{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4VZ6ALLAX5NAKT7RVTWQZHA5JB","short_pith_number":"pith:4VZ6ALLA","schema_version":"1.0","canonical_sha256":"e573e02d60bf5a054ff1aced0c9c1d487a537269721be6e2e4cb4d8485715815","source":{"kind":"arxiv","id":"1802.05630","version":2},"attestation_state":"computed","paper":{"title":"CNN+LSTM Architecture for Speech Emotion Recognition with Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andrei Petrovskii, Benoit Schmauch, Caroline Etienne, Guillaume Fidanza, Laurence Devillers","submitted_at":"2018-02-15T16:05:02Z","abstract_excerpt":"In this work we design a neural network for recognizing emotions in speech, using the IEMOCAP dataset. Following the latest advances in audio analysis, we use an architecture involving both convolutional layers, for extracting high-level features from raw spectrograms, and recurrent ones for aggregating long-term dependencies. We examine the techniques of data augmentation with vocal track length perturbation, layer-wise optimizer adjustment, batch normalization of recurrent layers and obtain highly competitive results of 64.5% for weighted accuracy and 61.7% for unweighted accuracy on four em"},"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":"1802.05630","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-02-15T16:05:02Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"ec61e726deed720c1097bdf8605a6a6c0232f62c5bcd725ef1a6da55341426f0","abstract_canon_sha256":"a0bc39503943b4f82a4011762bd98029ea2634b8208e3e4a2e74298a9d110fa7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:56.347265Z","signature_b64":"05R77Ytlt6yoylgdp9tNSjI9oJhpaveGquzZAkNyEAGvXt1sGGTQ80iheqFYLTG+PGQP6CvaMhmqoq51CTezAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e573e02d60bf5a054ff1aced0c9c1d487a537269721be6e2e4cb4d8485715815","last_reissued_at":"2026-05-18T00:05:56.346811Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:56.346811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CNN+LSTM Architecture for Speech Emotion Recognition with Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andrei Petrovskii, Benoit Schmauch, Caroline Etienne, Guillaume Fidanza, Laurence Devillers","submitted_at":"2018-02-15T16:05:02Z","abstract_excerpt":"In this work we design a neural network for recognizing emotions in speech, using the IEMOCAP dataset. Following the latest advances in audio analysis, we use an architecture involving both convolutional layers, for extracting high-level features from raw spectrograms, and recurrent ones for aggregating long-term dependencies. We examine the techniques of data augmentation with vocal track length perturbation, layer-wise optimizer adjustment, batch normalization of recurrent layers and obtain highly competitive results of 64.5% for weighted accuracy and 61.7% for unweighted accuracy on four em"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05630","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":""},"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":"1802.05630","created_at":"2026-05-18T00:05:56.346883+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.05630v2","created_at":"2026-05-18T00:05:56.346883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05630","created_at":"2026-05-18T00:05:56.346883+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VZ6ALLAX5NA","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VZ6ALLAX5NAKT7R","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VZ6ALLA","created_at":"2026-05-18T12:32:05.422762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25938","citing_title":"Speech Emotion Recognition Using MFCC Features and LSTM-Based Deep Learning Model","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VZ6ALLAX5NAKT7RVTWQZHA5JB","json":"https://pith.science/pith/4VZ6ALLAX5NAKT7RVTWQZHA5JB.json","graph_json":"https://pith.science/api/pith-number/4VZ6ALLAX5NAKT7RVTWQZHA5JB/graph.json","events_json":"https://pith.science/api/pith-number/4VZ6ALLAX5NAKT7RVTWQZHA5JB/events.json","paper":"https://pith.science/paper/4VZ6ALLA"},"agent_actions":{"view_html":"https://pith.science/pith/4VZ6ALLAX5NAKT7RVTWQZHA5JB","download_json":"https://pith.science/pith/4VZ6ALLAX5NAKT7RVTWQZHA5JB.json","view_paper":"https://pith.science/paper/4VZ6ALLA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.05630&json=true","fetch_graph":"https://pith.science/api/pith-number/4VZ6ALLAX5NAKT7RVTWQZHA5JB/graph.json","fetch_events":"https://pith.science/api/pith-number/4VZ6ALLAX5NAKT7RVTWQZHA5JB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VZ6ALLAX5NAKT7RVTWQZHA5JB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VZ6ALLAX5NAKT7RVTWQZHA5JB/action/storage_attestation","attest_author":"https://pith.science/pith/4VZ6ALLAX5NAKT7RVTWQZHA5JB/action/author_attestation","sign_citation":"https://pith.science/pith/4VZ6ALLAX5NAKT7RVTWQZHA5JB/action/citation_signature","submit_replication":"https://pith.science/pith/4VZ6ALLAX5NAKT7RVTWQZHA5JB/action/replication_record"}},"created_at":"2026-05-18T00:05:56.346883+00:00","updated_at":"2026-05-18T00:05:56.346883+00:00"}