{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XBTLWXKQB4SX5GET6UD3HTENS6","short_pith_number":"pith:XBTLWXKQ","schema_version":"1.0","canonical_sha256":"b866bb5d500f257e9893f507b3cc8d97b66c359ed06ff4265ebffe2ea058f21e","source":{"kind":"arxiv","id":"2304.06910","version":2},"attestation_state":"computed","paper":{"title":"HCAM -- Hierarchical Cross Attention Model for Multi-modal Emotion Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Soumya Dutta, Sriram Ganapathy","submitted_at":"2023-04-14T03:25:00Z","abstract_excerpt":"Emotion recognition in conversations is challenging due to the multi-modal nature of the emotion expression. We propose a hierarchical cross-attention model (HCAM) approach to multi-modal emotion recognition using a combination of recurrent and co-attention neural network models. The input to the model consists of two modalities, i) audio data, processed through a learnable wav2vec approach and, ii) text data represented using a bidirectional encoder representations from transformers (BERT) model. The audio and text representations are processed using a set of bi-directional recurrent neural n"},"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":"2304.06910","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-04-14T03:25:00Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"f3c5dae93991c42e36e953ad4b0c1086b56c92c0ec1c7048d8074e79860ea0b0","abstract_canon_sha256":"dff3dfbb00e4484b18b52f5ae642b1e4d0c930f08c0a32253252192a63fe24be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:27.519698Z","signature_b64":"AfPsBNpGubyhUYKvErLIxj1COxXgCmF+lNLHMKPtks7evgeIrtQH1kx29REi1X0HRpWlRhz51UySuMp79s9VAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b866bb5d500f257e9893f507b3cc8d97b66c359ed06ff4265ebffe2ea058f21e","last_reissued_at":"2026-07-05T07:31:27.518977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:27.518977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HCAM -- Hierarchical Cross Attention Model for Multi-modal Emotion Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Soumya Dutta, Sriram Ganapathy","submitted_at":"2023-04-14T03:25:00Z","abstract_excerpt":"Emotion recognition in conversations is challenging due to the multi-modal nature of the emotion expression. We propose a hierarchical cross-attention model (HCAM) approach to multi-modal emotion recognition using a combination of recurrent and co-attention neural network models. The input to the model consists of two modalities, i) audio data, processed through a learnable wav2vec approach and, ii) text data represented using a bidirectional encoder representations from transformers (BERT) model. The audio and text representations are processed using a set of bi-directional recurrent neural n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.06910","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/2304.06910/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":"2304.06910","created_at":"2026-07-05T07:31:27.519033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.06910v2","created_at":"2026-07-05T07:31:27.519033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06910","created_at":"2026-07-05T07:31:27.519033+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBTLWXKQB4SX","created_at":"2026-07-05T07:31:27.519033+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBTLWXKQB4SX5GET","created_at":"2026-07-05T07:31:27.519033+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBTLWXKQ","created_at":"2026-07-05T07:31:27.519033+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02088","citing_title":"Enhancing Speech Emotion Recognition with Graph-Based Multimodal Fusion and Prosodic Features for the Speech Emotion Recognition in Naturalistic Conditions Challenge at Interspeech 2025","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XBTLWXKQB4SX5GET6UD3HTENS6","json":"https://pith.science/pith/XBTLWXKQB4SX5GET6UD3HTENS6.json","graph_json":"https://pith.science/api/pith-number/XBTLWXKQB4SX5GET6UD3HTENS6/graph.json","events_json":"https://pith.science/api/pith-number/XBTLWXKQB4SX5GET6UD3HTENS6/events.json","paper":"https://pith.science/paper/XBTLWXKQ"},"agent_actions":{"view_html":"https://pith.science/pith/XBTLWXKQB4SX5GET6UD3HTENS6","download_json":"https://pith.science/pith/XBTLWXKQB4SX5GET6UD3HTENS6.json","view_paper":"https://pith.science/paper/XBTLWXKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.06910&json=true","fetch_graph":"https://pith.science/api/pith-number/XBTLWXKQB4SX5GET6UD3HTENS6/graph.json","fetch_events":"https://pith.science/api/pith-number/XBTLWXKQB4SX5GET6UD3HTENS6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBTLWXKQB4SX5GET6UD3HTENS6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBTLWXKQB4SX5GET6UD3HTENS6/action/storage_attestation","attest_author":"https://pith.science/pith/XBTLWXKQB4SX5GET6UD3HTENS6/action/author_attestation","sign_citation":"https://pith.science/pith/XBTLWXKQB4SX5GET6UD3HTENS6/action/citation_signature","submit_replication":"https://pith.science/pith/XBTLWXKQB4SX5GET6UD3HTENS6/action/replication_record"}},"created_at":"2026-07-05T07:31:27.519033+00:00","updated_at":"2026-07-05T07:31:27.519033+00:00"}