{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QBLS5IOU7SQ574YG3DYR2QM5GD","short_pith_number":"pith:QBLS5IOU","schema_version":"1.0","canonical_sha256":"80572ea1d4fca1dff306d8f11d419d30ee03dbd6b497600f97a665319d7b4468","source":{"kind":"arxiv","id":"2301.07087","version":2},"attestation_state":"computed","paper":{"title":"MooseNet: A Trainable Metric for Synthesized Speech with a PLDA Module","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ond\\v{r}ej Du\\v{s}ek, Ond\\v{r}ej Pl\\'atek","submitted_at":"2023-01-17T18:53:15Z","abstract_excerpt":"We present MooseNet, a trainable speech metric that predicts the listeners' Mean Opinion Score (MOS). We propose a novel approach where the Probabilistic Linear Discriminative Analysis (PLDA) generative model is used on top of an embedding obtained from a self-supervised learning (SSL) neural network (NN) model. We show that PLDA works well with a non-finetuned SSL model when trained only on 136 utterances (ca. one minute training time) and that PLDA consistently improves various neural MOS prediction models, even state-of-the-art models with task-specific fine-tuning. Our ablation study shows"},"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":"2301.07087","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-17T18:53:15Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d65f1152f18b7a39a2639c4d939cbba1d5c9223ded3c5b65124447d10e449507","abstract_canon_sha256":"b21ece1240f5a02779f086d5bc194a9203bfb34ccb0b85e4c6ddd9b026c5f8e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:05.834280Z","signature_b64":"5avqpy1AwJwWdPLla+HwdduQ7nwS7PBmEJ+QgadiXVkAZaD0kX0wVQtd8aILNB2poZYssYmexY6ydqHaPB6xCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80572ea1d4fca1dff306d8f11d419d30ee03dbd6b497600f97a665319d7b4468","last_reissued_at":"2026-07-05T07:05:05.833769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:05.833769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MooseNet: A Trainable Metric for Synthesized Speech with a PLDA Module","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ond\\v{r}ej Du\\v{s}ek, Ond\\v{r}ej Pl\\'atek","submitted_at":"2023-01-17T18:53:15Z","abstract_excerpt":"We present MooseNet, a trainable speech metric that predicts the listeners' Mean Opinion Score (MOS). We propose a novel approach where the Probabilistic Linear Discriminative Analysis (PLDA) generative model is used on top of an embedding obtained from a self-supervised learning (SSL) neural network (NN) model. We show that PLDA works well with a non-finetuned SSL model when trained only on 136 utterances (ca. one minute training time) and that PLDA consistently improves various neural MOS prediction models, even state-of-the-art models with task-specific fine-tuning. Our ablation study shows"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.07087","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/2301.07087/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":"2301.07087","created_at":"2026-07-05T07:05:05.833837+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.07087v2","created_at":"2026-07-05T07:05:05.833837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.07087","created_at":"2026-07-05T07:05:05.833837+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBLS5IOU7SQ5","created_at":"2026-07-05T07:05:05.833837+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBLS5IOU7SQ574YG","created_at":"2026-07-05T07:05:05.833837+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBLS5IOU","created_at":"2026-07-05T07:05:05.833837+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/QBLS5IOU7SQ574YG3DYR2QM5GD","json":"https://pith.science/pith/QBLS5IOU7SQ574YG3DYR2QM5GD.json","graph_json":"https://pith.science/api/pith-number/QBLS5IOU7SQ574YG3DYR2QM5GD/graph.json","events_json":"https://pith.science/api/pith-number/QBLS5IOU7SQ574YG3DYR2QM5GD/events.json","paper":"https://pith.science/paper/QBLS5IOU"},"agent_actions":{"view_html":"https://pith.science/pith/QBLS5IOU7SQ574YG3DYR2QM5GD","download_json":"https://pith.science/pith/QBLS5IOU7SQ574YG3DYR2QM5GD.json","view_paper":"https://pith.science/paper/QBLS5IOU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.07087&json=true","fetch_graph":"https://pith.science/api/pith-number/QBLS5IOU7SQ574YG3DYR2QM5GD/graph.json","fetch_events":"https://pith.science/api/pith-number/QBLS5IOU7SQ574YG3DYR2QM5GD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBLS5IOU7SQ574YG3DYR2QM5GD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBLS5IOU7SQ574YG3DYR2QM5GD/action/storage_attestation","attest_author":"https://pith.science/pith/QBLS5IOU7SQ574YG3DYR2QM5GD/action/author_attestation","sign_citation":"https://pith.science/pith/QBLS5IOU7SQ574YG3DYR2QM5GD/action/citation_signature","submit_replication":"https://pith.science/pith/QBLS5IOU7SQ574YG3DYR2QM5GD/action/replication_record"}},"created_at":"2026-07-05T07:05:05.833837+00:00","updated_at":"2026-07-05T07:05:05.833837+00:00"}