{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WW7RRZQUI5YUTPV4QAATAUA2NQ","short_pith_number":"pith:WW7RRZQU","schema_version":"1.0","canonical_sha256":"b5bf18e614477149bebc800130501a6c2f8eb69605ec85aa0dadcd5021b8fef6","source":{"kind":"arxiv","id":"2401.16812","version":3},"attestation_state":"computed","paper":{"title":"SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hiroshi Saruwatari, Shinji Watanabe, Shinnosuke Takamichi, Soumi Maiti, Takaaki Saeki","submitted_at":"2024-01-30T08:26:28Z","abstract_excerpt":"While subjective assessments have been the gold standard for evaluating speech generation, there is a growing need for objective metrics that are highly correlated with human subjective judgments due to their cost efficiency. This paper proposes reference-aware automatic evaluation methods for speech generation inspired by evaluation metrics in natural language processing. The proposed SpeechBERTScore computes the BERTScore for self-supervised dense speech features of the generated and reference speech, which can have different sequential lengths. We also propose SpeechBLEU and SpeechTokenDist"},"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":"2401.16812","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-01-30T08:26:28Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"e88744413dd9643583399de8e35ac2525d4eb03deb386b1c1028ba68c4ae59d8","abstract_canon_sha256":"55734453c5f1afa7a15b8c3693dc2af512680e4c34f3dca3f8342ab6c885f00b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:29.412186Z","signature_b64":"JMCfhIMrV0R0iQUhC3bPxq+NY6t6fsGWddcDW/tp4NQrGCd7sZKkSMUK3Qh6FSmTPYFYLQwoPdrEBmq5R3kZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5bf18e614477149bebc800130501a6c2f8eb69605ec85aa0dadcd5021b8fef6","last_reissued_at":"2026-07-05T09:01:29.411629Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:29.411629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hiroshi Saruwatari, Shinji Watanabe, Shinnosuke Takamichi, Soumi Maiti, Takaaki Saeki","submitted_at":"2024-01-30T08:26:28Z","abstract_excerpt":"While subjective assessments have been the gold standard for evaluating speech generation, there is a growing need for objective metrics that are highly correlated with human subjective judgments due to their cost efficiency. This paper proposes reference-aware automatic evaluation methods for speech generation inspired by evaluation metrics in natural language processing. The proposed SpeechBERTScore computes the BERTScore for self-supervised dense speech features of the generated and reference speech, which can have different sequential lengths. We also propose SpeechBLEU and SpeechTokenDist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16812","kind":"arxiv","version":3},"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/2401.16812/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":"2401.16812","created_at":"2026-07-05T09:01:29.411689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.16812v3","created_at":"2026-07-05T09:01:29.411689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16812","created_at":"2026-07-05T09:01:29.411689+00:00"},{"alias_kind":"pith_short_12","alias_value":"WW7RRZQUI5YU","created_at":"2026-07-05T09:01:29.411689+00:00"},{"alias_kind":"pith_short_16","alias_value":"WW7RRZQUI5YUTPV4","created_at":"2026-07-05T09:01:29.411689+00:00"},{"alias_kind":"pith_short_8","alias_value":"WW7RRZQU","created_at":"2026-07-05T09:01:29.411689+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.06392","citing_title":"InsideSSL: Understanding Self-Supervised Speech Representations using a Model-Centric Perspective","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09837","citing_title":"Self-EmoQ: Plutchik-Guided Value-based Planning to Drive Streaming Emotional TTS","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2411.03715","citing_title":"MOS-Bench: Benchmarking Generalization Abilities of Subjective Speech Quality Assessment Models","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WW7RRZQUI5YUTPV4QAATAUA2NQ","json":"https://pith.science/pith/WW7RRZQUI5YUTPV4QAATAUA2NQ.json","graph_json":"https://pith.science/api/pith-number/WW7RRZQUI5YUTPV4QAATAUA2NQ/graph.json","events_json":"https://pith.science/api/pith-number/WW7RRZQUI5YUTPV4QAATAUA2NQ/events.json","paper":"https://pith.science/paper/WW7RRZQU"},"agent_actions":{"view_html":"https://pith.science/pith/WW7RRZQUI5YUTPV4QAATAUA2NQ","download_json":"https://pith.science/pith/WW7RRZQUI5YUTPV4QAATAUA2NQ.json","view_paper":"https://pith.science/paper/WW7RRZQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.16812&json=true","fetch_graph":"https://pith.science/api/pith-number/WW7RRZQUI5YUTPV4QAATAUA2NQ/graph.json","fetch_events":"https://pith.science/api/pith-number/WW7RRZQUI5YUTPV4QAATAUA2NQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WW7RRZQUI5YUTPV4QAATAUA2NQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WW7RRZQUI5YUTPV4QAATAUA2NQ/action/storage_attestation","attest_author":"https://pith.science/pith/WW7RRZQUI5YUTPV4QAATAUA2NQ/action/author_attestation","sign_citation":"https://pith.science/pith/WW7RRZQUI5YUTPV4QAATAUA2NQ/action/citation_signature","submit_replication":"https://pith.science/pith/WW7RRZQUI5YUTPV4QAATAUA2NQ/action/replication_record"}},"created_at":"2026-07-05T09:01:29.411689+00:00","updated_at":"2026-07-05T09:01:29.411689+00:00"}