{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UPIIFSMZPTFCYMUM4W7CYMG32L","short_pith_number":"pith:UPIIFSMZ","schema_version":"1.0","canonical_sha256":"a3d082c9997cca2c328ce5be2c30dbd2dee932fec481c6904e8730329c2434db","source":{"kind":"arxiv","id":"2308.01831","version":2},"attestation_state":"computed","paper":{"title":"Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS","eess.SP"],"primary_cat":"cs.CL","authors_text":"Dahun Kim, Jeongsoo Choi, Minsu Kim, Yong Man Ro","submitted_at":"2023-08-03T15:47:04Z","abstract_excerpt":"This paper proposes a textless training method for many-to-many multilingual speech-to-speech translation that can also benefit the transfer of pre-trained knowledge to text-based systems, text-to-speech synthesis and text-to-speech translation. To this end, we represent multilingual speech with speech units that are the discretized representations of speech features derived from a self-supervised speech model. By treating the speech units as pseudo-text, we can focus on the linguistic content of the speech, which can be easily associated with both speech and text modalities at the phonetic le"},"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":"2308.01831","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-03T15:47:04Z","cross_cats_sorted":["eess.AS","eess.SP"],"title_canon_sha256":"43d8d2417ab92e972e7b6e10d868a4c0059dc7af716d423d4f2146afb63ccead","abstract_canon_sha256":"27504bc097813408b90ad3fcecde796921cc346751bfcc23751454eaad18ae1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:13.485995Z","signature_b64":"FhCzQhd/6y95WwwJ3C2InIXigbqjPlMd0ovpY/YPX1JGN0Qw/VO9qHX9cKpEq4mFzzMbDdmGzDwyWuqHc/xzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3d082c9997cca2c328ce5be2c30dbd2dee932fec481c6904e8730329c2434db","last_reissued_at":"2026-07-05T08:56:13.485598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:13.485598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS","eess.SP"],"primary_cat":"cs.CL","authors_text":"Dahun Kim, Jeongsoo Choi, Minsu Kim, Yong Man Ro","submitted_at":"2023-08-03T15:47:04Z","abstract_excerpt":"This paper proposes a textless training method for many-to-many multilingual speech-to-speech translation that can also benefit the transfer of pre-trained knowledge to text-based systems, text-to-speech synthesis and text-to-speech translation. To this end, we represent multilingual speech with speech units that are the discretized representations of speech features derived from a self-supervised speech model. By treating the speech units as pseudo-text, we can focus on the linguistic content of the speech, which can be easily associated with both speech and text modalities at the phonetic le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01831","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/2308.01831/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":"2308.01831","created_at":"2026-07-05T08:56:13.485653+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.01831v2","created_at":"2026-07-05T08:56:13.485653+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01831","created_at":"2026-07-05T08:56:13.485653+00:00"},{"alias_kind":"pith_short_12","alias_value":"UPIIFSMZPTFC","created_at":"2026-07-05T08:56:13.485653+00:00"},{"alias_kind":"pith_short_16","alias_value":"UPIIFSMZPTFCYMUM","created_at":"2026-07-05T08:56:13.485653+00:00"},{"alias_kind":"pith_short_8","alias_value":"UPIIFSMZ","created_at":"2026-07-05T08:56:13.485653+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.05835","citing_title":"NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UPIIFSMZPTFCYMUM4W7CYMG32L","json":"https://pith.science/pith/UPIIFSMZPTFCYMUM4W7CYMG32L.json","graph_json":"https://pith.science/api/pith-number/UPIIFSMZPTFCYMUM4W7CYMG32L/graph.json","events_json":"https://pith.science/api/pith-number/UPIIFSMZPTFCYMUM4W7CYMG32L/events.json","paper":"https://pith.science/paper/UPIIFSMZ"},"agent_actions":{"view_html":"https://pith.science/pith/UPIIFSMZPTFCYMUM4W7CYMG32L","download_json":"https://pith.science/pith/UPIIFSMZPTFCYMUM4W7CYMG32L.json","view_paper":"https://pith.science/paper/UPIIFSMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.01831&json=true","fetch_graph":"https://pith.science/api/pith-number/UPIIFSMZPTFCYMUM4W7CYMG32L/graph.json","fetch_events":"https://pith.science/api/pith-number/UPIIFSMZPTFCYMUM4W7CYMG32L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UPIIFSMZPTFCYMUM4W7CYMG32L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UPIIFSMZPTFCYMUM4W7CYMG32L/action/storage_attestation","attest_author":"https://pith.science/pith/UPIIFSMZPTFCYMUM4W7CYMG32L/action/author_attestation","sign_citation":"https://pith.science/pith/UPIIFSMZPTFCYMUM4W7CYMG32L/action/citation_signature","submit_replication":"https://pith.science/pith/UPIIFSMZPTFCYMUM4W7CYMG32L/action/replication_record"}},"created_at":"2026-07-05T08:56:13.485653+00:00","updated_at":"2026-07-05T08:56:13.485653+00:00"}