{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EAPTUMUJGXIUBPFR6QBR5SBYPI","short_pith_number":"pith:EAPTUMUJ","schema_version":"1.0","canonical_sha256":"201f3a328935d140bcb1f4031ec8387a37ef8ffd6f2c5cb4b1afa9dbb3b65264","source":{"kind":"arxiv","id":"2410.06675","version":2},"attestation_state":"computed","paper":{"title":"SCOREQ: Speech Quality Assessment with Contrastive Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Alessandro Ragano, Andrew Hines, Jan Skoglund","submitted_at":"2024-10-09T08:30:59Z","abstract_excerpt":"In this paper, we present SCOREQ, a novel approach for speech quality prediction. SCOREQ is a triplet loss function for contrastive regression that addresses the domain generalisation shortcoming exhibited by state of the art no-reference speech quality metrics. In the paper we: (i) illustrate the problem of L2 loss training failing at capturing the continuous nature of the mean opinion score (MOS) labels; (ii) demonstrate the lack of generalisation through a benchmarking evaluation across several speech domains; (iii) outline our approach and explore the impact of the architectural design dec"},"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":"2410.06675","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-09T08:30:59Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"e833b12e5b7df08543808c41e7bcbf49cb6fff2a0bc3b83bf73f7e18f8a35266","abstract_canon_sha256":"b5f7b2a5dc5d0429964d40b5b8bfc6a6c6ff78bf92f7cb947802d08831751d19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:16.763712Z","signature_b64":"ebr1h93MVur3z9Ky/ZJ4xAx7n/VQele0Rp2WqOjrhCvnwpojRzUicYTuo0Zbsld2+sVjZT1HZdTNIUQefd5sAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"201f3a328935d140bcb1f4031ec8387a37ef8ffd6f2c5cb4b1afa9dbb3b65264","last_reissued_at":"2026-07-05T10:01:16.763255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:16.763255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCOREQ: Speech Quality Assessment with Contrastive Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Alessandro Ragano, Andrew Hines, Jan Skoglund","submitted_at":"2024-10-09T08:30:59Z","abstract_excerpt":"In this paper, we present SCOREQ, a novel approach for speech quality prediction. SCOREQ is a triplet loss function for contrastive regression that addresses the domain generalisation shortcoming exhibited by state of the art no-reference speech quality metrics. In the paper we: (i) illustrate the problem of L2 loss training failing at capturing the continuous nature of the mean opinion score (MOS) labels; (ii) demonstrate the lack of generalisation through a benchmarking evaluation across several speech domains; (iii) outline our approach and explore the impact of the architectural design dec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06675","kind":"arxiv","version":2},"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/2410.06675/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":"2410.06675","created_at":"2026-07-05T10:01:16.763326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.06675v2","created_at":"2026-07-05T10:01:16.763326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06675","created_at":"2026-07-05T10:01:16.763326+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAPTUMUJGXIU","created_at":"2026-07-05T10:01:16.763326+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAPTUMUJGXIUBPFR","created_at":"2026-07-05T10:01:16.763326+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAPTUMUJ","created_at":"2026-07-05T10:01:16.763326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.08890","citing_title":"Transient Noise Removal via Diffusion-based Speech Inpainting","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EAPTUMUJGXIUBPFR6QBR5SBYPI","json":"https://pith.science/pith/EAPTUMUJGXIUBPFR6QBR5SBYPI.json","graph_json":"https://pith.science/api/pith-number/EAPTUMUJGXIUBPFR6QBR5SBYPI/graph.json","events_json":"https://pith.science/api/pith-number/EAPTUMUJGXIUBPFR6QBR5SBYPI/events.json","paper":"https://pith.science/paper/EAPTUMUJ"},"agent_actions":{"view_html":"https://pith.science/pith/EAPTUMUJGXIUBPFR6QBR5SBYPI","download_json":"https://pith.science/pith/EAPTUMUJGXIUBPFR6QBR5SBYPI.json","view_paper":"https://pith.science/paper/EAPTUMUJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.06675&json=true","fetch_graph":"https://pith.science/api/pith-number/EAPTUMUJGXIUBPFR6QBR5SBYPI/graph.json","fetch_events":"https://pith.science/api/pith-number/EAPTUMUJGXIUBPFR6QBR5SBYPI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAPTUMUJGXIUBPFR6QBR5SBYPI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAPTUMUJGXIUBPFR6QBR5SBYPI/action/storage_attestation","attest_author":"https://pith.science/pith/EAPTUMUJGXIUBPFR6QBR5SBYPI/action/author_attestation","sign_citation":"https://pith.science/pith/EAPTUMUJGXIUBPFR6QBR5SBYPI/action/citation_signature","submit_replication":"https://pith.science/pith/EAPTUMUJGXIUBPFR6QBR5SBYPI/action/replication_record"}},"created_at":"2026-07-05T10:01:16.763326+00:00","updated_at":"2026-07-05T10:01:16.763326+00:00"}