{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UINQU6KYDTSWKPDV4YGVEXHSF5","short_pith_number":"pith:UINQU6KY","schema_version":"1.0","canonical_sha256":"a21b0a79581ce5653c75e60d525cf22f72120855a0b57dcb655a7f29417584a8","source":{"kind":"arxiv","id":"2501.06320","version":1},"attestation_state":"computed","paper":{"title":"TTS-Transducer: End-to-End Speech Synthesis with Neural Transducer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jason Li, Subhankar Ghosh, Vitaly Lavrukhin, Vladimir Bataev","submitted_at":"2025-01-10T19:50:32Z","abstract_excerpt":"This work introduces TTS-Transducer - a novel architecture for text-to-speech, leveraging the strengths of audio codec models and neural transducers. Transducers, renowned for their superior quality and robustness in speech recognition, are employed to learn monotonic alignments and allow for avoiding using explicit duration predictors. Neural audio codecs efficiently compress audio into discrete codes, revealing the possibility of applying text modeling approaches to speech generation. However, the complexity of predicting multiple tokens per frame from several codebooks, as necessitated by 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":"2501.06320","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-10T19:50:32Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"468528d502fa1a6cf877efbe314260fae4c7954e3343086eeae86f20bc6efb69","abstract_canon_sha256":"da434af765fd01c8557efc2acce86812a63b045d5b84566c48b19f1c3e056208"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:12.863857Z","signature_b64":"uiScHsiFPhaf/zusWDnlvpCGb3oXaq/vomc3vGp+e+FR+y3B5Y7yd9pkvfrtJ9K/b4ludYk64eLriZnjFzy+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a21b0a79581ce5653c75e60d525cf22f72120855a0b57dcb655a7f29417584a8","last_reissued_at":"2026-07-05T10:49:12.863346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:12.863346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TTS-Transducer: End-to-End Speech Synthesis with Neural Transducer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jason Li, Subhankar Ghosh, Vitaly Lavrukhin, Vladimir Bataev","submitted_at":"2025-01-10T19:50:32Z","abstract_excerpt":"This work introduces TTS-Transducer - a novel architecture for text-to-speech, leveraging the strengths of audio codec models and neural transducers. Transducers, renowned for their superior quality and robustness in speech recognition, are employed to learn monotonic alignments and allow for avoiding using explicit duration predictors. Neural audio codecs efficiently compress audio into discrete codes, revealing the possibility of applying text modeling approaches to speech generation. However, the complexity of predicting multiple tokens per frame from several codebooks, as necessitated by a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06320","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/2501.06320/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":"2501.06320","created_at":"2026-07-05T10:49:12.863406+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.06320v1","created_at":"2026-07-05T10:49:12.863406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06320","created_at":"2026-07-05T10:49:12.863406+00:00"},{"alias_kind":"pith_short_12","alias_value":"UINQU6KYDTSW","created_at":"2026-07-05T10:49:12.863406+00:00"},{"alias_kind":"pith_short_16","alias_value":"UINQU6KYDTSWKPDV","created_at":"2026-07-05T10:49:12.863406+00:00"},{"alias_kind":"pith_short_8","alias_value":"UINQU6KY","created_at":"2026-07-05T10:49:12.863406+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/UINQU6KYDTSWKPDV4YGVEXHSF5","json":"https://pith.science/pith/UINQU6KYDTSWKPDV4YGVEXHSF5.json","graph_json":"https://pith.science/api/pith-number/UINQU6KYDTSWKPDV4YGVEXHSF5/graph.json","events_json":"https://pith.science/api/pith-number/UINQU6KYDTSWKPDV4YGVEXHSF5/events.json","paper":"https://pith.science/paper/UINQU6KY"},"agent_actions":{"view_html":"https://pith.science/pith/UINQU6KYDTSWKPDV4YGVEXHSF5","download_json":"https://pith.science/pith/UINQU6KYDTSWKPDV4YGVEXHSF5.json","view_paper":"https://pith.science/paper/UINQU6KY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.06320&json=true","fetch_graph":"https://pith.science/api/pith-number/UINQU6KYDTSWKPDV4YGVEXHSF5/graph.json","fetch_events":"https://pith.science/api/pith-number/UINQU6KYDTSWKPDV4YGVEXHSF5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UINQU6KYDTSWKPDV4YGVEXHSF5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UINQU6KYDTSWKPDV4YGVEXHSF5/action/storage_attestation","attest_author":"https://pith.science/pith/UINQU6KYDTSWKPDV4YGVEXHSF5/action/author_attestation","sign_citation":"https://pith.science/pith/UINQU6KYDTSWKPDV4YGVEXHSF5/action/citation_signature","submit_replication":"https://pith.science/pith/UINQU6KYDTSWKPDV4YGVEXHSF5/action/replication_record"}},"created_at":"2026-07-05T10:49:12.863406+00:00","updated_at":"2026-07-05T10:49:12.863406+00:00"}