{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2ZW4KD2YLKHAMG2U2XOWMLDHQ3","short_pith_number":"pith:2ZW4KD2Y","schema_version":"1.0","canonical_sha256":"d66dc50f585a8e061b54d5dd662c6786d0044b12e1861e7ed2e004e73846513c","source":{"kind":"arxiv","id":"2509.09791","version":1},"attestation_state":"computed","paper":{"title":"The MSP-Podcast Corpus","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Abinay Reddy Naini, Ali N. Salman, Carlos Busso, Huang-Cheng Chou, Kusha Sridhar, Lucas Goncalves, Luz Martinez-Lucas, Pravin Mote, Reza Lotfian, Seong-Gyun Leem, Srinivas Parthasarathy, Wei-Cheng Lin","submitted_at":"2025-09-11T18:51:58Z","abstract_excerpt":"The availability of large, high-quality emotional speech databases is essential for advancing speech emotion recognition (SER) in real-world scenarios. However, many existing databases face limitations in size, emotional balance, and speaker diversity. This study describes the MSP-Podcast corpus, summarizing our ten-year effort. The corpus consists of over 400 hours of diverse audio samples from various audio-sharing websites, all of which have Common Licenses that permit the distribution of the corpus. We annotate the corpus with rich emotional labels, including primary (single dominant emoti"},"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":"2509.09791","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2025-09-11T18:51:58Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"7ee13e294c619d098c55718b8e0896daa529f38e0b1d0c0d31a522d268c3f0a5","abstract_canon_sha256":"2d631229318dc4eae7d69ed4df3f733a533722e26ad0f7da0b1d6f26a3aca777"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:49.459269Z","signature_b64":"IufbwhJGB5sYbodwXCqqwo+exG22vLEXsrx3YoFDVwlig8bohwAneQXomYK+qKIRC6NP/uO34nX7FufSTJ64Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d66dc50f585a8e061b54d5dd662c6786d0044b12e1861e7ed2e004e73846513c","last_reissued_at":"2026-07-05T12:09:49.458769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:49.458769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The MSP-Podcast Corpus","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Abinay Reddy Naini, Ali N. Salman, Carlos Busso, Huang-Cheng Chou, Kusha Sridhar, Lucas Goncalves, Luz Martinez-Lucas, Pravin Mote, Reza Lotfian, Seong-Gyun Leem, Srinivas Parthasarathy, Wei-Cheng Lin","submitted_at":"2025-09-11T18:51:58Z","abstract_excerpt":"The availability of large, high-quality emotional speech databases is essential for advancing speech emotion recognition (SER) in real-world scenarios. However, many existing databases face limitations in size, emotional balance, and speaker diversity. This study describes the MSP-Podcast corpus, summarizing our ten-year effort. The corpus consists of over 400 hours of diverse audio samples from various audio-sharing websites, all of which have Common Licenses that permit the distribution of the corpus. We annotate the corpus with rich emotional labels, including primary (single dominant emoti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09791","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/2509.09791/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":"2509.09791","created_at":"2026-07-05T12:09:49.458830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09791v1","created_at":"2026-07-05T12:09:49.458830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09791","created_at":"2026-07-05T12:09:49.458830+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZW4KD2YLKHA","created_at":"2026-07-05T12:09:49.458830+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZW4KD2YLKHAMG2U","created_at":"2026-07-05T12:09:49.458830+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZW4KD2Y","created_at":"2026-07-05T12:09:49.458830+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06611","citing_title":"Audio Sentiment Analysis via Distillation and Cross-Modal Integration of Generated Multilingual Transcripts","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24082","citing_title":"Comparative Reasoning: Making an Audio Language Model Better at Comparing Emotions","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05376","citing_title":"SHALA-LLM: Smartly Handling Ambiguous Labels in Aligning LLMs","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27536","citing_title":"Learning from Annotation Uncertainty: Entropy-Aware Curriculum for Speech Emotion Recognition","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00851","citing_title":"Sympatheia: Emotionally Adaptive Voice Assistant with Continuous Affect Conditioning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23373","citing_title":"AffectCodec: Emotion-Preserving Neural Speech Codec with Block-Diagonal Residual FSQ","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17583","citing_title":"AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12838","citing_title":"Multimodal Hidden Markov Models for Persistent Emotional State Tracking","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11098","citing_title":"AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26347","citing_title":"The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09881","citing_title":"Toward using Speech to Sense Student Emotion in Remote Learning Environments","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ZW4KD2YLKHAMG2U2XOWMLDHQ3","json":"https://pith.science/pith/2ZW4KD2YLKHAMG2U2XOWMLDHQ3.json","graph_json":"https://pith.science/api/pith-number/2ZW4KD2YLKHAMG2U2XOWMLDHQ3/graph.json","events_json":"https://pith.science/api/pith-number/2ZW4KD2YLKHAMG2U2XOWMLDHQ3/events.json","paper":"https://pith.science/paper/2ZW4KD2Y"},"agent_actions":{"view_html":"https://pith.science/pith/2ZW4KD2YLKHAMG2U2XOWMLDHQ3","download_json":"https://pith.science/pith/2ZW4KD2YLKHAMG2U2XOWMLDHQ3.json","view_paper":"https://pith.science/paper/2ZW4KD2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09791&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZW4KD2YLKHAMG2U2XOWMLDHQ3/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZW4KD2YLKHAMG2U2XOWMLDHQ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZW4KD2YLKHAMG2U2XOWMLDHQ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZW4KD2YLKHAMG2U2XOWMLDHQ3/action/storage_attestation","attest_author":"https://pith.science/pith/2ZW4KD2YLKHAMG2U2XOWMLDHQ3/action/author_attestation","sign_citation":"https://pith.science/pith/2ZW4KD2YLKHAMG2U2XOWMLDHQ3/action/citation_signature","submit_replication":"https://pith.science/pith/2ZW4KD2YLKHAMG2U2XOWMLDHQ3/action/replication_record"}},"created_at":"2026-07-05T12:09:49.458830+00:00","updated_at":"2026-07-05T12:09:49.458830+00:00"}