{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZBDQZ46TGHQML7NJNZFZETFFFM","short_pith_number":"pith:ZBDQZ46T","schema_version":"1.0","canonical_sha256":"c8470cf3d331e0c5fda96e4b924ca52b02f4cc53ace580789d95f2a6827c5193","source":{"kind":"arxiv","id":"2309.01164","version":1},"attestation_state":"computed","paper":{"title":"Noise robust speech emotion recognition with signal-to-noise ratio adapting speech enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Julia Hirschberg, Yu Tsao, Yu-Wen Chen","submitted_at":"2023-09-03T13:00:04Z","abstract_excerpt":"Speech emotion recognition (SER) often experiences reduced performance due to background noise. In addition, making a prediction on signals with only background noise could undermine user trust in the system. In this study, we propose a Noise Robust Speech Emotion Recognition system, NRSER. NRSER employs speech enhancement (SE) to effectively reduce the noise in input signals. Then, the signal-to-noise-ratio (SNR)-level detection structure and waveform reconstitution strategy are introduced to reduce the negative impact of SE on speech signals with no or little background noise. Our experiment"},"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":"2309.01164","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-03T13:00:04Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"27eafda9f8f2cd3ae594e489e9f3869d1f2a58b94b23a8bdf1d9114e427bfbee","abstract_canon_sha256":"2e118d18ab7ff26549e8053ec0271f2a7e34a6167a69335d29c55592055e4586"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:33.742669Z","signature_b64":"IkY4grh9irIXepFB6hZvkNMd2dd3Ja95z/B34ymw9MkLeSx2dQC+9eFHiUj1EM4sNHSoYk55EAjeTNXzE3MyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8470cf3d331e0c5fda96e4b924ca52b02f4cc53ace580789d95f2a6827c5193","last_reissued_at":"2026-07-05T06:47:33.742184Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:33.742184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Noise robust speech emotion recognition with signal-to-noise ratio adapting speech enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Julia Hirschberg, Yu Tsao, Yu-Wen Chen","submitted_at":"2023-09-03T13:00:04Z","abstract_excerpt":"Speech emotion recognition (SER) often experiences reduced performance due to background noise. In addition, making a prediction on signals with only background noise could undermine user trust in the system. In this study, we propose a Noise Robust Speech Emotion Recognition system, NRSER. NRSER employs speech enhancement (SE) to effectively reduce the noise in input signals. Then, the signal-to-noise-ratio (SNR)-level detection structure and waveform reconstitution strategy are introduced to reduce the negative impact of SE on speech signals with no or little background noise. Our experiment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01164","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/2309.01164/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":"2309.01164","created_at":"2026-07-05T06:47:33.742244+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.01164v1","created_at":"2026-07-05T06:47:33.742244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01164","created_at":"2026-07-05T06:47:33.742244+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBDQZ46TGHQM","created_at":"2026-07-05T06:47:33.742244+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBDQZ46TGHQML7NJ","created_at":"2026-07-05T06:47:33.742244+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBDQZ46T","created_at":"2026-07-05T06:47:33.742244+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.08470","citing_title":"Joint Learning using Mixture-of-Expert-Based Representation for Speech Enhancement and Robust Emotion Recognition","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZBDQZ46TGHQML7NJNZFZETFFFM","json":"https://pith.science/pith/ZBDQZ46TGHQML7NJNZFZETFFFM.json","graph_json":"https://pith.science/api/pith-number/ZBDQZ46TGHQML7NJNZFZETFFFM/graph.json","events_json":"https://pith.science/api/pith-number/ZBDQZ46TGHQML7NJNZFZETFFFM/events.json","paper":"https://pith.science/paper/ZBDQZ46T"},"agent_actions":{"view_html":"https://pith.science/pith/ZBDQZ46TGHQML7NJNZFZETFFFM","download_json":"https://pith.science/pith/ZBDQZ46TGHQML7NJNZFZETFFFM.json","view_paper":"https://pith.science/paper/ZBDQZ46T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.01164&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBDQZ46TGHQML7NJNZFZETFFFM/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBDQZ46TGHQML7NJNZFZETFFFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBDQZ46TGHQML7NJNZFZETFFFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBDQZ46TGHQML7NJNZFZETFFFM/action/storage_attestation","attest_author":"https://pith.science/pith/ZBDQZ46TGHQML7NJNZFZETFFFM/action/author_attestation","sign_citation":"https://pith.science/pith/ZBDQZ46TGHQML7NJNZFZETFFFM/action/citation_signature","submit_replication":"https://pith.science/pith/ZBDQZ46TGHQML7NJNZFZETFFFM/action/replication_record"}},"created_at":"2026-07-05T06:47:33.742244+00:00","updated_at":"2026-07-05T06:47:33.742244+00:00"}