{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2NTYGFV4HFUW6P4G2ELT6TYSBR","short_pith_number":"pith:2NTYGFV4","schema_version":"1.0","canonical_sha256":"d3678316bc39696f3f86d1173f4f120c599c84094b357aac4d2d2d232f595ff2","source":{"kind":"arxiv","id":"2506.19398","version":1},"attestation_state":"computed","paper":{"title":"ClearerVoice-Studio: Bridging Advanced Speech Processing Research and Practical Deployment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Ma, Shengkui Zhao, Zexu Pan","submitted_at":"2025-06-24T08:01:33Z","abstract_excerpt":"This paper introduces ClearerVoice-Studio, an open-source, AI-powered speech processing toolkit designed to bridge cutting-edge research and practical application. Unlike broad platforms like SpeechBrain and ESPnet, ClearerVoice-Studio focuses on interconnected speech tasks of speech enhancement, separation, super-resolution, and multimodal target speaker extraction. A key advantage is its state-of-the-art pretrained models, including FRCRN with 3 million uses and MossFormer with 2.5 million uses, optimized for real-world scenarios. It also offers model optimization tools, multi-format audio s"},"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":"2506.19398","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-24T08:01:33Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"dca0372bda13e9bb1afde8f86f06d81e20b7a81ac664f9d1f42897bf9907a61e","abstract_canon_sha256":"38d776e69ca4ad30bbc81fc81edf01a1b5ab6e6b6c106f0c7e40106a22456fbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:14.585307Z","signature_b64":"xz8nyhneg/l/0UFFdRq3SM7NMIFPwMS0SBMm6zHi635CyFIp0SV2uzhrhxpL9Dv+9vN+KwlYVLiuBj1nyUs5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3678316bc39696f3f86d1173f4f120c599c84094b357aac4d2d2d232f595ff2","last_reissued_at":"2026-07-05T11:26:14.584779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:14.584779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ClearerVoice-Studio: Bridging Advanced Speech Processing Research and Practical Deployment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Ma, Shengkui Zhao, Zexu Pan","submitted_at":"2025-06-24T08:01:33Z","abstract_excerpt":"This paper introduces ClearerVoice-Studio, an open-source, AI-powered speech processing toolkit designed to bridge cutting-edge research and practical application. Unlike broad platforms like SpeechBrain and ESPnet, ClearerVoice-Studio focuses on interconnected speech tasks of speech enhancement, separation, super-resolution, and multimodal target speaker extraction. A key advantage is its state-of-the-art pretrained models, including FRCRN with 3 million uses and MossFormer with 2.5 million uses, optimized for real-world scenarios. It also offers model optimization tools, multi-format audio s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19398","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/2506.19398/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":"2506.19398","created_at":"2026-07-05T11:26:14.584854+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19398v1","created_at":"2026-07-05T11:26:14.584854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19398","created_at":"2026-07-05T11:26:14.584854+00:00"},{"alias_kind":"pith_short_12","alias_value":"2NTYGFV4HFUW","created_at":"2026-07-05T11:26:14.584854+00:00"},{"alias_kind":"pith_short_16","alias_value":"2NTYGFV4HFUW6P4G","created_at":"2026-07-05T11:26:14.584854+00:00"},{"alias_kind":"pith_short_8","alias_value":"2NTYGFV4","created_at":"2026-07-05T11:26:14.584854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11828","citing_title":"Feature-Aligned Speech Watermarking for Robustness to Reconstruction Distortions","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17225","citing_title":"Can Large Audio Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10367","citing_title":"Beyond Monologue: Interactive Talking-Listening Avatar Generation with Conversational Audio Context-Aware Kernels","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15923","citing_title":"Hierarchical Codec Diffusion for Video-to-Speech Generation","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2NTYGFV4HFUW6P4G2ELT6TYSBR","json":"https://pith.science/pith/2NTYGFV4HFUW6P4G2ELT6TYSBR.json","graph_json":"https://pith.science/api/pith-number/2NTYGFV4HFUW6P4G2ELT6TYSBR/graph.json","events_json":"https://pith.science/api/pith-number/2NTYGFV4HFUW6P4G2ELT6TYSBR/events.json","paper":"https://pith.science/paper/2NTYGFV4"},"agent_actions":{"view_html":"https://pith.science/pith/2NTYGFV4HFUW6P4G2ELT6TYSBR","download_json":"https://pith.science/pith/2NTYGFV4HFUW6P4G2ELT6TYSBR.json","view_paper":"https://pith.science/paper/2NTYGFV4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19398&json=true","fetch_graph":"https://pith.science/api/pith-number/2NTYGFV4HFUW6P4G2ELT6TYSBR/graph.json","fetch_events":"https://pith.science/api/pith-number/2NTYGFV4HFUW6P4G2ELT6TYSBR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2NTYGFV4HFUW6P4G2ELT6TYSBR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2NTYGFV4HFUW6P4G2ELT6TYSBR/action/storage_attestation","attest_author":"https://pith.science/pith/2NTYGFV4HFUW6P4G2ELT6TYSBR/action/author_attestation","sign_citation":"https://pith.science/pith/2NTYGFV4HFUW6P4G2ELT6TYSBR/action/citation_signature","submit_replication":"https://pith.science/pith/2NTYGFV4HFUW6P4G2ELT6TYSBR/action/replication_record"}},"created_at":"2026-07-05T11:26:14.584854+00:00","updated_at":"2026-07-05T11:26:14.584854+00:00"}