{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IOQD4HDNF2ZRWLX675DO3KJA5F","short_pith_number":"pith:IOQD4HDN","schema_version":"1.0","canonical_sha256":"43a03e1c6d2eb31b2efeff46eda920e977ee1bb247f367bdbb0cae1177271c11","source":{"kind":"arxiv","id":"2012.03500","version":1},"attestation_state":"computed","paper":{"title":"EfficientTTS: An Efficient and High-Quality Text-to-Speech Architecture","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenfeng Miao, Jing Xiao, Jun Ma, Minchuan Chen, Shaojun Wang, Shuang Liang, Zhencheng Liu","submitted_at":"2020-12-07T07:46:46Z","abstract_excerpt":"In this work, we address the Text-to-Speech (TTS) task by proposing a non-autoregressive architecture called EfficientTTS. Unlike the dominant non-autoregressive TTS models, which are trained with the need of external aligners, EfficientTTS optimizes all its parameters with a stable, end-to-end training procedure, while allowing for synthesizing high quality speech in a fast and efficient manner. EfficientTTS is motivated by a new monotonic alignment modeling approach (also introduced in this work), which specifies monotonic constraints to the sequence alignment with almost no increase of comp"},"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":"2012.03500","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2020-12-07T07:46:46Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"ab6cfbd9fb314a1a76cd2137bd7192bc857ff7114ff1d113022d73abbbd090bc","abstract_canon_sha256":"a55a896f938b5424e95739ca1cae41adabad26303d5332ed2a1ee2738b3aebc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:30.323107Z","signature_b64":"GmXJDccuPKAQZlPXZRwBSGAe/c48Q3VwBbhIl6ytehpwfI/+wUVJI38WeuFu9h/aGeb3/BRXd5KSL5eSwo8oAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43a03e1c6d2eb31b2efeff46eda920e977ee1bb247f367bdbb0cae1177271c11","last_reissued_at":"2026-07-05T01:57:30.322694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:30.322694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EfficientTTS: An Efficient and High-Quality Text-to-Speech Architecture","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenfeng Miao, Jing Xiao, Jun Ma, Minchuan Chen, Shaojun Wang, Shuang Liang, Zhencheng Liu","submitted_at":"2020-12-07T07:46:46Z","abstract_excerpt":"In this work, we address the Text-to-Speech (TTS) task by proposing a non-autoregressive architecture called EfficientTTS. Unlike the dominant non-autoregressive TTS models, which are trained with the need of external aligners, EfficientTTS optimizes all its parameters with a stable, end-to-end training procedure, while allowing for synthesizing high quality speech in a fast and efficient manner. EfficientTTS is motivated by a new monotonic alignment modeling approach (also introduced in this work), which specifies monotonic constraints to the sequence alignment with almost no increase of comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.03500","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/2012.03500/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":"2012.03500","created_at":"2026-07-05T01:57:30.322763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.03500v1","created_at":"2026-07-05T01:57:30.322763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.03500","created_at":"2026-07-05T01:57:30.322763+00:00"},{"alias_kind":"pith_short_12","alias_value":"IOQD4HDNF2ZR","created_at":"2026-07-05T01:57:30.322763+00:00"},{"alias_kind":"pith_short_16","alias_value":"IOQD4HDNF2ZRWLX6","created_at":"2026-07-05T01:57:30.322763+00:00"},{"alias_kind":"pith_short_8","alias_value":"IOQD4HDN","created_at":"2026-07-05T01:57:30.322763+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/IOQD4HDNF2ZRWLX675DO3KJA5F","json":"https://pith.science/pith/IOQD4HDNF2ZRWLX675DO3KJA5F.json","graph_json":"https://pith.science/api/pith-number/IOQD4HDNF2ZRWLX675DO3KJA5F/graph.json","events_json":"https://pith.science/api/pith-number/IOQD4HDNF2ZRWLX675DO3KJA5F/events.json","paper":"https://pith.science/paper/IOQD4HDN"},"agent_actions":{"view_html":"https://pith.science/pith/IOQD4HDNF2ZRWLX675DO3KJA5F","download_json":"https://pith.science/pith/IOQD4HDNF2ZRWLX675DO3KJA5F.json","view_paper":"https://pith.science/paper/IOQD4HDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.03500&json=true","fetch_graph":"https://pith.science/api/pith-number/IOQD4HDNF2ZRWLX675DO3KJA5F/graph.json","fetch_events":"https://pith.science/api/pith-number/IOQD4HDNF2ZRWLX675DO3KJA5F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IOQD4HDNF2ZRWLX675DO3KJA5F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IOQD4HDNF2ZRWLX675DO3KJA5F/action/storage_attestation","attest_author":"https://pith.science/pith/IOQD4HDNF2ZRWLX675DO3KJA5F/action/author_attestation","sign_citation":"https://pith.science/pith/IOQD4HDNF2ZRWLX675DO3KJA5F/action/citation_signature","submit_replication":"https://pith.science/pith/IOQD4HDNF2ZRWLX675DO3KJA5F/action/replication_record"}},"created_at":"2026-07-05T01:57:30.322763+00:00","updated_at":"2026-07-05T01:57:30.322763+00:00"}