{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XTQBDUY2GIF4FM7PVQEOPQIIJY","short_pith_number":"pith:XTQBDUY2","schema_version":"1.0","canonical_sha256":"bce011d31a320bc2b3efac08e7c1084e2c84013c58a20920e75b3937c2d01016","source":{"kind":"arxiv","id":"2606.05367","version":1},"attestation_state":"computed","paper":{"title":"Task-Vector Arithmetic for Emotional Expressivity Control in Language-Model-Based Text-to-Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Arnaldo Candido Junior, Daniel Oliveira de Brito","submitted_at":"2026-06-03T19:15:28Z","abstract_excerpt":"We investigate whether task-vector arithmetic, successful for cross-speaker emotional intensity control in modular text-to-speech (TTS), transfers to large-scale TTS systems built on language-model backbones with in-context learning (LM-TTS). Through a systematic elimination study over four progressively narrower operands on Qwen3-TTS-12Hz-1.7B - model weights via LoRA fine-tuning, continuous codec embeddings, discrete codec tokens, and the speaker embedding (x-vector) produced by an ECAPA-TDNN encoder jointly trained with the synthesis backbone - we localize the dominant carrier of emotional "},"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":"2606.05367","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-03T19:15:28Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"a7671cffe7499d50b18552c94398b20a7baa1365a13edadef513ead4e47930bd","abstract_canon_sha256":"b5350936380661f1cdb68abd3e6e7c3ff86d5faa02eded00bbed73750d8af568"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:55.511000Z","signature_b64":"jTjlBFYqxBT3K0vHtP30nMQ2kSSogT6D+7KPNZW1NUSFVqDyMPICenZ4siK3S3M/FtVM/AEb88qZ3ByFjTPmAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bce011d31a320bc2b3efac08e7c1084e2c84013c58a20920e75b3937c2d01016","last_reissued_at":"2026-06-05T00:13:55.510578Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:55.510578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task-Vector Arithmetic for Emotional Expressivity Control in Language-Model-Based Text-to-Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Arnaldo Candido Junior, Daniel Oliveira de Brito","submitted_at":"2026-06-03T19:15:28Z","abstract_excerpt":"We investigate whether task-vector arithmetic, successful for cross-speaker emotional intensity control in modular text-to-speech (TTS), transfers to large-scale TTS systems built on language-model backbones with in-context learning (LM-TTS). Through a systematic elimination study over four progressively narrower operands on Qwen3-TTS-12Hz-1.7B - model weights via LoRA fine-tuning, continuous codec embeddings, discrete codec tokens, and the speaker embedding (x-vector) produced by an ECAPA-TDNN encoder jointly trained with the synthesis backbone - we localize the dominant carrier of emotional "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05367","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/2606.05367/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":"2606.05367","created_at":"2026-06-05T00:13:55.510649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05367v1","created_at":"2026-06-05T00:13:55.510649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05367","created_at":"2026-06-05T00:13:55.510649+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTQBDUY2GIF4","created_at":"2026-06-05T00:13:55.510649+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTQBDUY2GIF4FM7P","created_at":"2026-06-05T00:13:55.510649+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTQBDUY2","created_at":"2026-06-05T00:13:55.510649+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/XTQBDUY2GIF4FM7PVQEOPQIIJY","json":"https://pith.science/pith/XTQBDUY2GIF4FM7PVQEOPQIIJY.json","graph_json":"https://pith.science/api/pith-number/XTQBDUY2GIF4FM7PVQEOPQIIJY/graph.json","events_json":"https://pith.science/api/pith-number/XTQBDUY2GIF4FM7PVQEOPQIIJY/events.json","paper":"https://pith.science/paper/XTQBDUY2"},"agent_actions":{"view_html":"https://pith.science/pith/XTQBDUY2GIF4FM7PVQEOPQIIJY","download_json":"https://pith.science/pith/XTQBDUY2GIF4FM7PVQEOPQIIJY.json","view_paper":"https://pith.science/paper/XTQBDUY2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05367&json=true","fetch_graph":"https://pith.science/api/pith-number/XTQBDUY2GIF4FM7PVQEOPQIIJY/graph.json","fetch_events":"https://pith.science/api/pith-number/XTQBDUY2GIF4FM7PVQEOPQIIJY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTQBDUY2GIF4FM7PVQEOPQIIJY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTQBDUY2GIF4FM7PVQEOPQIIJY/action/storage_attestation","attest_author":"https://pith.science/pith/XTQBDUY2GIF4FM7PVQEOPQIIJY/action/author_attestation","sign_citation":"https://pith.science/pith/XTQBDUY2GIF4FM7PVQEOPQIIJY/action/citation_signature","submit_replication":"https://pith.science/pith/XTQBDUY2GIF4FM7PVQEOPQIIJY/action/replication_record"}},"created_at":"2026-06-05T00:13:55.510649+00:00","updated_at":"2026-06-05T00:13:55.510649+00:00"}