{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KYMVUQBNZOVD2Y6Z5577FUW6CP","short_pith_number":"pith:KYMVUQBN","schema_version":"1.0","canonical_sha256":"56195a402dcbaa3d63d9ef7ff2d2de13e2400c5c9538d3b112341909fa09397e","source":{"kind":"arxiv","id":"2104.08189","version":3},"attestation_state":"computed","paper":{"title":"TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, Stanislav Beliaev","submitted_at":"2021-04-16T15:58:46Z","abstract_excerpt":"We propose TalkNet, a non-autoregressive convolutional neural model for speech synthesis with explicit pitch and duration prediction. The model consists of three feed-forward convolutional networks. The first network predicts grapheme durations. An input text is expanded by repeating each symbol according to the predicted duration. The second network predicts pitch value for every mel frame. The third network generates a mel-spectrogram from the expanded text conditioned on predicted pitch. All networks are based on 1D depth-wise separable convolutional architecture. The explicit duration pred"},"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":"2104.08189","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-16T15:58:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c5b5886dd0c41fbb6622f15201f1420467cb8e0bc32f04c815c2bfcd41823d9d","abstract_canon_sha256":"7fa58fb12e9b7fe48a385095046eaf35820e928c7df339b2681d970ad23c6a2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:20.105441Z","signature_b64":"ShHFjIi0+hd4fjVvFKJnsxAfJktmCtFgz//JIhfg+uJdRA7FyE1cle8kJySIDmA8giUn5CB+EFTd3kU2MVkcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56195a402dcbaa3d63d9ef7ff2d2de13e2400c5c9538d3b112341909fa09397e","last_reissued_at":"2026-07-05T02:50:20.104926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:20.104926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, Stanislav Beliaev","submitted_at":"2021-04-16T15:58:46Z","abstract_excerpt":"We propose TalkNet, a non-autoregressive convolutional neural model for speech synthesis with explicit pitch and duration prediction. The model consists of three feed-forward convolutional networks. The first network predicts grapheme durations. An input text is expanded by repeating each symbol according to the predicted duration. The second network predicts pitch value for every mel frame. The third network generates a mel-spectrogram from the expanded text conditioned on predicted pitch. All networks are based on 1D depth-wise separable convolutional architecture. The explicit duration pred"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08189","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/2104.08189/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":"2104.08189","created_at":"2026-07-05T02:50:20.104986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.08189v3","created_at":"2026-07-05T02:50:20.104986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08189","created_at":"2026-07-05T02:50:20.104986+00:00"},{"alias_kind":"pith_short_12","alias_value":"KYMVUQBNZOVD","created_at":"2026-07-05T02:50:20.104986+00:00"},{"alias_kind":"pith_short_16","alias_value":"KYMVUQBNZOVD2Y6Z","created_at":"2026-07-05T02:50:20.104986+00:00"},{"alias_kind":"pith_short_8","alias_value":"KYMVUQBN","created_at":"2026-07-05T02:50:20.104986+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.10571","citing_title":"AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KYMVUQBNZOVD2Y6Z5577FUW6CP","json":"https://pith.science/pith/KYMVUQBNZOVD2Y6Z5577FUW6CP.json","graph_json":"https://pith.science/api/pith-number/KYMVUQBNZOVD2Y6Z5577FUW6CP/graph.json","events_json":"https://pith.science/api/pith-number/KYMVUQBNZOVD2Y6Z5577FUW6CP/events.json","paper":"https://pith.science/paper/KYMVUQBN"},"agent_actions":{"view_html":"https://pith.science/pith/KYMVUQBNZOVD2Y6Z5577FUW6CP","download_json":"https://pith.science/pith/KYMVUQBNZOVD2Y6Z5577FUW6CP.json","view_paper":"https://pith.science/paper/KYMVUQBN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.08189&json=true","fetch_graph":"https://pith.science/api/pith-number/KYMVUQBNZOVD2Y6Z5577FUW6CP/graph.json","fetch_events":"https://pith.science/api/pith-number/KYMVUQBNZOVD2Y6Z5577FUW6CP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KYMVUQBNZOVD2Y6Z5577FUW6CP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KYMVUQBNZOVD2Y6Z5577FUW6CP/action/storage_attestation","attest_author":"https://pith.science/pith/KYMVUQBNZOVD2Y6Z5577FUW6CP/action/author_attestation","sign_citation":"https://pith.science/pith/KYMVUQBNZOVD2Y6Z5577FUW6CP/action/citation_signature","submit_replication":"https://pith.science/pith/KYMVUQBNZOVD2Y6Z5577FUW6CP/action/replication_record"}},"created_at":"2026-07-05T02:50:20.104986+00:00","updated_at":"2026-07-05T02:50:20.104986+00:00"}