{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IVUYM7JYYCPSEM6627Z6BDJP45","short_pith_number":"pith:IVUYM7JY","schema_version":"1.0","canonical_sha256":"4569867d38c09f2233ded7f3e08d2fe76acfaf21749cd3605e9dac9fa3a1e306","source":{"kind":"arxiv","id":"2308.05725","version":1},"attestation_state":"computed","paper":{"title":"EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Antony D'Avirro, Bowen Shi, Emmanuel Dupoux, Felix Kreuk, Gabriel Synnaeve, Itai Gat, Jade Copet, Maryam Fazel-Zarani, Michael Hassid, Tal Remez, Tu Anh Nguyen, Wei-Ning Hsu, Yossi Adi","submitted_at":"2023-08-10T17:41:19Z","abstract_excerpt":"Recent work has shown that it is possible to resynthesize high-quality speech based, not on text, but on low bitrate discrete units that have been learned in a self-supervised fashion and can therefore capture expressive aspects of speech that are hard to transcribe (prosody, voice styles, non-verbal vocalization). The adoption of these methods is still limited by the fact that most speech synthesis datasets are read, severely limiting spontaneity and expressivity. Here, we introduce Expresso, a high-quality expressive speech dataset for textless speech synthesis that includes both read speech"},"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":"2308.05725","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-10T17:41:19Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"3fd9692c4ae48bb079eaa0b335d33623a74267d10d799c85482c6087280fcdda","abstract_canon_sha256":"b10881e74834f623dfba853348e00d4003d034252237e9d235c0573dd1e86153"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:04.295041Z","signature_b64":"lvxYrwu/lyq+DhD15p5Iy/vdNkZwFfrhhNJnlCFmMCL4PUnlBc8F3xh6USNVbfk7bD1zf5LkWh8+rx5Yf0KECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4569867d38c09f2233ded7f3e08d2fe76acfaf21749cd3605e9dac9fa3a1e306","last_reissued_at":"2026-07-05T06:40:04.294640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:04.294640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Antony D'Avirro, Bowen Shi, Emmanuel Dupoux, Felix Kreuk, Gabriel Synnaeve, Itai Gat, Jade Copet, Maryam Fazel-Zarani, Michael Hassid, Tal Remez, Tu Anh Nguyen, Wei-Ning Hsu, Yossi Adi","submitted_at":"2023-08-10T17:41:19Z","abstract_excerpt":"Recent work has shown that it is possible to resynthesize high-quality speech based, not on text, but on low bitrate discrete units that have been learned in a self-supervised fashion and can therefore capture expressive aspects of speech that are hard to transcribe (prosody, voice styles, non-verbal vocalization). The adoption of these methods is still limited by the fact that most speech synthesis datasets are read, severely limiting spontaneity and expressivity. Here, we introduce Expresso, a high-quality expressive speech dataset for textless speech synthesis that includes both read speech"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.05725","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/2308.05725/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":"2308.05725","created_at":"2026-07-05T06:40:04.294705+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.05725v1","created_at":"2026-07-05T06:40:04.294705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.05725","created_at":"2026-07-05T06:40:04.294705+00:00"},{"alias_kind":"pith_short_12","alias_value":"IVUYM7JYYCPS","created_at":"2026-07-05T06:40:04.294705+00:00"},{"alias_kind":"pith_short_16","alias_value":"IVUYM7JYYCPSEM66","created_at":"2026-07-05T06:40:04.294705+00:00"},{"alias_kind":"pith_short_8","alias_value":"IVUYM7JY","created_at":"2026-07-05T06:40:04.294705+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02214","citing_title":"Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01677","citing_title":"UniVocal: Unified Speech-Singing Code-Switching Synthesis","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30748","citing_title":"Chatterbox-Flash: Prior-Calibrated Block Diffusion for Streaming Zero-Shot TTS","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25504","citing_title":"Toward Natural Emotional Text-To-Speech System with Fine-Grained Non-Verbal Expression Control","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20830","citing_title":"Raon-OpenTTS: Open Models and Data for Robust Text-to-Speech","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2505.22765","citing_title":"StressTest: Can YOUR Speech LM Handle the Stress?","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2509.04072","citing_title":"Computational Narrative Understanding for Expressive Text-to-Speech","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22220","citing_title":"StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17589","citing_title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2603.25551","citing_title":"Voxtral TTS","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04505","citing_title":"JASTIN: Aligning LLMs for Zero-Shot Audio and Speech Evaluation via Natural Language Instructions","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IVUYM7JYYCPSEM6627Z6BDJP45","json":"https://pith.science/pith/IVUYM7JYYCPSEM6627Z6BDJP45.json","graph_json":"https://pith.science/api/pith-number/IVUYM7JYYCPSEM6627Z6BDJP45/graph.json","events_json":"https://pith.science/api/pith-number/IVUYM7JYYCPSEM6627Z6BDJP45/events.json","paper":"https://pith.science/paper/IVUYM7JY"},"agent_actions":{"view_html":"https://pith.science/pith/IVUYM7JYYCPSEM6627Z6BDJP45","download_json":"https://pith.science/pith/IVUYM7JYYCPSEM6627Z6BDJP45.json","view_paper":"https://pith.science/paper/IVUYM7JY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.05725&json=true","fetch_graph":"https://pith.science/api/pith-number/IVUYM7JYYCPSEM6627Z6BDJP45/graph.json","fetch_events":"https://pith.science/api/pith-number/IVUYM7JYYCPSEM6627Z6BDJP45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IVUYM7JYYCPSEM6627Z6BDJP45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IVUYM7JYYCPSEM6627Z6BDJP45/action/storage_attestation","attest_author":"https://pith.science/pith/IVUYM7JYYCPSEM6627Z6BDJP45/action/author_attestation","sign_citation":"https://pith.science/pith/IVUYM7JYYCPSEM6627Z6BDJP45/action/citation_signature","submit_replication":"https://pith.science/pith/IVUYM7JYYCPSEM6627Z6BDJP45/action/replication_record"}},"created_at":"2026-07-05T06:40:04.294705+00:00","updated_at":"2026-07-05T06:40:04.294705+00:00"}