{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PPZXHT6L5VW7ILG7U6NTOC35KJ","short_pith_number":"pith:PPZXHT6L","canonical_record":{"source":{"id":"2401.05111","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-10T12:21:21Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"15632cb81bea61f81f68390a27496eecbc79069d7c704249c0c3fb5485127a74","abstract_canon_sha256":"3a6db78db6c6e89715600285405c085a6e9d436568a26060be0822bd2ead6914"},"schema_version":"1.0"},"canonical_sha256":"7bf373cfcbed6df42cdfa79b370b7d52411c6e084b9129997d2484d8d64b0847","source":{"kind":"arxiv","id":"2401.05111","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.05111","created_at":"2026-07-05T07:32:03Z"},{"alias_kind":"arxiv_version","alias_value":"2401.05111v1","created_at":"2026-07-05T07:32:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05111","created_at":"2026-07-05T07:32:03Z"},{"alias_kind":"pith_short_12","alias_value":"PPZXHT6L5VW7","created_at":"2026-07-05T07:32:03Z"},{"alias_kind":"pith_short_16","alias_value":"PPZXHT6L5VW7ILG7","created_at":"2026-07-05T07:32:03Z"},{"alias_kind":"pith_short_8","alias_value":"PPZXHT6L","created_at":"2026-07-05T07:32:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PPZXHT6L5VW7ILG7U6NTOC35KJ","target":"record","payload":{"canonical_record":{"source":{"id":"2401.05111","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-10T12:21:21Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"15632cb81bea61f81f68390a27496eecbc79069d7c704249c0c3fb5485127a74","abstract_canon_sha256":"3a6db78db6c6e89715600285405c085a6e9d436568a26060be0822bd2ead6914"},"schema_version":"1.0"},"canonical_sha256":"7bf373cfcbed6df42cdfa79b370b7d52411c6e084b9129997d2484d8d64b0847","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:03.220383Z","signature_b64":"PAtCQ2BQ4Vyu7dX/FsCugB+zwo5deObWA4Zef6z3x2awSHcPPpZ9u6uIABcxaDD/aJsdJ/igukVgql4s50ZrAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bf373cfcbed6df42cdfa79b370b7d52411c6e084b9129997d2484d8d64b0847","last_reissued_at":"2026-07-05T07:32:03.219983Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:03.219983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.05111","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:32:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s9O4e/jtAA5xKBUZCqu4VWEmsKlaYRVGm2s7LB6R+JgGuIbtiGyrc2QhytdzGsEsKtVysTEzfnJzS3JVFL0zDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T21:03:27.264533Z"},"content_sha256":"7502760b720bf88f6d92501e2d9fb358d6e7f4a4ecdfab9b2ddc48b499e1f790","schema_version":"1.0","event_id":"sha256:7502760b720bf88f6d92501e2d9fb358d6e7f4a4ecdfab9b2ddc48b499e1f790"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PPZXHT6L5VW7ILG7U6NTOC35KJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hiroki Kanagawa, Hiroshi Sato, Kenichi Fujita, Marc Delcroix, Takafumi Moriya, Takanori Ashihara, Yusuke Ijima","submitted_at":"2024-01-10T12:21:21Z","abstract_excerpt":"The zero-shot text-to-speech (TTS) method, based on speaker embeddings extracted from reference speech using self-supervised learning (SSL) speech representations, can reproduce speaker characteristics very accurately. However, this approach suffers from degradation in speech synthesis quality when the reference speech contains noise. In this paper, we propose a noise-robust zero-shot TTS method. We incorporated adapters into the SSL model, which we fine-tuned with the TTS model using noisy reference speech. In addition, to further improve performance, we adopted a speech enhancement (SE) fron"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05111","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/2401.05111/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:32:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Qv7eq/VbrFcPoHm5jZf+87wNcfD4XUSlZvNN9GG41g7I4sTz3V5MMV3gX+WZiJ0Hwh6FFvGMcrdWpeaApRfBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T21:03:27.265169Z"},"content_sha256":"7c066893108bc1e5b9b54777aa4de26eb288dd8086d2b6672aa6cc28aedb25a9","schema_version":"1.0","event_id":"sha256:7c066893108bc1e5b9b54777aa4de26eb288dd8086d2b6672aa6cc28aedb25a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PPZXHT6L5VW7ILG7U6NTOC35KJ/bundle.json","state_url":"https://pith.science/pith/PPZXHT6L5VW7ILG7U6NTOC35KJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PPZXHT6L5VW7ILG7U6NTOC35KJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-11T21:03:27Z","links":{"resolver":"https://pith.science/pith/PPZXHT6L5VW7ILG7U6NTOC35KJ","bundle":"https://pith.science/pith/PPZXHT6L5VW7ILG7U6NTOC35KJ/bundle.json","state":"https://pith.science/pith/PPZXHT6L5VW7ILG7U6NTOC35KJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PPZXHT6L5VW7ILG7U6NTOC35KJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PPZXHT6L5VW7ILG7U6NTOC35KJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3a6db78db6c6e89715600285405c085a6e9d436568a26060be0822bd2ead6914","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-10T12:21:21Z","title_canon_sha256":"15632cb81bea61f81f68390a27496eecbc79069d7c704249c0c3fb5485127a74"},"schema_version":"1.0","source":{"id":"2401.05111","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.05111","created_at":"2026-07-05T07:32:03Z"},{"alias_kind":"arxiv_version","alias_value":"2401.05111v1","created_at":"2026-07-05T07:32:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05111","created_at":"2026-07-05T07:32:03Z"},{"alias_kind":"pith_short_12","alias_value":"PPZXHT6L5VW7","created_at":"2026-07-05T07:32:03Z"},{"alias_kind":"pith_short_16","alias_value":"PPZXHT6L5VW7ILG7","created_at":"2026-07-05T07:32:03Z"},{"alias_kind":"pith_short_8","alias_value":"PPZXHT6L","created_at":"2026-07-05T07:32:03Z"}],"graph_snapshots":[{"event_id":"sha256:7c066893108bc1e5b9b54777aa4de26eb288dd8086d2b6672aa6cc28aedb25a9","target":"graph","created_at":"2026-07-05T07:32:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.05111/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The zero-shot text-to-speech (TTS) method, based on speaker embeddings extracted from reference speech using self-supervised learning (SSL) speech representations, can reproduce speaker characteristics very accurately. However, this approach suffers from degradation in speech synthesis quality when the reference speech contains noise. In this paper, we propose a noise-robust zero-shot TTS method. We incorporated adapters into the SSL model, which we fine-tuned with the TTS model using noisy reference speech. In addition, to further improve performance, we adopted a speech enhancement (SE) fron","authors_text":"Hiroki Kanagawa, Hiroshi Sato, Kenichi Fujita, Marc Delcroix, Takafumi Moriya, Takanori Ashihara, Yusuke Ijima","cross_cats":["cs.CL","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-10T12:21:21Z","title":"Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05111","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7502760b720bf88f6d92501e2d9fb358d6e7f4a4ecdfab9b2ddc48b499e1f790","target":"record","created_at":"2026-07-05T07:32:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3a6db78db6c6e89715600285405c085a6e9d436568a26060be0822bd2ead6914","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-10T12:21:21Z","title_canon_sha256":"15632cb81bea61f81f68390a27496eecbc79069d7c704249c0c3fb5485127a74"},"schema_version":"1.0","source":{"id":"2401.05111","kind":"arxiv","version":1}},"canonical_sha256":"7bf373cfcbed6df42cdfa79b370b7d52411c6e084b9129997d2484d8d64b0847","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bf373cfcbed6df42cdfa79b370b7d52411c6e084b9129997d2484d8d64b0847","first_computed_at":"2026-07-05T07:32:03.219983Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:32:03.219983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PAtCQ2BQ4Vyu7dX/FsCugB+zwo5deObWA4Zef6z3x2awSHcPPpZ9u6uIABcxaDD/aJsdJ/igukVgql4s50ZrAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:32:03.220383Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.05111","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7502760b720bf88f6d92501e2d9fb358d6e7f4a4ecdfab9b2ddc48b499e1f790","sha256:7c066893108bc1e5b9b54777aa4de26eb288dd8086d2b6672aa6cc28aedb25a9"],"state_sha256":"9b438fda911467bcf46ed1cdf8a052ec4feba01348bf679786869e05752b5905"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LCzsoZN9xbE8ox1Y6R8l7FPBG6Mve6RZF52yKtFFWNKadJOqKY4X95WX7KjMB5JIsgOnh6pqmjuIpJwRufw1CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T21:03:27.267798Z","bundle_sha256":"99dab56a4bf5faaa2c3bc1537df1a68366ea3f6dbe465d3e9a6bd9b83fb22c6e"}}