{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W5GQSDHIQUD6DLTONOARYQOOV3","short_pith_number":"pith:W5GQSDHI","schema_version":"1.0","canonical_sha256":"b74d090ce88507e1ae6e6b811c41ceaedffc3a80cee04b955e62eceacd2205be","source":{"kind":"arxiv","id":"2306.05709","version":1},"attestation_state":"computed","paper":{"title":"Learning Emotional Representations from Imbalanced Speech Data for Speech Emotion Recognition and Emotional Text-to-Speech","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Damian Borth, J\\'on Gu{\\dh}nason, Shijun Wang","submitted_at":"2023-06-09T07:04:56Z","abstract_excerpt":"Effective speech emotional representations play a key role in Speech Emotion Recognition (SER) and Emotional Text-To-Speech (TTS) tasks. However, emotional speech samples are more difficult and expensive to acquire compared with Neutral style speech, which causes one issue that most related works unfortunately neglect: imbalanced datasets. Models might overfit to the majority Neutral class and fail to produce robust and effective emotional representations. In this paper, we propose an Emotion Extractor to address this issue. We use augmentation approaches to train the model and enable it to ex"},"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":"2306.05709","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-09T07:04:56Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"b292874e1306e40df288761624c8ea6eed5f41fa6cc1b7a82a3eabf641ba16ac","abstract_canon_sha256":"9d96d34c322a5a616e1942ebd8f79ac21bf8cf5c99a1249d5583d9adc4b7a01b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:09.310547Z","signature_b64":"ffnNb9ThFUcr+AhuQblba1VJZMKvPNhTylItunmfug5HhjUYjiGVvQ4RTx+5/hc5exXR+W7z1K6XXPsOrm6eCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b74d090ce88507e1ae6e6b811c41ceaedffc3a80cee04b955e62eceacd2205be","last_reissued_at":"2026-07-05T06:19:09.310146Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:09.310146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Emotional Representations from Imbalanced Speech Data for Speech Emotion Recognition and Emotional Text-to-Speech","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Damian Borth, J\\'on Gu{\\dh}nason, Shijun Wang","submitted_at":"2023-06-09T07:04:56Z","abstract_excerpt":"Effective speech emotional representations play a key role in Speech Emotion Recognition (SER) and Emotional Text-To-Speech (TTS) tasks. However, emotional speech samples are more difficult and expensive to acquire compared with Neutral style speech, which causes one issue that most related works unfortunately neglect: imbalanced datasets. Models might overfit to the majority Neutral class and fail to produce robust and effective emotional representations. In this paper, we propose an Emotion Extractor to address this issue. We use augmentation approaches to train the model and enable it to ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05709","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/2306.05709/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":"2306.05709","created_at":"2026-07-05T06:19:09.310199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05709v1","created_at":"2026-07-05T06:19:09.310199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05709","created_at":"2026-07-05T06:19:09.310199+00:00"},{"alias_kind":"pith_short_12","alias_value":"W5GQSDHIQUD6","created_at":"2026-07-05T06:19:09.310199+00:00"},{"alias_kind":"pith_short_16","alias_value":"W5GQSDHIQUD6DLTO","created_at":"2026-07-05T06:19:09.310199+00:00"},{"alias_kind":"pith_short_8","alias_value":"W5GQSDHI","created_at":"2026-07-05T06:19:09.310199+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.16188","citing_title":"Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W5GQSDHIQUD6DLTONOARYQOOV3","json":"https://pith.science/pith/W5GQSDHIQUD6DLTONOARYQOOV3.json","graph_json":"https://pith.science/api/pith-number/W5GQSDHIQUD6DLTONOARYQOOV3/graph.json","events_json":"https://pith.science/api/pith-number/W5GQSDHIQUD6DLTONOARYQOOV3/events.json","paper":"https://pith.science/paper/W5GQSDHI"},"agent_actions":{"view_html":"https://pith.science/pith/W5GQSDHIQUD6DLTONOARYQOOV3","download_json":"https://pith.science/pith/W5GQSDHIQUD6DLTONOARYQOOV3.json","view_paper":"https://pith.science/paper/W5GQSDHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05709&json=true","fetch_graph":"https://pith.science/api/pith-number/W5GQSDHIQUD6DLTONOARYQOOV3/graph.json","fetch_events":"https://pith.science/api/pith-number/W5GQSDHIQUD6DLTONOARYQOOV3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W5GQSDHIQUD6DLTONOARYQOOV3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W5GQSDHIQUD6DLTONOARYQOOV3/action/storage_attestation","attest_author":"https://pith.science/pith/W5GQSDHIQUD6DLTONOARYQOOV3/action/author_attestation","sign_citation":"https://pith.science/pith/W5GQSDHIQUD6DLTONOARYQOOV3/action/citation_signature","submit_replication":"https://pith.science/pith/W5GQSDHIQUD6DLTONOARYQOOV3/action/replication_record"}},"created_at":"2026-07-05T06:19:09.310199+00:00","updated_at":"2026-07-05T06:19:09.310199+00:00"}