{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:7VYCJFVZEDSMQP273MLQTDYYJ4","short_pith_number":"pith:7VYCJFVZ","canonical_record":{"source":{"id":"2103.03049","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-04T14:14:58Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"2cdd508d5324fb05fae212cc74b842c286aef949f11b4704998b72193332d309","abstract_canon_sha256":"52447bf1f9143b4a659b5961ff7e4a21af0ca81a4425dc78bddcaf38356d202f"},"schema_version":"1.0"},"canonical_sha256":"fd702496b920e4c83f5fdb17098f184f3b41bbb0848681036da1f0ee2261f1cd","source":{"kind":"arxiv","id":"2103.03049","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.03049","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"arxiv_version","alias_value":"2103.03049v1","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03049","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"pith_short_12","alias_value":"7VYCJFVZEDSM","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"pith_short_16","alias_value":"7VYCJFVZEDSMQP27","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"pith_short_8","alias_value":"7VYCJFVZ","created_at":"2026-07-05T02:20:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:7VYCJFVZEDSMQP273MLQTDYYJ4","target":"record","payload":{"canonical_record":{"source":{"id":"2103.03049","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-04T14:14:58Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"2cdd508d5324fb05fae212cc74b842c286aef949f11b4704998b72193332d309","abstract_canon_sha256":"52447bf1f9143b4a659b5961ff7e4a21af0ca81a4425dc78bddcaf38356d202f"},"schema_version":"1.0"},"canonical_sha256":"fd702496b920e4c83f5fdb17098f184f3b41bbb0848681036da1f0ee2261f1cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:20:23.869459Z","signature_b64":"egELQ+lma4cuGwROzU38MURdvq++L0t3ytIVIOz8W6ue/MknhPcY9BUqsivoD0qKshZosBTblYS5f+NLbG6uDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd702496b920e4c83f5fdb17098f184f3b41bbb0848681036da1f0ee2261f1cd","last_reissued_at":"2026-07-05T02:20:23.868927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:20:23.868927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.03049","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":"2026-07-05T02:20:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h2meMkDiJYHp3fJTPSROxWH8OPg78/wvP7YMpnEiHvt8xPM2ZejnnxGTaOLZUdXFynR5goAU1KzwhX94i3bdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:19:51.373663Z"},"content_sha256":"75828c8f5bca5aa92bae72e7c39abc21cdf64a3134cf1ffddb73e882c3a4f029","schema_version":"1.0","event_id":"sha256:75828c8f5bca5aa92bae72e7c39abc21cdf64a3134cf1ffddb73e882c3a4f029"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:7VYCJFVZEDSMQP273MLQTDYYJ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Neural Text-to-Speech Model Utilizing Broadcast Data Mixed with Background Music","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Hanbin Bae, Hoon-Young Cho, Jae-Sung Bae, Young-Ik Kim, Young-Sun Joo","submitted_at":"2021-03-04T14:14:58Z","abstract_excerpt":"Recently, it has become easier to obtain speech data from various media such as the internet or YouTube, but directly utilizing them to train a neural text-to-speech (TTS) model is difficult. The proportion of clean speech is insufficient and the remainder includes background music. Even with the global style token (GST). Therefore, we propose the following method to successfully train an end-to-end TTS model with limited broadcast data. First, the background music is removed from the speech by introducing a music filter. Second, the GST-TTS model with an auxiliary quality classifier is traine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.03049","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/2103.03049/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":"2026-07-05T02:20:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aoPRfugkPrwQAat4+n0EyuQ9e++MJ4N7H0ckBPMLhQn1VWphWC4abMLAD9Vjeg5fq/iTszmwe6p4c4tsEuiiDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:19:51.374029Z"},"content_sha256":"53bfacd9b4780c63681a8b635106b41601f537a4861ac7fb30eee6038a9640ca","schema_version":"1.0","event_id":"sha256:53bfacd9b4780c63681a8b635106b41601f537a4861ac7fb30eee6038a9640ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7VYCJFVZEDSMQP273MLQTDYYJ4/bundle.json","state_url":"https://pith.science/pith/7VYCJFVZEDSMQP273MLQTDYYJ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7VYCJFVZEDSMQP273MLQTDYYJ4/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":"2026-08-19T15:19:51Z","links":{"resolver":"https://pith.science/pith/7VYCJFVZEDSMQP273MLQTDYYJ4","bundle":"https://pith.science/pith/7VYCJFVZEDSMQP273MLQTDYYJ4/bundle.json","state":"https://pith.science/pith/7VYCJFVZEDSMQP273MLQTDYYJ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7VYCJFVZEDSMQP273MLQTDYYJ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7VYCJFVZEDSMQP273MLQTDYYJ4","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":"52447bf1f9143b4a659b5961ff7e4a21af0ca81a4425dc78bddcaf38356d202f","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-04T14:14:58Z","title_canon_sha256":"2cdd508d5324fb05fae212cc74b842c286aef949f11b4704998b72193332d309"},"schema_version":"1.0","source":{"id":"2103.03049","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.03049","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"arxiv_version","alias_value":"2103.03049v1","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03049","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"pith_short_12","alias_value":"7VYCJFVZEDSM","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"pith_short_16","alias_value":"7VYCJFVZEDSMQP27","created_at":"2026-07-05T02:20:23Z"},{"alias_kind":"pith_short_8","alias_value":"7VYCJFVZ","created_at":"2026-07-05T02:20:23Z"}],"graph_snapshots":[{"event_id":"sha256:53bfacd9b4780c63681a8b635106b41601f537a4861ac7fb30eee6038a9640ca","target":"graph","created_at":"2026-07-05T02:20:23Z","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/2103.03049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, it has become easier to obtain speech data from various media such as the internet or YouTube, but directly utilizing them to train a neural text-to-speech (TTS) model is difficult. The proportion of clean speech is insufficient and the remainder includes background music. Even with the global style token (GST). Therefore, we propose the following method to successfully train an end-to-end TTS model with limited broadcast data. First, the background music is removed from the speech by introducing a music filter. Second, the GST-TTS model with an auxiliary quality classifier is traine","authors_text":"Hanbin Bae, Hoon-Young Cho, Jae-Sung Bae, Young-Ik Kim, Young-Sun Joo","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-04T14:14:58Z","title":"A Neural Text-to-Speech Model Utilizing Broadcast Data Mixed with Background Music"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.03049","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":"sha256:75828c8f5bca5aa92bae72e7c39abc21cdf64a3134cf1ffddb73e882c3a4f029","target":"record","created_at":"2026-07-05T02:20:23Z","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":"52447bf1f9143b4a659b5961ff7e4a21af0ca81a4425dc78bddcaf38356d202f","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-04T14:14:58Z","title_canon_sha256":"2cdd508d5324fb05fae212cc74b842c286aef949f11b4704998b72193332d309"},"schema_version":"1.0","source":{"id":"2103.03049","kind":"arxiv","version":1}},"canonical_sha256":"fd702496b920e4c83f5fdb17098f184f3b41bbb0848681036da1f0ee2261f1cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd702496b920e4c83f5fdb17098f184f3b41bbb0848681036da1f0ee2261f1cd","first_computed_at":"2026-07-05T02:20:23.868927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:20:23.868927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"egELQ+lma4cuGwROzU38MURdvq++L0t3ytIVIOz8W6ue/MknhPcY9BUqsivoD0qKshZosBTblYS5f+NLbG6uDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:20:23.869459Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.03049","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75828c8f5bca5aa92bae72e7c39abc21cdf64a3134cf1ffddb73e882c3a4f029","sha256:53bfacd9b4780c63681a8b635106b41601f537a4861ac7fb30eee6038a9640ca"],"state_sha256":"dfe230ccc3ac650b6a5084878429fa48f3b2df006780ef68664b7d9909ff1edd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g8qRKuOkG2yFmkPfxGxHSGC30t8Hg/Z0k09UENUKTzs11uwhx4/87fqmX0nvXsyhRaHTYLdRwhlhWg/lUtb1Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T15:19:51.377912Z","bundle_sha256":"b09fa8c8feb50c10beab608f8a1185519407adc9183f7e30a90f1f6927ef8576"}}