{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5QWP722OLF5PWZOIB4W4PHMZRG","short_pith_number":"pith:5QWP722O","schema_version":"1.0","canonical_sha256":"ec2cffeb4e597afb65c80f2dc79d9989a3481c24819ae7588aea43f0b86be830","source":{"kind":"arxiv","id":"2307.15097","version":1},"attestation_state":"computed","paper":{"title":"Cascaded Cross-Modal Transformer for Request and Complaint Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.CL","authors_text":"Nicolae-Catalin Ristea, Radu Tudor Ionescu","submitted_at":"2023-07-27T13:45:42Z","abstract_excerpt":"We propose a novel cascaded cross-modal transformer (CCMT) that combines speech and text transcripts to detect customer requests and complaints in phone conversations. Our approach leverages a multimodal paradigm by transcribing the speech using automatic speech recognition (ASR) models and translating the transcripts into different languages. Subsequently, we combine language-specific BERT-based models with Wav2Vec2.0 audio features in a novel cascaded cross-attention transformer model. We apply our system to the Requests Sub-Challenge of the ACM Multimedia 2023 Computational Paralinguistics "},"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":"2307.15097","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-27T13:45:42Z","cross_cats_sorted":["cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"11c3e1bda491d590cb06df54b0f53ac2507e589ab7d2c8b54386ae1f4cc0571d","abstract_canon_sha256":"16e722fa204e946e18cefdbcf40f391a29a8866f248d3aedb97dbddff7854058"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:30.402539Z","signature_b64":"k0S2tHo9lgsAIlcCb2LdZ2L1iwjdZv1Z6AXSYjKW0gfjLPcQsq5ZC2KnxvtNksbnECda09EhAGnAalV2mw2EDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec2cffeb4e597afb65c80f2dc79d9989a3481c24819ae7588aea43f0b86be830","last_reissued_at":"2026-07-05T06:35:30.402149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:30.402149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cascaded Cross-Modal Transformer for Request and Complaint Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.CL","authors_text":"Nicolae-Catalin Ristea, Radu Tudor Ionescu","submitted_at":"2023-07-27T13:45:42Z","abstract_excerpt":"We propose a novel cascaded cross-modal transformer (CCMT) that combines speech and text transcripts to detect customer requests and complaints in phone conversations. Our approach leverages a multimodal paradigm by transcribing the speech using automatic speech recognition (ASR) models and translating the transcripts into different languages. Subsequently, we combine language-specific BERT-based models with Wav2Vec2.0 audio features in a novel cascaded cross-attention transformer model. We apply our system to the Requests Sub-Challenge of the ACM Multimedia 2023 Computational Paralinguistics "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15097","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/2307.15097/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":"2307.15097","created_at":"2026-07-05T06:35:30.402208+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.15097v1","created_at":"2026-07-05T06:35:30.402208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15097","created_at":"2026-07-05T06:35:30.402208+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QWP722OLF5P","created_at":"2026-07-05T06:35:30.402208+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QWP722OLF5PWZOI","created_at":"2026-07-05T06:35:30.402208+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QWP722O","created_at":"2026-07-05T06:35:30.402208+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/5QWP722OLF5PWZOIB4W4PHMZRG","json":"https://pith.science/pith/5QWP722OLF5PWZOIB4W4PHMZRG.json","graph_json":"https://pith.science/api/pith-number/5QWP722OLF5PWZOIB4W4PHMZRG/graph.json","events_json":"https://pith.science/api/pith-number/5QWP722OLF5PWZOIB4W4PHMZRG/events.json","paper":"https://pith.science/paper/5QWP722O"},"agent_actions":{"view_html":"https://pith.science/pith/5QWP722OLF5PWZOIB4W4PHMZRG","download_json":"https://pith.science/pith/5QWP722OLF5PWZOIB4W4PHMZRG.json","view_paper":"https://pith.science/paper/5QWP722O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.15097&json=true","fetch_graph":"https://pith.science/api/pith-number/5QWP722OLF5PWZOIB4W4PHMZRG/graph.json","fetch_events":"https://pith.science/api/pith-number/5QWP722OLF5PWZOIB4W4PHMZRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QWP722OLF5PWZOIB4W4PHMZRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QWP722OLF5PWZOIB4W4PHMZRG/action/storage_attestation","attest_author":"https://pith.science/pith/5QWP722OLF5PWZOIB4W4PHMZRG/action/author_attestation","sign_citation":"https://pith.science/pith/5QWP722OLF5PWZOIB4W4PHMZRG/action/citation_signature","submit_replication":"https://pith.science/pith/5QWP722OLF5PWZOIB4W4PHMZRG/action/replication_record"}},"created_at":"2026-07-05T06:35:30.402208+00:00","updated_at":"2026-07-05T06:35:30.402208+00:00"}