{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:A57MPW6UKSJDWOCOLO3E4QA6GZ","short_pith_number":"pith:A57MPW6U","schema_version":"1.0","canonical_sha256":"077ec7dbd454923b384e5bb64e401e3678a77e283f1bb3e843439ac16b59a0ab","source":{"kind":"arxiv","id":"2201.11826","version":1},"attestation_state":"computed","paper":{"title":"Sentiment-Aware Automatic Speech Recognition pre-training for enhanced Speech Emotion Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ayoub Ghriss, Bo Yang, Chao Wang, Elizabeth Shriberg, Viktor Rozgic","submitted_at":"2022-01-27T22:20:28Z","abstract_excerpt":"We propose a novel multi-task pre-training method for Speech Emotion Recognition (SER). We pre-train SER model simultaneously on Automatic Speech Recognition (ASR) and sentiment classification tasks to make the acoustic ASR model more ``emotion aware''. We generate targets for the sentiment classification using text-to-sentiment model trained on publicly available data. Finally, we fine-tune the acoustic ASR on emotion annotated speech data. We evaluated the proposed approach on the MSP-Podcast dataset, where we achieved the best reported concordance correlation coefficient (CCC) of 0.41 for v"},"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":"2201.11826","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-27T22:20:28Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d42f538fd20a575de85ae741a8173c0071f88282692bfbf6e4586584245f39bb","abstract_canon_sha256":"6615c28ae9a97245d0a5baeb0396f87bdff99d401c71d019d6014e90123ac87d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:52:17.153555Z","signature_b64":"fKvdtiSkI7fVdgdcNcVhF73Cn9aloSPYcDDlWn7nW7t7NkTNQ+0X5RGBtjdqvpNocUPDauCkA0/08itr2hCWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"077ec7dbd454923b384e5bb64e401e3678a77e283f1bb3e843439ac16b59a0ab","last_reissued_at":"2026-07-05T03:52:17.153109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:52:17.153109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sentiment-Aware Automatic Speech Recognition pre-training for enhanced Speech Emotion Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ayoub Ghriss, Bo Yang, Chao Wang, Elizabeth Shriberg, Viktor Rozgic","submitted_at":"2022-01-27T22:20:28Z","abstract_excerpt":"We propose a novel multi-task pre-training method for Speech Emotion Recognition (SER). We pre-train SER model simultaneously on Automatic Speech Recognition (ASR) and sentiment classification tasks to make the acoustic ASR model more ``emotion aware''. We generate targets for the sentiment classification using text-to-sentiment model trained on publicly available data. Finally, we fine-tune the acoustic ASR on emotion annotated speech data. We evaluated the proposed approach on the MSP-Podcast dataset, where we achieved the best reported concordance correlation coefficient (CCC) of 0.41 for v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.11826","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/2201.11826/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":"2201.11826","created_at":"2026-07-05T03:52:17.153183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.11826v1","created_at":"2026-07-05T03:52:17.153183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.11826","created_at":"2026-07-05T03:52:17.153183+00:00"},{"alias_kind":"pith_short_12","alias_value":"A57MPW6UKSJD","created_at":"2026-07-05T03:52:17.153183+00:00"},{"alias_kind":"pith_short_16","alias_value":"A57MPW6UKSJDWOCO","created_at":"2026-07-05T03:52:17.153183+00:00"},{"alias_kind":"pith_short_8","alias_value":"A57MPW6U","created_at":"2026-07-05T03:52:17.153183+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/A57MPW6UKSJDWOCOLO3E4QA6GZ","json":"https://pith.science/pith/A57MPW6UKSJDWOCOLO3E4QA6GZ.json","graph_json":"https://pith.science/api/pith-number/A57MPW6UKSJDWOCOLO3E4QA6GZ/graph.json","events_json":"https://pith.science/api/pith-number/A57MPW6UKSJDWOCOLO3E4QA6GZ/events.json","paper":"https://pith.science/paper/A57MPW6U"},"agent_actions":{"view_html":"https://pith.science/pith/A57MPW6UKSJDWOCOLO3E4QA6GZ","download_json":"https://pith.science/pith/A57MPW6UKSJDWOCOLO3E4QA6GZ.json","view_paper":"https://pith.science/paper/A57MPW6U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.11826&json=true","fetch_graph":"https://pith.science/api/pith-number/A57MPW6UKSJDWOCOLO3E4QA6GZ/graph.json","fetch_events":"https://pith.science/api/pith-number/A57MPW6UKSJDWOCOLO3E4QA6GZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A57MPW6UKSJDWOCOLO3E4QA6GZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A57MPW6UKSJDWOCOLO3E4QA6GZ/action/storage_attestation","attest_author":"https://pith.science/pith/A57MPW6UKSJDWOCOLO3E4QA6GZ/action/author_attestation","sign_citation":"https://pith.science/pith/A57MPW6UKSJDWOCOLO3E4QA6GZ/action/citation_signature","submit_replication":"https://pith.science/pith/A57MPW6UKSJDWOCOLO3E4QA6GZ/action/replication_record"}},"created_at":"2026-07-05T03:52:17.153183+00:00","updated_at":"2026-07-05T03:52:17.153183+00:00"}