{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:U6YXZE7SSR4ZBN5TCUOYU3KP2K","short_pith_number":"pith:U6YXZE7S","canonical_record":{"source":{"id":"2008.04549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-11T06:48:36Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"8eb49e7ecf807ef6a76e4c2ddad6d2c9578393355a3a57a929fa58c46a64d0a6","abstract_canon_sha256":"ce4a475a4502417d96fa84227fab64ed9c1af366b5346382b49e451cf28863f2"},"schema_version":"1.0"},"canonical_sha256":"a7b17c93f2947990b7b3151d8a6d4fd2b44c581ef85c9cba087d799d25b115e5","source":{"kind":"arxiv","id":"2008.04549","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.04549","created_at":"2026-07-05T01:26:26Z"},{"alias_kind":"arxiv_version","alias_value":"2008.04549v1","created_at":"2026-07-05T01:26:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.04549","created_at":"2026-07-05T01:26:26Z"},{"alias_kind":"pith_short_12","alias_value":"U6YXZE7SSR4Z","created_at":"2026-07-05T01:26:26Z"},{"alias_kind":"pith_short_16","alias_value":"U6YXZE7SSR4ZBN5T","created_at":"2026-07-05T01:26:26Z"},{"alias_kind":"pith_short_8","alias_value":"U6YXZE7S","created_at":"2026-07-05T01:26:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:U6YXZE7SSR4ZBN5TCUOYU3KP2K","target":"record","payload":{"canonical_record":{"source":{"id":"2008.04549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-11T06:48:36Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"8eb49e7ecf807ef6a76e4c2ddad6d2c9578393355a3a57a929fa58c46a64d0a6","abstract_canon_sha256":"ce4a475a4502417d96fa84227fab64ed9c1af366b5346382b49e451cf28863f2"},"schema_version":"1.0"},"canonical_sha256":"a7b17c93f2947990b7b3151d8a6d4fd2b44c581ef85c9cba087d799d25b115e5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:26.312377Z","signature_b64":"z3+0JWhjEVv7KbNSHpuxBwDtAqF1lBd0mb1Iv2U4NhKaMZZQoHXIMIlW97NjKE58vGtxTQ1qJ+IrxCYRRYxFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7b17c93f2947990b7b3151d8a6d4fd2b44c581ef85c9cba087d799d25b115e5","last_reissued_at":"2026-07-05T01:26:26.311935Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:26.311935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.04549","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":"2026-07-05T01:26:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TlXVejciqSvTz3IlVGiPoa9fHon4gy8WVNrG2GeWWaW/XICbE434KzsqWeQ/plp+ASm5bo3S+3m9p0nfqSUsAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:58:34.170293Z"},"content_sha256":"3d9ad054496a47c1f2b9ea9b82196c8e9baab48a7e113867d8a704fd6c5f821d","schema_version":"1.0","event_id":"sha256:3d9ad054496a47c1f2b9ea9b82196c8e9baab48a7e113867d8a704fd6c5f821d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:U6YXZE7SSR4ZBN5TCUOYU3KP2K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Learning For Sequence-to-sequence Text-to-speech For Low-resource Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Haitong Zhang, Yue Lin","submitted_at":"2020-08-11T06:48:36Z","abstract_excerpt":"Recently, sequence-to-sequence models with attention have been successfully applied in Text-to-speech (TTS). These models can generate near-human speech with a large accurately-transcribed speech corpus. However, preparing such a large data-set is both expensive and laborious. To alleviate the problem of heavy data demand, we propose a novel unsupervised pre-training mechanism in this paper. Specifically, we first use Vector-quantization Variational-Autoencoder (VQ-VAE) to ex-tract the unsupervised linguistic units from large-scale, publicly found, and untranscribed speech. We then pre-train t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.04549","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/2008.04549/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":"2026-07-05T01:26:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZrW677UnuaJmxxXzxqz6e64qJDAzyI/R7xqsgqHHNU1WJ4bnaWbJhUZdGl+5QJWB5IC5K+cQ2Wolfe5gYSwnBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:58:34.170811Z"},"content_sha256":"88a7a38b786cbe1890cccfde0f7116805eb759dcaacc7d46bb4c7d7e5f77145f","schema_version":"1.0","event_id":"sha256:88a7a38b786cbe1890cccfde0f7116805eb759dcaacc7d46bb4c7d7e5f77145f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U6YXZE7SSR4ZBN5TCUOYU3KP2K/bundle.json","state_url":"https://pith.science/pith/U6YXZE7SSR4ZBN5TCUOYU3KP2K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U6YXZE7SSR4ZBN5TCUOYU3KP2K/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":"2026-08-05T22:58:34Z","links":{"resolver":"https://pith.science/pith/U6YXZE7SSR4ZBN5TCUOYU3KP2K","bundle":"https://pith.science/pith/U6YXZE7SSR4ZBN5TCUOYU3KP2K/bundle.json","state":"https://pith.science/pith/U6YXZE7SSR4ZBN5TCUOYU3KP2K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U6YXZE7SSR4ZBN5TCUOYU3KP2K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:U6YXZE7SSR4ZBN5TCUOYU3KP2K","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":"ce4a475a4502417d96fa84227fab64ed9c1af366b5346382b49e451cf28863f2","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-11T06:48:36Z","title_canon_sha256":"8eb49e7ecf807ef6a76e4c2ddad6d2c9578393355a3a57a929fa58c46a64d0a6"},"schema_version":"1.0","source":{"id":"2008.04549","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.04549","created_at":"2026-07-05T01:26:26Z"},{"alias_kind":"arxiv_version","alias_value":"2008.04549v1","created_at":"2026-07-05T01:26:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.04549","created_at":"2026-07-05T01:26:26Z"},{"alias_kind":"pith_short_12","alias_value":"U6YXZE7SSR4Z","created_at":"2026-07-05T01:26:26Z"},{"alias_kind":"pith_short_16","alias_value":"U6YXZE7SSR4ZBN5T","created_at":"2026-07-05T01:26:26Z"},{"alias_kind":"pith_short_8","alias_value":"U6YXZE7S","created_at":"2026-07-05T01:26:26Z"}],"graph_snapshots":[{"event_id":"sha256:88a7a38b786cbe1890cccfde0f7116805eb759dcaacc7d46bb4c7d7e5f77145f","target":"graph","created_at":"2026-07-05T01:26:26Z","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/2008.04549/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, sequence-to-sequence models with attention have been successfully applied in Text-to-speech (TTS). These models can generate near-human speech with a large accurately-transcribed speech corpus. However, preparing such a large data-set is both expensive and laborious. To alleviate the problem of heavy data demand, we propose a novel unsupervised pre-training mechanism in this paper. Specifically, we first use Vector-quantization Variational-Autoencoder (VQ-VAE) to ex-tract the unsupervised linguistic units from large-scale, publicly found, and untranscribed speech. We then pre-train t","authors_text":"Haitong Zhang, Yue Lin","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-11T06:48:36Z","title":"Unsupervised Learning For Sequence-to-sequence Text-to-speech For Low-resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.04549","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":"sha256:3d9ad054496a47c1f2b9ea9b82196c8e9baab48a7e113867d8a704fd6c5f821d","target":"record","created_at":"2026-07-05T01:26:26Z","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":"ce4a475a4502417d96fa84227fab64ed9c1af366b5346382b49e451cf28863f2","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-11T06:48:36Z","title_canon_sha256":"8eb49e7ecf807ef6a76e4c2ddad6d2c9578393355a3a57a929fa58c46a64d0a6"},"schema_version":"1.0","source":{"id":"2008.04549","kind":"arxiv","version":1}},"canonical_sha256":"a7b17c93f2947990b7b3151d8a6d4fd2b44c581ef85c9cba087d799d25b115e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7b17c93f2947990b7b3151d8a6d4fd2b44c581ef85c9cba087d799d25b115e5","first_computed_at":"2026-07-05T01:26:26.311935Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:26:26.311935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z3+0JWhjEVv7KbNSHpuxBwDtAqF1lBd0mb1Iv2U4NhKaMZZQoHXIMIlW97NjKE58vGtxTQ1qJ+IrxCYRRYxFAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:26:26.312377Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.04549","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d9ad054496a47c1f2b9ea9b82196c8e9baab48a7e113867d8a704fd6c5f821d","sha256:88a7a38b786cbe1890cccfde0f7116805eb759dcaacc7d46bb4c7d7e5f77145f"],"state_sha256":"1717b7b5995631d1726908085b551e1db28f061791b2de31aaef078bfc860161"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a+GuDcalmjMuzP6Rmc1nTBvn1O6LndhnfNNSpIGFad1/g1v0rWs2627nYs2LUXEr8PTJ/YB74ntlq1LYK6M1Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:58:34.175654Z","bundle_sha256":"be2f5d35d6c1f2ebcc63098efecc858bbe497222e2f7297bf4a3ce1540498e3c"}}