{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WPOVHVEABKA7GMH4UCKDON7XNI","short_pith_number":"pith:WPOVHVEA","schema_version":"1.0","canonical_sha256":"b3dd53d4800a81f330fca0943737f76a151926e1e07a71e2e878a5a6b2ce7710","source":{"kind":"arxiv","id":"2506.02059","version":1},"attestation_state":"computed","paper":{"title":"Learning More with Less: Self-Supervised Approaches for Low-Resource Speech Emotion Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"David Sasu, Julia Hirschberg, Kaan Donbekci, Lin Ai, Pengyuan Shi, Run Chen, Zehui Wu, Ziwei Gong","submitted_at":"2025-06-01T15:49:40Z","abstract_excerpt":"Speech Emotion Recognition (SER) has seen significant progress with deep learning, yet remains challenging for Low-Resource Languages (LRLs) due to the scarcity of annotated data. In this work, we explore unsupervised learning to improve SER in low-resource settings. Specifically, we investigate contrastive learning (CL) and Bootstrap Your Own Latent (BYOL) as self-supervised approaches to enhance cross-lingual generalization. Our methods achieve notable F1 score improvements of 10.6% in Urdu, 15.2% in German, and 13.9% in Bangla, demonstrating their effectiveness in LRLs. Additionally, we ana"},"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":"2506.02059","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-01T15:49:40Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"847de96ab3c36d4d9a175c2a5503fe25cb9ef5ccb23aac24f65863fa4070c96d","abstract_canon_sha256":"56580f6172348154c0658acb720a002789dcd8385d50cd7c24f4f607ef85d8d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:31.628237Z","signature_b64":"yxS7mmvHwd3CN+KZ7FQaixlELW4M/3mu3P1kjDoTb7Gt/9rkDcRA4H9gOh1DK5SVAMFh7EEgSn9jDVpQozjcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3dd53d4800a81f330fca0943737f76a151926e1e07a71e2e878a5a6b2ce7710","last_reissued_at":"2026-07-05T11:14:31.627813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:31.627813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning More with Less: Self-Supervised Approaches for Low-Resource Speech Emotion Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"David Sasu, Julia Hirschberg, Kaan Donbekci, Lin Ai, Pengyuan Shi, Run Chen, Zehui Wu, Ziwei Gong","submitted_at":"2025-06-01T15:49:40Z","abstract_excerpt":"Speech Emotion Recognition (SER) has seen significant progress with deep learning, yet remains challenging for Low-Resource Languages (LRLs) due to the scarcity of annotated data. In this work, we explore unsupervised learning to improve SER in low-resource settings. Specifically, we investigate contrastive learning (CL) and Bootstrap Your Own Latent (BYOL) as self-supervised approaches to enhance cross-lingual generalization. Our methods achieve notable F1 score improvements of 10.6% in Urdu, 15.2% in German, and 13.9% in Bangla, demonstrating their effectiveness in LRLs. Additionally, we ana"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02059","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/2506.02059/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":"2506.02059","created_at":"2026-07-05T11:14:31.627869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02059v1","created_at":"2026-07-05T11:14:31.627869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02059","created_at":"2026-07-05T11:14:31.627869+00:00"},{"alias_kind":"pith_short_12","alias_value":"WPOVHVEABKA7","created_at":"2026-07-05T11:14:31.627869+00:00"},{"alias_kind":"pith_short_16","alias_value":"WPOVHVEABKA7GMH4","created_at":"2026-07-05T11:14:31.627869+00:00"},{"alias_kind":"pith_short_8","alias_value":"WPOVHVEA","created_at":"2026-07-05T11:14:31.627869+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02059","citing_title":"Learning More with Less: Self-Supervised Approaches for Low-Resource Speech Emotion Recognition","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WPOVHVEABKA7GMH4UCKDON7XNI","json":"https://pith.science/pith/WPOVHVEABKA7GMH4UCKDON7XNI.json","graph_json":"https://pith.science/api/pith-number/WPOVHVEABKA7GMH4UCKDON7XNI/graph.json","events_json":"https://pith.science/api/pith-number/WPOVHVEABKA7GMH4UCKDON7XNI/events.json","paper":"https://pith.science/paper/WPOVHVEA"},"agent_actions":{"view_html":"https://pith.science/pith/WPOVHVEABKA7GMH4UCKDON7XNI","download_json":"https://pith.science/pith/WPOVHVEABKA7GMH4UCKDON7XNI.json","view_paper":"https://pith.science/paper/WPOVHVEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02059&json=true","fetch_graph":"https://pith.science/api/pith-number/WPOVHVEABKA7GMH4UCKDON7XNI/graph.json","fetch_events":"https://pith.science/api/pith-number/WPOVHVEABKA7GMH4UCKDON7XNI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WPOVHVEABKA7GMH4UCKDON7XNI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WPOVHVEABKA7GMH4UCKDON7XNI/action/storage_attestation","attest_author":"https://pith.science/pith/WPOVHVEABKA7GMH4UCKDON7XNI/action/author_attestation","sign_citation":"https://pith.science/pith/WPOVHVEABKA7GMH4UCKDON7XNI/action/citation_signature","submit_replication":"https://pith.science/pith/WPOVHVEABKA7GMH4UCKDON7XNI/action/replication_record"}},"created_at":"2026-07-05T11:14:31.627869+00:00","updated_at":"2026-07-05T11:14:31.627869+00:00"}