{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:G2EA2AMJKSQSRZC7LXCY7KRF6E","short_pith_number":"pith:G2EA2AMJ","schema_version":"1.0","canonical_sha256":"36880d018954a128e45f5dc58faa25f10fca9d91dcdb37f90e6575afdfedde09","source":{"kind":"arxiv","id":"2308.08577","version":1},"attestation_state":"computed","paper":{"title":"AffectEcho: Speaker Independent and Language-Agnostic Emotion and Affect Transfer for Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.HC","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aneesh Bhattacharya, Aniket Bera, Hrishikesh Viswanath, Mridu Prashanth, Pascal Jutras-Dub\\'e, Prerit Gupta, Yashvardhan Khaitan","submitted_at":"2023-08-16T06:28:29Z","abstract_excerpt":"Affect is an emotional characteristic encompassing valence, arousal, and intensity, and is a crucial attribute for enabling authentic conversations. While existing text-to-speech (TTS) and speech-to-speech systems rely on strength embedding vectors and global style tokens to capture emotions, these models represent emotions as a component of style or represent them in discrete categories. We propose AffectEcho, an emotion translation model, that uses a Vector Quantized codebook to model emotions within a quantized space featuring five levels of affect intensity to capture complex nuances and s"},"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":"2308.08577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-08-16T06:28:29Z","cross_cats_sorted":["cs.CL","cs.HC","eess.AS"],"title_canon_sha256":"ab800e617e962175fca8b257e8bd48814f5c617527263cca6428ca3b735a1510","abstract_canon_sha256":"09560f2a357fd2dc248c11d2f8e4f3108052faf173361e9d9e6280c1a057ea72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:08.405215Z","signature_b64":"OCT5CxXe99oTvrWTBAMNkCCAs1Zo/ihOhrkckD65EZ+5fV75Xkepia6w3zPL//T/jXCq9bZ8WwLtATWvOR5sBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36880d018954a128e45f5dc58faa25f10fca9d91dcdb37f90e6575afdfedde09","last_reissued_at":"2026-07-05T06:42:08.404749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:08.404749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AffectEcho: Speaker Independent and Language-Agnostic Emotion and Affect Transfer for Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.HC","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aneesh Bhattacharya, Aniket Bera, Hrishikesh Viswanath, Mridu Prashanth, Pascal Jutras-Dub\\'e, Prerit Gupta, Yashvardhan Khaitan","submitted_at":"2023-08-16T06:28:29Z","abstract_excerpt":"Affect is an emotional characteristic encompassing valence, arousal, and intensity, and is a crucial attribute for enabling authentic conversations. While existing text-to-speech (TTS) and speech-to-speech systems rely on strength embedding vectors and global style tokens to capture emotions, these models represent emotions as a component of style or represent them in discrete categories. We propose AffectEcho, an emotion translation model, that uses a Vector Quantized codebook to model emotions within a quantized space featuring five levels of affect intensity to capture complex nuances and s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.08577","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/2308.08577/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":"2308.08577","created_at":"2026-07-05T06:42:08.404812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.08577v1","created_at":"2026-07-05T06:42:08.404812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.08577","created_at":"2026-07-05T06:42:08.404812+00:00"},{"alias_kind":"pith_short_12","alias_value":"G2EA2AMJKSQS","created_at":"2026-07-05T06:42:08.404812+00:00"},{"alias_kind":"pith_short_16","alias_value":"G2EA2AMJKSQSRZC7","created_at":"2026-07-05T06:42:08.404812+00:00"},{"alias_kind":"pith_short_8","alias_value":"G2EA2AMJ","created_at":"2026-07-05T06:42:08.404812+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/G2EA2AMJKSQSRZC7LXCY7KRF6E","json":"https://pith.science/pith/G2EA2AMJKSQSRZC7LXCY7KRF6E.json","graph_json":"https://pith.science/api/pith-number/G2EA2AMJKSQSRZC7LXCY7KRF6E/graph.json","events_json":"https://pith.science/api/pith-number/G2EA2AMJKSQSRZC7LXCY7KRF6E/events.json","paper":"https://pith.science/paper/G2EA2AMJ"},"agent_actions":{"view_html":"https://pith.science/pith/G2EA2AMJKSQSRZC7LXCY7KRF6E","download_json":"https://pith.science/pith/G2EA2AMJKSQSRZC7LXCY7KRF6E.json","view_paper":"https://pith.science/paper/G2EA2AMJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.08577&json=true","fetch_graph":"https://pith.science/api/pith-number/G2EA2AMJKSQSRZC7LXCY7KRF6E/graph.json","fetch_events":"https://pith.science/api/pith-number/G2EA2AMJKSQSRZC7LXCY7KRF6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G2EA2AMJKSQSRZC7LXCY7KRF6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G2EA2AMJKSQSRZC7LXCY7KRF6E/action/storage_attestation","attest_author":"https://pith.science/pith/G2EA2AMJKSQSRZC7LXCY7KRF6E/action/author_attestation","sign_citation":"https://pith.science/pith/G2EA2AMJKSQSRZC7LXCY7KRF6E/action/citation_signature","submit_replication":"https://pith.science/pith/G2EA2AMJKSQSRZC7LXCY7KRF6E/action/replication_record"}},"created_at":"2026-07-05T06:42:08.404812+00:00","updated_at":"2026-07-05T06:42:08.404812+00:00"}