{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3M642EV2NT7XFSZYVEQAUGLOYV","short_pith_number":"pith:3M642EV2","schema_version":"1.0","canonical_sha256":"db3dcd12ba6cff72cb38a9200a196ec5753fe7fdd5d0f3d1e8c20e3dfb1f8515","source":{"kind":"arxiv","id":"2102.00247","version":4},"attestation_state":"computed","paper":{"title":"Triple M: A Practical Text-to-speech Synthesis System With Multi-guidance Attention And Multi-band Multi-time LPCNet","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Fenglong Xie, Li Lu, Li Meng, Shilun Lin, Xinhui Li","submitted_at":"2021-01-30T15:38:36Z","abstract_excerpt":"In this work, a robust and efficient text-to-speech (TTS) synthesis system named Triple M is proposed for large-scale online application. The key components of Triple M are: 1) A sequence-to-sequence model adopts a novel multi-guidance attention to transfer complementary advantages from guiding attention mechanisms to the basic attention mechanism without in-domain performance loss and online service modification. Compared with single attention mechanism, multi-guidance attention not only brings better naturalness to long sentence synthesis, but also reduces the word error rate by 26.8%. 2) A "},"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":"2102.00247","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-30T15:38:36Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"bca4c1da079c4cf84c4e7183bd0a4472913b5f051905a64e3640d345cbb948eb","abstract_canon_sha256":"a545db6de77b990b06bebb59d8e695adeb7ee226f3a85eb5e826298db02ad1d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:57.338804Z","signature_b64":"sxVvtDyOStrrWXK2hA61+1AnggPpEW6zOB5Mlvl0J3Fg/W+vBWMl012rY3H8uSyLmcYlExfyB7aptRNeBT5NCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db3dcd12ba6cff72cb38a9200a196ec5753fe7fdd5d0f3d1e8c20e3dfb1f8515","last_reissued_at":"2026-07-05T02:29:57.338346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:57.338346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Triple M: A Practical Text-to-speech Synthesis System With Multi-guidance Attention And Multi-band Multi-time LPCNet","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Fenglong Xie, Li Lu, Li Meng, Shilun Lin, Xinhui Li","submitted_at":"2021-01-30T15:38:36Z","abstract_excerpt":"In this work, a robust and efficient text-to-speech (TTS) synthesis system named Triple M is proposed for large-scale online application. The key components of Triple M are: 1) A sequence-to-sequence model adopts a novel multi-guidance attention to transfer complementary advantages from guiding attention mechanisms to the basic attention mechanism without in-domain performance loss and online service modification. Compared with single attention mechanism, multi-guidance attention not only brings better naturalness to long sentence synthesis, but also reduces the word error rate by 26.8%. 2) A "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.00247","kind":"arxiv","version":4},"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/2102.00247/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":"2102.00247","created_at":"2026-07-05T02:29:57.338405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.00247v4","created_at":"2026-07-05T02:29:57.338405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.00247","created_at":"2026-07-05T02:29:57.338405+00:00"},{"alias_kind":"pith_short_12","alias_value":"3M642EV2NT7X","created_at":"2026-07-05T02:29:57.338405+00:00"},{"alias_kind":"pith_short_16","alias_value":"3M642EV2NT7XFSZY","created_at":"2026-07-05T02:29:57.338405+00:00"},{"alias_kind":"pith_short_8","alias_value":"3M642EV2","created_at":"2026-07-05T02:29:57.338405+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/3M642EV2NT7XFSZYVEQAUGLOYV","json":"https://pith.science/pith/3M642EV2NT7XFSZYVEQAUGLOYV.json","graph_json":"https://pith.science/api/pith-number/3M642EV2NT7XFSZYVEQAUGLOYV/graph.json","events_json":"https://pith.science/api/pith-number/3M642EV2NT7XFSZYVEQAUGLOYV/events.json","paper":"https://pith.science/paper/3M642EV2"},"agent_actions":{"view_html":"https://pith.science/pith/3M642EV2NT7XFSZYVEQAUGLOYV","download_json":"https://pith.science/pith/3M642EV2NT7XFSZYVEQAUGLOYV.json","view_paper":"https://pith.science/paper/3M642EV2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.00247&json=true","fetch_graph":"https://pith.science/api/pith-number/3M642EV2NT7XFSZYVEQAUGLOYV/graph.json","fetch_events":"https://pith.science/api/pith-number/3M642EV2NT7XFSZYVEQAUGLOYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3M642EV2NT7XFSZYVEQAUGLOYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3M642EV2NT7XFSZYVEQAUGLOYV/action/storage_attestation","attest_author":"https://pith.science/pith/3M642EV2NT7XFSZYVEQAUGLOYV/action/author_attestation","sign_citation":"https://pith.science/pith/3M642EV2NT7XFSZYVEQAUGLOYV/action/citation_signature","submit_replication":"https://pith.science/pith/3M642EV2NT7XFSZYVEQAUGLOYV/action/replication_record"}},"created_at":"2026-07-05T02:29:57.338405+00:00","updated_at":"2026-07-05T02:29:57.338405+00:00"}