{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6TP5GV3F6CWTSZWTCEL6UE553P","short_pith_number":"pith:6TP5GV3F","schema_version":"1.0","canonical_sha256":"f4dfd35765f0ad3966d31117ea13bddbc84dfbfda90144d3ee7044f81e7a307b","source":{"kind":"arxiv","id":"2406.18009","version":2},"attestation_state":"computed","paper":{"title":"E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Canrun Li, Chung-Hsien Tsai, Hemin Yang, Manthan Thakker, Min Tang, Naoyuki Kanda, Sefik Emre Eskimez, Sheng Zhao, Xiaofei Wang, Xu Tan, Yanqing Liu, Zhen Xiao, Zirun Zhu","submitted_at":"2024-06-26T01:38:37Z","abstract_excerpt":"This paper introduces Embarrassingly Easy Text-to-Speech (E2 TTS), a fully non-autoregressive zero-shot text-to-speech system that offers human-level naturalness and state-of-the-art speaker similarity and intelligibility. In the E2 TTS framework, the text input is converted into a character sequence with filler tokens. The flow-matching-based mel spectrogram generator is then trained based on the audio infilling task. Unlike many previous works, it does not require additional components (e.g., duration model, grapheme-to-phoneme) or complex techniques (e.g., monotonic alignment search). Despi"},"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":"2406.18009","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-26T01:38:37Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"2947cc99373d3b3d8d0d7bd89d7946f627dde439fead4ff1f1875bfde11f38b6","abstract_canon_sha256":"3d5db474f05ff244b374b80b5995928e8bb3401e73f361f8450bf24b3a819ef0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:06.603119Z","signature_b64":"2CtMU/RlrqycdbX38/1Dk8rg0+wRGTEoJk4zELFmR4kdEHWHhkYta8/Zn6orFGhdUm1A3AJtNAsTKrGPb1hhBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4dfd35765f0ad3966d31117ea13bddbc84dfbfda90144d3ee7044f81e7a307b","last_reissued_at":"2026-07-05T09:06:06.602595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:06.602595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Canrun Li, Chung-Hsien Tsai, Hemin Yang, Manthan Thakker, Min Tang, Naoyuki Kanda, Sefik Emre Eskimez, Sheng Zhao, Xiaofei Wang, Xu Tan, Yanqing Liu, Zhen Xiao, Zirun Zhu","submitted_at":"2024-06-26T01:38:37Z","abstract_excerpt":"This paper introduces Embarrassingly Easy Text-to-Speech (E2 TTS), a fully non-autoregressive zero-shot text-to-speech system that offers human-level naturalness and state-of-the-art speaker similarity and intelligibility. In the E2 TTS framework, the text input is converted into a character sequence with filler tokens. The flow-matching-based mel spectrogram generator is then trained based on the audio infilling task. Unlike many previous works, it does not require additional components (e.g., duration model, grapheme-to-phoneme) or complex techniques (e.g., monotonic alignment search). Despi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18009","kind":"arxiv","version":2},"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/2406.18009/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":"2406.18009","created_at":"2026-07-05T09:06:06.602663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18009v2","created_at":"2026-07-05T09:06:06.602663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18009","created_at":"2026-07-05T09:06:06.602663+00:00"},{"alias_kind":"pith_short_12","alias_value":"6TP5GV3F6CWT","created_at":"2026-07-05T09:06:06.602663+00:00"},{"alias_kind":"pith_short_16","alias_value":"6TP5GV3F6CWTSZWT","created_at":"2026-07-05T09:06:06.602663+00:00"},{"alias_kind":"pith_short_8","alias_value":"6TP5GV3F","created_at":"2026-07-05T09:06:06.602663+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.09318","citing_title":"ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2410.06885","citing_title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17589","citing_title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2412.10117","citing_title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26296","citing_title":"SPG-Codec: Exploring the Role and Boundaries of Semantic Priors in Ultra-Low-Bitrate Neural Speech Coding","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":81,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6TP5GV3F6CWTSZWTCEL6UE553P","json":"https://pith.science/pith/6TP5GV3F6CWTSZWTCEL6UE553P.json","graph_json":"https://pith.science/api/pith-number/6TP5GV3F6CWTSZWTCEL6UE553P/graph.json","events_json":"https://pith.science/api/pith-number/6TP5GV3F6CWTSZWTCEL6UE553P/events.json","paper":"https://pith.science/paper/6TP5GV3F"},"agent_actions":{"view_html":"https://pith.science/pith/6TP5GV3F6CWTSZWTCEL6UE553P","download_json":"https://pith.science/pith/6TP5GV3F6CWTSZWTCEL6UE553P.json","view_paper":"https://pith.science/paper/6TP5GV3F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18009&json=true","fetch_graph":"https://pith.science/api/pith-number/6TP5GV3F6CWTSZWTCEL6UE553P/graph.json","fetch_events":"https://pith.science/api/pith-number/6TP5GV3F6CWTSZWTCEL6UE553P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6TP5GV3F6CWTSZWTCEL6UE553P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6TP5GV3F6CWTSZWTCEL6UE553P/action/storage_attestation","attest_author":"https://pith.science/pith/6TP5GV3F6CWTSZWTCEL6UE553P/action/author_attestation","sign_citation":"https://pith.science/pith/6TP5GV3F6CWTSZWTCEL6UE553P/action/citation_signature","submit_replication":"https://pith.science/pith/6TP5GV3F6CWTSZWTCEL6UE553P/action/replication_record"}},"created_at":"2026-07-05T09:06:06.602663+00:00","updated_at":"2026-07-05T09:06:06.602663+00:00"}