{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6YC3PSNUCDZKSLLVBFC5JSH6BK","short_pith_number":"pith:6YC3PSNU","schema_version":"1.0","canonical_sha256":"f605b7c9b410f2a92d750945d4c8fe0aa345c43265121508d072cc4f34690ec7","source":{"kind":"arxiv","id":"2201.07438","version":2},"attestation_state":"computed","paper":{"title":"MHTTS: Fast multi-head text-to-speech for spontaneous speech with imperfect transcription","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Dabiao Ma, Feng Ye, Meng Li, Yitong Zhang","submitted_at":"2022-01-19T06:39:00Z","abstract_excerpt":"Neural network based end-to-end Text-to-Speech (TTS) has greatly improved the quality of synthesized speech. While how to use massive spontaneous speech without transcription efficiently still remains an open problem. In this paper, we propose MHTTS, a fast multi-speaker TTS system that is robust to transcription errors and speaking style speech data. Specifically, we introduce a multi-head model and transfer text information from high-quality corpus with manual transcription to spontaneous speech with imperfectly recognized transcription by jointly training them. MHTTS has three advantages: 1"},"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":"2201.07438","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-01-19T06:39:00Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"002f88fd72b8a51c39c545961244bef1d26c4b88fa4b46bb2e089263ee132768","abstract_canon_sha256":"11a0a4c9ab47984c959854c28bf8a7ff76135e62633c7162402e3e2c9446f416"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:04.365917Z","signature_b64":"72yJszZTjfoDH7ZYDtTiqJs5rA9URrmI3jA9tYIgKrehjilPcoqsvG1l+BwqRrXJq8D3uyeVghE5zsArdU9OAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f605b7c9b410f2a92d750945d4c8fe0aa345c43265121508d072cc4f34690ec7","last_reissued_at":"2026-07-05T03:54:04.365557Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:04.365557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MHTTS: Fast multi-head text-to-speech for spontaneous speech with imperfect transcription","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Dabiao Ma, Feng Ye, Meng Li, Yitong Zhang","submitted_at":"2022-01-19T06:39:00Z","abstract_excerpt":"Neural network based end-to-end Text-to-Speech (TTS) has greatly improved the quality of synthesized speech. While how to use massive spontaneous speech without transcription efficiently still remains an open problem. In this paper, we propose MHTTS, a fast multi-speaker TTS system that is robust to transcription errors and speaking style speech data. Specifically, we introduce a multi-head model and transfer text information from high-quality corpus with manual transcription to spontaneous speech with imperfectly recognized transcription by jointly training them. MHTTS has three advantages: 1"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.07438","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/2201.07438/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":"2201.07438","created_at":"2026-07-05T03:54:04.365625+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.07438v2","created_at":"2026-07-05T03:54:04.365625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.07438","created_at":"2026-07-05T03:54:04.365625+00:00"},{"alias_kind":"pith_short_12","alias_value":"6YC3PSNUCDZK","created_at":"2026-07-05T03:54:04.365625+00:00"},{"alias_kind":"pith_short_16","alias_value":"6YC3PSNUCDZKSLLV","created_at":"2026-07-05T03:54:04.365625+00:00"},{"alias_kind":"pith_short_8","alias_value":"6YC3PSNU","created_at":"2026-07-05T03:54:04.365625+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/6YC3PSNUCDZKSLLVBFC5JSH6BK","json":"https://pith.science/pith/6YC3PSNUCDZKSLLVBFC5JSH6BK.json","graph_json":"https://pith.science/api/pith-number/6YC3PSNUCDZKSLLVBFC5JSH6BK/graph.json","events_json":"https://pith.science/api/pith-number/6YC3PSNUCDZKSLLVBFC5JSH6BK/events.json","paper":"https://pith.science/paper/6YC3PSNU"},"agent_actions":{"view_html":"https://pith.science/pith/6YC3PSNUCDZKSLLVBFC5JSH6BK","download_json":"https://pith.science/pith/6YC3PSNUCDZKSLLVBFC5JSH6BK.json","view_paper":"https://pith.science/paper/6YC3PSNU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.07438&json=true","fetch_graph":"https://pith.science/api/pith-number/6YC3PSNUCDZKSLLVBFC5JSH6BK/graph.json","fetch_events":"https://pith.science/api/pith-number/6YC3PSNUCDZKSLLVBFC5JSH6BK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6YC3PSNUCDZKSLLVBFC5JSH6BK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6YC3PSNUCDZKSLLVBFC5JSH6BK/action/storage_attestation","attest_author":"https://pith.science/pith/6YC3PSNUCDZKSLLVBFC5JSH6BK/action/author_attestation","sign_citation":"https://pith.science/pith/6YC3PSNUCDZKSLLVBFC5JSH6BK/action/citation_signature","submit_replication":"https://pith.science/pith/6YC3PSNUCDZKSLLVBFC5JSH6BK/action/replication_record"}},"created_at":"2026-07-05T03:54:04.365625+00:00","updated_at":"2026-07-05T03:54:04.365625+00:00"}