MNZEIT74ZTVOBBPFZRALECHCB4.json","view_paper":"https://pith.science/paper/MNZEIT74","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.07468&json=true","fetch_graph":"https://pith.science/api/pith-number/MNZEIT74ZTVOBBPFZRALECHCB4/graph.json","fetch_events":"https://pith.science/api/pith-number/MNZEIT74ZTVOBBPFZRALECHCB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNZEIT74ZTVOBBPFZRALECHCB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNZEIT74ZTVOBBPFZRALECHCB4/action/storage_attestation","attest_author":"https://pith.science/pith/MNZEIT74ZTVOBBPFZRALECHCB4/action/author_attestation","sign_citation":"https://pith.science/pith/MNZEIT74ZTVOBBPFZRALECHCB4/action/citation_signature","submit_replication":"https://pith.science/pith/MNZEIT74ZTVOBBPFZRALECHCB4/action/replication_record"}},"created_at":"2026-07-05T08:07:57.252951+00:00","updated_at":"2026-07-05T08:07:57.252951+00:00"}