{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VOY4UB3VAPEU5FSO5EDAIKSKW4","short_pith_number":"pith:VOY4UB3V","schema_version":"1.0","canonical_sha256":"abb1ca077503c94e964ee906042a4ab725e1494d6ee0aabeedd34c97c00985de","source":{"kind":"arxiv","id":"2212.13015","version":1},"attestation_state":"computed","paper":{"title":"Skit-S2I: An Indian Accented Speech to Intent dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Kumarmanas Nethil, Shangeth Rajaa, Swaraj Dalmia","submitted_at":"2022-12-26T05:10:43Z","abstract_excerpt":"Conventional conversation assistants extract text transcripts from the speech signal using automatic speech recognition (ASR) and then predict intent from the transcriptions. Using end-to-end spoken language understanding (SLU), the intents of the speaker are predicted directly from the speech signal without requiring intermediate text transcripts. As a result, the model can optimize directly for intent classification and avoid cascading errors from ASR. The end-to-end SLU system also helps in reducing the latency of the intent prediction model. Although many datasets are available publicly fo"},"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":"2212.13015","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-26T05:10:43Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"a5cf78fada99eba95aadfcd8a49a80aedef1e0cac22b5d258cd223fe6e3a42a0","abstract_canon_sha256":"58b33fe0322c4e622b4e7f2f5b22809479601c37f17d1b721b2b246fc6fa3a24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:28:15.802467Z","signature_b64":"mC0xDGqNpufI5iwJeoS0/Z/8x5hqv+LQ3Pkl8nkFNLRTw5xJz527RrK/hoVJO2liGK3OQZ7SscvcalAsP4UBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abb1ca077503c94e964ee906042a4ab725e1494d6ee0aabeedd34c97c00985de","last_reissued_at":"2026-07-05T05:28:15.802003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:28:15.802003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skit-S2I: An Indian Accented Speech to Intent dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Kumarmanas Nethil, Shangeth Rajaa, Swaraj Dalmia","submitted_at":"2022-12-26T05:10:43Z","abstract_excerpt":"Conventional conversation assistants extract text transcripts from the speech signal using automatic speech recognition (ASR) and then predict intent from the transcriptions. Using end-to-end spoken language understanding (SLU), the intents of the speaker are predicted directly from the speech signal without requiring intermediate text transcripts. As a result, the model can optimize directly for intent classification and avoid cascading errors from ASR. The end-to-end SLU system also helps in reducing the latency of the intent prediction model. Although many datasets are available publicly fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.13015","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/2212.13015/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":"2212.13015","created_at":"2026-07-05T05:28:15.802079+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.13015v1","created_at":"2026-07-05T05:28:15.802079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.13015","created_at":"2026-07-05T05:28:15.802079+00:00"},{"alias_kind":"pith_short_12","alias_value":"VOY4UB3VAPEU","created_at":"2026-07-05T05:28:15.802079+00:00"},{"alias_kind":"pith_short_16","alias_value":"VOY4UB3VAPEU5FSO","created_at":"2026-07-05T05:28:15.802079+00:00"},{"alias_kind":"pith_short_8","alias_value":"VOY4UB3V","created_at":"2026-07-05T05:28:15.802079+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18423","citing_title":"BhashaSutra: A Task-Centric Unified Survey of Indian NLP Datasets, Corpora, and Resources","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VOY4UB3VAPEU5FSO5EDAIKSKW4","json":"https://pith.science/pith/VOY4UB3VAPEU5FSO5EDAIKSKW4.json","graph_json":"https://pith.science/api/pith-number/VOY4UB3VAPEU5FSO5EDAIKSKW4/graph.json","events_json":"https://pith.science/api/pith-number/VOY4UB3VAPEU5FSO5EDAIKSKW4/events.json","paper":"https://pith.science/paper/VOY4UB3V"},"agent_actions":{"view_html":"https://pith.science/pith/VOY4UB3VAPEU5FSO5EDAIKSKW4","download_json":"https://pith.science/pith/VOY4UB3VAPEU5FSO5EDAIKSKW4.json","view_paper":"https://pith.science/paper/VOY4UB3V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.13015&json=true","fetch_graph":"https://pith.science/api/pith-number/VOY4UB3VAPEU5FSO5EDAIKSKW4/graph.json","fetch_events":"https://pith.science/api/pith-number/VOY4UB3VAPEU5FSO5EDAIKSKW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VOY4UB3VAPEU5FSO5EDAIKSKW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VOY4UB3VAPEU5FSO5EDAIKSKW4/action/storage_attestation","attest_author":"https://pith.science/pith/VOY4UB3VAPEU5FSO5EDAIKSKW4/action/author_attestation","sign_citation":"https://pith.science/pith/VOY4UB3VAPEU5FSO5EDAIKSKW4/action/citation_signature","submit_replication":"https://pith.science/pith/VOY4UB3VAPEU5FSO5EDAIKSKW4/action/replication_record"}},"created_at":"2026-07-05T05:28:15.802079+00:00","updated_at":"2026-07-05T05:28:15.802079+00:00"}