{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JX4FXY5DCBTRLEN4EZJBMH3SJI","short_pith_number":"pith:JX4FXY5D","schema_version":"1.0","canonical_sha256":"4df85be3a310671591bc2652161f724a20d4705a28d7f546fd77ba040fb18c2d","source":{"kind":"arxiv","id":"2606.20650","version":1},"attestation_state":"computed","paper":{"title":"EmoInstruct-TTS: Dual-Path Instruction-Guided Emotional Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bingao Xu, Ganjun Liu, Hongchuan Wu, Jiasheng Chen, Jun Du, Minghui Wu, Ting Meng, Yonglong Cai, Zikun Fang","submitted_at":"2026-06-08T06:54:55Z","abstract_excerpt":"Instruction-based controllable speech synthesis enables users to specify emotions through natural language. However, existing approaches often rely on coarse emotion labels and lack explicit modeling of fine-grained intensity. We propose EmoInstruct-TTS, a dual-path instruction-guided framework for emotional speech synthesis. We introduce Emotion2embed, a supervised semantic-acoustic emotion embedding covering 48 emotional states, including fine-grained categories and intensity levels. To infer embeddings from free-form instructions, we design an Instruction-Conditioned Emotion Flow Model (ICE"},"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":"2606.20650","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T06:54:55Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"3d0918d3431ed95fe31d5005a6703ebc6edf4e281d88f43ce6b672c5eab19908","abstract_canon_sha256":"fc5f8481c1e9265738f8f69c58cca9c1ddbef8916ffcee6e48c691fe801c06cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T00:11:52.579369Z","signature_b64":"uXvOp5NISiQKOFsepPZFT3X981lIz4GqXf50kJV/XISIKEsicc3Gi+4GPX9O6TLq0+Ss8XFtkC2mxdrHSrC3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4df85be3a310671591bc2652161f724a20d4705a28d7f546fd77ba040fb18c2d","last_reissued_at":"2026-06-23T00:11:52.578987Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T00:11:52.578987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EmoInstruct-TTS: Dual-Path Instruction-Guided Emotional Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bingao Xu, Ganjun Liu, Hongchuan Wu, Jiasheng Chen, Jun Du, Minghui Wu, Ting Meng, Yonglong Cai, Zikun Fang","submitted_at":"2026-06-08T06:54:55Z","abstract_excerpt":"Instruction-based controllable speech synthesis enables users to specify emotions through natural language. However, existing approaches often rely on coarse emotion labels and lack explicit modeling of fine-grained intensity. We propose EmoInstruct-TTS, a dual-path instruction-guided framework for emotional speech synthesis. We introduce Emotion2embed, a supervised semantic-acoustic emotion embedding covering 48 emotional states, including fine-grained categories and intensity levels. To infer embeddings from free-form instructions, we design an Instruction-Conditioned Emotion Flow Model (ICE"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20650","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/2606.20650/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":"2606.20650","created_at":"2026-06-23T00:11:52.579053+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20650v1","created_at":"2026-06-23T00:11:52.579053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20650","created_at":"2026-06-23T00:11:52.579053+00:00"},{"alias_kind":"pith_short_12","alias_value":"JX4FXY5DCBTR","created_at":"2026-06-23T00:11:52.579053+00:00"},{"alias_kind":"pith_short_16","alias_value":"JX4FXY5DCBTRLEN4","created_at":"2026-06-23T00:11:52.579053+00:00"},{"alias_kind":"pith_short_8","alias_value":"JX4FXY5D","created_at":"2026-06-23T00:11:52.579053+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/JX4FXY5DCBTRLEN4EZJBMH3SJI","json":"https://pith.science/pith/JX4FXY5DCBTRLEN4EZJBMH3SJI.json","graph_json":"https://pith.science/api/pith-number/JX4FXY5DCBTRLEN4EZJBMH3SJI/graph.json","events_json":"https://pith.science/api/pith-number/JX4FXY5DCBTRLEN4EZJBMH3SJI/events.json","paper":"https://pith.science/paper/JX4FXY5D"},"agent_actions":{"view_html":"https://pith.science/pith/JX4FXY5DCBTRLEN4EZJBMH3SJI","download_json":"https://pith.science/pith/JX4FXY5DCBTRLEN4EZJBMH3SJI.json","view_paper":"https://pith.science/paper/JX4FXY5D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20650&json=true","fetch_graph":"https://pith.science/api/pith-number/JX4FXY5DCBTRLEN4EZJBMH3SJI/graph.json","fetch_events":"https://pith.science/api/pith-number/JX4FXY5DCBTRLEN4EZJBMH3SJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JX4FXY5DCBTRLEN4EZJBMH3SJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JX4FXY5DCBTRLEN4EZJBMH3SJI/action/storage_attestation","attest_author":"https://pith.science/pith/JX4FXY5DCBTRLEN4EZJBMH3SJI/action/author_attestation","sign_citation":"https://pith.science/pith/JX4FXY5DCBTRLEN4EZJBMH3SJI/action/citation_signature","submit_replication":"https://pith.science/pith/JX4FXY5DCBTRLEN4EZJBMH3SJI/action/replication_record"}},"created_at":"2026-06-23T00:11:52.579053+00:00","updated_at":"2026-06-23T00:11:52.579053+00:00"}