{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JFFXITFK6KZFJR43WKMJVTBD6F","short_pith_number":"pith:JFFXITFK","schema_version":"1.0","canonical_sha256":"494b744caaf2b254c79bb2989acc23f14a2529b20c243e8eb92404a72d3ce8bb","source":{"kind":"arxiv","id":"2407.15300","version":1},"attestation_state":"computed","paper":{"title":"SELM: Enhancing Speech Emotion Recognition for Out-of-Domain Scenarios","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bhiksha Raj, Hazim Bukhari, Hira Dhamyal, Rita Singh, Soham Deshmukh","submitted_at":"2024-07-22T00:01:20Z","abstract_excerpt":"Speech Emotion Recognition (SER) has been traditionally formulated as a classification task. However, emotions are generally a spectrum whose distribution varies from situation to situation leading to poor Out-of-Domain (OOD) performance. We take inspiration from statistical formulation of Automatic Speech Recognition (ASR) and formulate the SER task as generating the most likely sequence of text tokens to infer emotion. The formulation breaks SER into predicting acoustic model features weighted by language model prediction. As an instance of this approach, we present SELM, an audio-conditione"},"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":"2407.15300","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-22T00:01:20Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"5b394aa5b3abe92ddfc5a3e0504082e0fcf382f2f34a62e8f257a6911315c31d","abstract_canon_sha256":"106b090ff332e51b0edb880151a3d45df073b51efd11d8f76e9a15e71f83c6ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:41.608075Z","signature_b64":"0W/E7Xe9tsxk2ZYMianiH1EkYAShQHrW3g2QYQcXMp4Odz+VWcR40eM6E9feoTcvNNGQsppten3/aYrJquq/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"494b744caaf2b254c79bb2989acc23f14a2529b20c243e8eb92404a72d3ce8bb","last_reissued_at":"2026-07-05T08:46:41.607540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:41.607540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SELM: Enhancing Speech Emotion Recognition for Out-of-Domain Scenarios","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bhiksha Raj, Hazim Bukhari, Hira Dhamyal, Rita Singh, Soham Deshmukh","submitted_at":"2024-07-22T00:01:20Z","abstract_excerpt":"Speech Emotion Recognition (SER) has been traditionally formulated as a classification task. However, emotions are generally a spectrum whose distribution varies from situation to situation leading to poor Out-of-Domain (OOD) performance. We take inspiration from statistical formulation of Automatic Speech Recognition (ASR) and formulate the SER task as generating the most likely sequence of text tokens to infer emotion. The formulation breaks SER into predicting acoustic model features weighted by language model prediction. As an instance of this approach, we present SELM, an audio-conditione"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15300","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/2407.15300/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":"2407.15300","created_at":"2026-07-05T08:46:41.607602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15300v1","created_at":"2026-07-05T08:46:41.607602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15300","created_at":"2026-07-05T08:46:41.607602+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFFXITFK6KZF","created_at":"2026-07-05T08:46:41.607602+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFFXITFK6KZFJR43","created_at":"2026-07-05T08:46:41.607602+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFFXITFK","created_at":"2026-07-05T08:46:41.607602+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/JFFXITFK6KZFJR43WKMJVTBD6F","json":"https://pith.science/pith/JFFXITFK6KZFJR43WKMJVTBD6F.json","graph_json":"https://pith.science/api/pith-number/JFFXITFK6KZFJR43WKMJVTBD6F/graph.json","events_json":"https://pith.science/api/pith-number/JFFXITFK6KZFJR43WKMJVTBD6F/events.json","paper":"https://pith.science/paper/JFFXITFK"},"agent_actions":{"view_html":"https://pith.science/pith/JFFXITFK6KZFJR43WKMJVTBD6F","download_json":"https://pith.science/pith/JFFXITFK6KZFJR43WKMJVTBD6F.json","view_paper":"https://pith.science/paper/JFFXITFK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15300&json=true","fetch_graph":"https://pith.science/api/pith-number/JFFXITFK6KZFJR43WKMJVTBD6F/graph.json","fetch_events":"https://pith.science/api/pith-number/JFFXITFK6KZFJR43WKMJVTBD6F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFFXITFK6KZFJR43WKMJVTBD6F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFFXITFK6KZFJR43WKMJVTBD6F/action/storage_attestation","attest_author":"https://pith.science/pith/JFFXITFK6KZFJR43WKMJVTBD6F/action/author_attestation","sign_citation":"https://pith.science/pith/JFFXITFK6KZFJR43WKMJVTBD6F/action/citation_signature","submit_replication":"https://pith.science/pith/JFFXITFK6KZFJR43WKMJVTBD6F/action/replication_record"}},"created_at":"2026-07-05T08:46:41.607602+00:00","updated_at":"2026-07-05T08:46:41.607602+00:00"}