{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7THZL6TAIYRFPYGODYXJU5YQVP","short_pith_number":"pith:7THZL6TA","schema_version":"1.0","canonical_sha256":"fccf95fa60462257e0ce1e2e9a7710abcfb4f9950ba8f1cc4ff26da3cd799512","source":{"kind":"arxiv","id":"1708.05071","version":1},"attestation_state":"computed","paper":{"title":"Learning spectro-temporal features with 3D CNNs for speech emotion recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Gwenn Englebienne, Jaebok Kim, Khiet P. Truong, Vanessa Evers","submitted_at":"2017-08-14T17:32:06Z","abstract_excerpt":"In this paper, we propose to use deep 3-dimensional convolutional networks (3D CNNs) in order to address the challenge of modelling spectro-temporal dynamics for speech emotion recognition (SER). Compared to a hybrid of Convolutional Neural Network and Long-Short-Term-Memory (CNN-LSTM), our proposed 3D CNNs simultaneously extract short-term and long-term spectral features with a moderate number of parameters. We evaluated our proposed and other state-of-the-art methods in a speaker-independent manner using aggregated corpora that give a large and diverse set of speakers. We found that 1) shall"},"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":"1708.05071","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-14T17:32:06Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d346c9047b96a8dbbfb7d6804fc60dd2082a440c10d61d9fd667095003291def","abstract_canon_sha256":"1b8f8253d2b072b6fad64a27ae15bf3206f37b2ef35250ffc16d2fa31d422fde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:53.955632Z","signature_b64":"abgNqCq+3FNJDqxeS4HsJg2TWbUyJiKF3SPkP7WWT4kStzhs8cqUt/FXKwrggS1s9KHvAJLqGpzrgUi4AKrGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fccf95fa60462257e0ce1e2e9a7710abcfb4f9950ba8f1cc4ff26da3cd799512","last_reissued_at":"2026-05-18T00:37:53.954972Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:53.954972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning spectro-temporal features with 3D CNNs for speech emotion recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Gwenn Englebienne, Jaebok Kim, Khiet P. Truong, Vanessa Evers","submitted_at":"2017-08-14T17:32:06Z","abstract_excerpt":"In this paper, we propose to use deep 3-dimensional convolutional networks (3D CNNs) in order to address the challenge of modelling spectro-temporal dynamics for speech emotion recognition (SER). Compared to a hybrid of Convolutional Neural Network and Long-Short-Term-Memory (CNN-LSTM), our proposed 3D CNNs simultaneously extract short-term and long-term spectral features with a moderate number of parameters. We evaluated our proposed and other state-of-the-art methods in a speaker-independent manner using aggregated corpora that give a large and diverse set of speakers. We found that 1) shall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.05071","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":""},"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":"1708.05071","created_at":"2026-05-18T00:37:53.955073+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.05071v1","created_at":"2026-05-18T00:37:53.955073+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.05071","created_at":"2026-05-18T00:37:53.955073+00:00"},{"alias_kind":"pith_short_12","alias_value":"7THZL6TAIYRF","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7THZL6TAIYRFPYGO","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7THZL6TA","created_at":"2026-05-18T12:31:05.417338+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/7THZL6TAIYRFPYGODYXJU5YQVP","json":"https://pith.science/pith/7THZL6TAIYRFPYGODYXJU5YQVP.json","graph_json":"https://pith.science/api/pith-number/7THZL6TAIYRFPYGODYXJU5YQVP/graph.json","events_json":"https://pith.science/api/pith-number/7THZL6TAIYRFPYGODYXJU5YQVP/events.json","paper":"https://pith.science/paper/7THZL6TA"},"agent_actions":{"view_html":"https://pith.science/pith/7THZL6TAIYRFPYGODYXJU5YQVP","download_json":"https://pith.science/pith/7THZL6TAIYRFPYGODYXJU5YQVP.json","view_paper":"https://pith.science/paper/7THZL6TA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.05071&json=true","fetch_graph":"https://pith.science/api/pith-number/7THZL6TAIYRFPYGODYXJU5YQVP/graph.json","fetch_events":"https://pith.science/api/pith-number/7THZL6TAIYRFPYGODYXJU5YQVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7THZL6TAIYRFPYGODYXJU5YQVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7THZL6TAIYRFPYGODYXJU5YQVP/action/storage_attestation","attest_author":"https://pith.science/pith/7THZL6TAIYRFPYGODYXJU5YQVP/action/author_attestation","sign_citation":"https://pith.science/pith/7THZL6TAIYRFPYGODYXJU5YQVP/action/citation_signature","submit_replication":"https://pith.science/pith/7THZL6TAIYRFPYGODYXJU5YQVP/action/replication_record"}},"created_at":"2026-05-18T00:37:53.955073+00:00","updated_at":"2026-05-18T00:37:53.955073+00:00"}