{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6ZXGQMZGRIWKB3GH3XLJLHNXAX","short_pith_number":"pith:6ZXGQMZG","schema_version":"1.0","canonical_sha256":"f66e6833268a2ca0ecc7ddd6959db705db5233b0222a9453c462318191fa86a1","source":{"kind":"arxiv","id":"2305.02937","version":2},"attestation_state":"computed","paper":{"title":"End-to-end spoken language understanding using joint CTC loss and self-supervised, pretrained acoustic encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Clement Chung, Jixuan Wang, Kai Wei, Martin Radfar","submitted_at":"2023-05-04T15:36:37Z","abstract_excerpt":"It is challenging to extract semantic meanings directly from audio signals in spoken language understanding (SLU), due to the lack of textual information. Popular end-to-end (E2E) SLU models utilize sequence-to-sequence automatic speech recognition (ASR) models to extract textual embeddings as input to infer semantics, which, however, require computationally expensive auto-regressive decoding. In this work, we leverage self-supervised acoustic encoders fine-tuned with Connectionist Temporal Classification (CTC) to extract textual embeddings and use joint CTC and SLU losses for utterance-level "},"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":"2305.02937","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-04T15:36:37Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"e879febcaa1d77f8777e116466f768a143bfec547df9d0b56272608669bbdef7","abstract_canon_sha256":"1599895aeaa11db2f3863ee75025c61582c1223e81b89083087207adc31f14a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:50.095238Z","signature_b64":"cicc0XObgJ1on99wgazSbfQ+5biffZdyHnxyDf1Od0p8OuHN+vPcWsNzdtEneNK9KToP0JSjvf59jGkB/7bSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f66e6833268a2ca0ecc7ddd6959db705db5233b0222a9453c462318191fa86a1","last_reissued_at":"2026-07-05T06:16:50.094851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:50.094851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-end spoken language understanding using joint CTC loss and self-supervised, pretrained acoustic encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Clement Chung, Jixuan Wang, Kai Wei, Martin Radfar","submitted_at":"2023-05-04T15:36:37Z","abstract_excerpt":"It is challenging to extract semantic meanings directly from audio signals in spoken language understanding (SLU), due to the lack of textual information. Popular end-to-end (E2E) SLU models utilize sequence-to-sequence automatic speech recognition (ASR) models to extract textual embeddings as input to infer semantics, which, however, require computationally expensive auto-regressive decoding. In this work, we leverage self-supervised acoustic encoders fine-tuned with Connectionist Temporal Classification (CTC) to extract textual embeddings and use joint CTC and SLU losses for utterance-level "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02937","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/2305.02937/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":"2305.02937","created_at":"2026-07-05T06:16:50.094906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.02937v2","created_at":"2026-07-05T06:16:50.094906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02937","created_at":"2026-07-05T06:16:50.094906+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ZXGQMZGRIWK","created_at":"2026-07-05T06:16:50.094906+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ZXGQMZGRIWKB3GH","created_at":"2026-07-05T06:16:50.094906+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ZXGQMZG","created_at":"2026-07-05T06:16:50.094906+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/6ZXGQMZGRIWKB3GH3XLJLHNXAX","json":"https://pith.science/pith/6ZXGQMZGRIWKB3GH3XLJLHNXAX.json","graph_json":"https://pith.science/api/pith-number/6ZXGQMZGRIWKB3GH3XLJLHNXAX/graph.json","events_json":"https://pith.science/api/pith-number/6ZXGQMZGRIWKB3GH3XLJLHNXAX/events.json","paper":"https://pith.science/paper/6ZXGQMZG"},"agent_actions":{"view_html":"https://pith.science/pith/6ZXGQMZGRIWKB3GH3XLJLHNXAX","download_json":"https://pith.science/pith/6ZXGQMZGRIWKB3GH3XLJLHNXAX.json","view_paper":"https://pith.science/paper/6ZXGQMZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.02937&json=true","fetch_graph":"https://pith.science/api/pith-number/6ZXGQMZGRIWKB3GH3XLJLHNXAX/graph.json","fetch_events":"https://pith.science/api/pith-number/6ZXGQMZGRIWKB3GH3XLJLHNXAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ZXGQMZGRIWKB3GH3XLJLHNXAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ZXGQMZGRIWKB3GH3XLJLHNXAX/action/storage_attestation","attest_author":"https://pith.science/pith/6ZXGQMZGRIWKB3GH3XLJLHNXAX/action/author_attestation","sign_citation":"https://pith.science/pith/6ZXGQMZGRIWKB3GH3XLJLHNXAX/action/citation_signature","submit_replication":"https://pith.science/pith/6ZXGQMZGRIWKB3GH3XLJLHNXAX/action/replication_record"}},"created_at":"2026-07-05T06:16:50.094906+00:00","updated_at":"2026-07-05T06:16:50.094906+00:00"}