{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:U7GGVGLJQFPW6QN55ZVPCA4VY6","short_pith_number":"pith:U7GGVGLJ","schema_version":"1.0","canonical_sha256":"a7cc6a9969815f6f41bdee6af10395c7900e823e29d65fabe767ccd2d8800b1b","source":{"kind":"arxiv","id":"1911.09645","version":2},"attestation_state":"computed","paper":{"title":"Prosody Transfer in Neural Text to Speech Using Global Pitch and Loudness Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dhaval Shah, Jervis Pinto, Kilol Gupta, Siddharth Gururani, Zahra Shakeri","submitted_at":"2019-11-21T18:04:47Z","abstract_excerpt":"This paper presents a simple yet effective method to achieve prosody transfer from a reference speech signal to synthesized speech. The main idea is to incorporate well-known acoustic correlates of prosody such as pitch and loudness contours of the reference speech into a modern neural text-to-speech (TTS) synthesizer such as Tacotron2 (TC2). More specifically, a small set of acoustic features are extracted from reference audio and then used to condition a TC2 synthesizer. The trained model is evaluated using subjective listening tests and a novel objective evaluation of prosody transfer is pr"},"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":"1911.09645","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-11-21T18:04:47Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"942856e5a33c4e039c75d890b5e5234fe6b1176677234defe3efdf2101f2cddf","abstract_canon_sha256":"e98150c1fc0e889ce5f04f09f7aff1fe21fad44f34cc7cd0245cb01ad62f8bd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:07.452737Z","signature_b64":"mpmIzKNWDgsg6mSyEzX4vOj/pPqpS65+hPYv5fZAZqlzmrJbp4BEyNvwwUSRjwqkVW9byNNNWSH9hlZF6MgfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7cc6a9969815f6f41bdee6af10395c7900e823e29d65fabe767ccd2d8800b1b","last_reissued_at":"2026-07-05T01:03:07.452283Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:07.452283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prosody Transfer in Neural Text to Speech Using Global Pitch and Loudness Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dhaval Shah, Jervis Pinto, Kilol Gupta, Siddharth Gururani, Zahra Shakeri","submitted_at":"2019-11-21T18:04:47Z","abstract_excerpt":"This paper presents a simple yet effective method to achieve prosody transfer from a reference speech signal to synthesized speech. The main idea is to incorporate well-known acoustic correlates of prosody such as pitch and loudness contours of the reference speech into a modern neural text-to-speech (TTS) synthesizer such as Tacotron2 (TC2). More specifically, a small set of acoustic features are extracted from reference audio and then used to condition a TC2 synthesizer. The trained model is evaluated using subjective listening tests and a novel objective evaluation of prosody transfer is pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.09645","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/1911.09645/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":"1911.09645","created_at":"2026-07-05T01:03:07.452347+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.09645v2","created_at":"2026-07-05T01:03:07.452347+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.09645","created_at":"2026-07-05T01:03:07.452347+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7GGVGLJQFPW","created_at":"2026-07-05T01:03:07.452347+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7GGVGLJQFPW6QN5","created_at":"2026-07-05T01:03:07.452347+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7GGVGLJ","created_at":"2026-07-05T01:03:07.452347+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22612","citing_title":"Adaptive Duration Model for Text Speech Alignment","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U7GGVGLJQFPW6QN55ZVPCA4VY6","json":"https://pith.science/pith/U7GGVGLJQFPW6QN55ZVPCA4VY6.json","graph_json":"https://pith.science/api/pith-number/U7GGVGLJQFPW6QN55ZVPCA4VY6/graph.json","events_json":"https://pith.science/api/pith-number/U7GGVGLJQFPW6QN55ZVPCA4VY6/events.json","paper":"https://pith.science/paper/U7GGVGLJ"},"agent_actions":{"view_html":"https://pith.science/pith/U7GGVGLJQFPW6QN55ZVPCA4VY6","download_json":"https://pith.science/pith/U7GGVGLJQFPW6QN55ZVPCA4VY6.json","view_paper":"https://pith.science/paper/U7GGVGLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.09645&json=true","fetch_graph":"https://pith.science/api/pith-number/U7GGVGLJQFPW6QN55ZVPCA4VY6/graph.json","fetch_events":"https://pith.science/api/pith-number/U7GGVGLJQFPW6QN55ZVPCA4VY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7GGVGLJQFPW6QN55ZVPCA4VY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7GGVGLJQFPW6QN55ZVPCA4VY6/action/storage_attestation","attest_author":"https://pith.science/pith/U7GGVGLJQFPW6QN55ZVPCA4VY6/action/author_attestation","sign_citation":"https://pith.science/pith/U7GGVGLJQFPW6QN55ZVPCA4VY6/action/citation_signature","submit_replication":"https://pith.science/pith/U7GGVGLJQFPW6QN55ZVPCA4VY6/action/replication_record"}},"created_at":"2026-07-05T01:03:07.452347+00:00","updated_at":"2026-07-05T01:03:07.452347+00:00"}