{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:3YIIYNZ2UE2PPTZZ32Z3HIR435","short_pith_number":"pith:3YIIYNZ2","canonical_record":{"source":{"id":"1811.08111","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-11-20T08:02:54Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"6ab116b7f2f9fa01898369d682250cad3b8246f64456be381e24d0097b601291","abstract_canon_sha256":"f44f9feefc49222d4b5bebed2e4f2d9eb143a28c974c6b6eebc27e34aa1f7f9b"},"schema_version":"1.0"},"canonical_sha256":"de108c373aa134f7cf39deb3b3a23cdf6f66d0184bdf5dbf5bbe6ce5227a061c","source":{"kind":"arxiv","id":"1811.08111","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.08111","created_at":"2026-07-05T00:32:47Z"},{"alias_kind":"arxiv_version","alias_value":"1811.08111v1","created_at":"2026-07-05T00:32:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.08111","created_at":"2026-07-05T00:32:47Z"},{"alias_kind":"pith_short_12","alias_value":"3YIIYNZ2UE2P","created_at":"2026-07-05T00:32:47Z"},{"alias_kind":"pith_short_16","alias_value":"3YIIYNZ2UE2PPTZZ","created_at":"2026-07-05T00:32:47Z"},{"alias_kind":"pith_short_8","alias_value":"3YIIYNZ2","created_at":"2026-07-05T00:32:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:3YIIYNZ2UE2PPTZZ32Z3HIR435","target":"record","payload":{"canonical_record":{"source":{"id":"1811.08111","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-11-20T08:02:54Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"6ab116b7f2f9fa01898369d682250cad3b8246f64456be381e24d0097b601291","abstract_canon_sha256":"f44f9feefc49222d4b5bebed2e4f2d9eb143a28c974c6b6eebc27e34aa1f7f9b"},"schema_version":"1.0"},"canonical_sha256":"de108c373aa134f7cf39deb3b3a23cdf6f66d0184bdf5dbf5bbe6ce5227a061c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:32:47.983199Z","signature_b64":"V782f2+Fclb8EAEpb9IMD/4mbwxFWN1mE7ejWT7j7/dmiDFZ2+VzLBX21t8GAX0Mkw59NS2CuIp0wfTiuvb7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de108c373aa134f7cf39deb3b3a23cdf6f66d0184bdf5dbf5bbe6ce5227a061c","last_reissued_at":"2026-07-05T00:32:47.982692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:32:47.982692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.08111","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":"2026-07-05T00:32:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"coI8kyaAr56wezDbYRZ23Qaq6DKNi8wQpb97j9nTuJ27nacZmCx/3w1TDT2cJTpv7GYiNK6I0plgJZQqBygwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:55:31.555476Z"},"content_sha256":"76e886c7cf028b2cf6479e84b42029c40b30b4418d0477ebd943700d3b1e2494","schema_version":"1.0","event_id":"sha256:76e886c7cf028b2cf6479e84b42029c40b30b4418d0477ebd943700d3b1e2494"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:3YIIYNZ2UE2PPTZZ32Z3HIR435","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Sequence-to-Sequence Acoustic Modeling by Adding Text-Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chen Liang, Jing-Xuan Zhang, Li-Juan Liu, Li-Rong Dai, Yuan Jiang, Zhen-Hua Ling","submitted_at":"2018-11-20T08:02:54Z","abstract_excerpt":"This paper presents methods of making using of text supervision to improve the performance of sequence-to-sequence (seq2seq) voice conversion. Compared with conventional frame-to-frame voice conversion approaches, the seq2seq acoustic modeling method proposed in our previous work achieved higher naturalness and similarity. In this paper, we further improve its performance by utilizing the text transcriptions of parallel training data. First, a multi-task learning structure is designed which adds auxiliary classifiers to the middle layers of the seq2seq model and predicts linguistic labels as a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.08111","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/1811.08111/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":"2026-07-05T00:32:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LAWcU+e4S8Zxtyine4RMPZYfwhOVQUzIx+fc8rKKSATGQ1mmj9jLt0bIR/AuA3F9ykwFrWW3LA/iMEKe2TkcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:55:31.555852Z"},"content_sha256":"29e6df4148ffda5d94c109e7ee6fb6d38979fb415cdc8e7db371259dc1eae8d4","schema_version":"1.0","event_id":"sha256:29e6df4148ffda5d94c109e7ee6fb6d38979fb415cdc8e7db371259dc1eae8d4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3YIIYNZ2UE2PPTZZ32Z3HIR435/bundle.json","state_url":"https://pith.science/pith/3YIIYNZ2UE2PPTZZ32Z3HIR435/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3YIIYNZ2UE2PPTZZ32Z3HIR435/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":"2026-07-07T03:55:31Z","links":{"resolver":"https://pith.science/pith/3YIIYNZ2UE2PPTZZ32Z3HIR435","bundle":"https://pith.science/pith/3YIIYNZ2UE2PPTZZ32Z3HIR435/bundle.json","state":"https://pith.science/pith/3YIIYNZ2UE2PPTZZ32Z3HIR435/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3YIIYNZ2UE2PPTZZ32Z3HIR435/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:3YIIYNZ2UE2PPTZZ32Z3HIR435","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":"f44f9feefc49222d4b5bebed2e4f2d9eb143a28c974c6b6eebc27e34aa1f7f9b","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-11-20T08:02:54Z","title_canon_sha256":"6ab116b7f2f9fa01898369d682250cad3b8246f64456be381e24d0097b601291"},"schema_version":"1.0","source":{"id":"1811.08111","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.08111","created_at":"2026-07-05T00:32:47Z"},{"alias_kind":"arxiv_version","alias_value":"1811.08111v1","created_at":"2026-07-05T00:32:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.08111","created_at":"2026-07-05T00:32:47Z"},{"alias_kind":"pith_short_12","alias_value":"3YIIYNZ2UE2P","created_at":"2026-07-05T00:32:47Z"},{"alias_kind":"pith_short_16","alias_value":"3YIIYNZ2UE2PPTZZ","created_at":"2026-07-05T00:32:47Z"},{"alias_kind":"pith_short_8","alias_value":"3YIIYNZ2","created_at":"2026-07-05T00:32:47Z"}],"graph_snapshots":[{"event_id":"sha256:29e6df4148ffda5d94c109e7ee6fb6d38979fb415cdc8e7db371259dc1eae8d4","target":"graph","created_at":"2026-07-05T00:32:47Z","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/1811.08111/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents methods of making using of text supervision to improve the performance of sequence-to-sequence (seq2seq) voice conversion. Compared with conventional frame-to-frame voice conversion approaches, the seq2seq acoustic modeling method proposed in our previous work achieved higher naturalness and similarity. In this paper, we further improve its performance by utilizing the text transcriptions of parallel training data. First, a multi-task learning structure is designed which adds auxiliary classifiers to the middle layers of the seq2seq model and predicts linguistic labels as a","authors_text":"Chen Liang, Jing-Xuan Zhang, Li-Juan Liu, Li-Rong Dai, Yuan Jiang, Zhen-Hua Ling","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-11-20T08:02:54Z","title":"Improving Sequence-to-Sequence Acoustic Modeling by Adding Text-Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.08111","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":"sha256:76e886c7cf028b2cf6479e84b42029c40b30b4418d0477ebd943700d3b1e2494","target":"record","created_at":"2026-07-05T00:32:47Z","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":"f44f9feefc49222d4b5bebed2e4f2d9eb143a28c974c6b6eebc27e34aa1f7f9b","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-11-20T08:02:54Z","title_canon_sha256":"6ab116b7f2f9fa01898369d682250cad3b8246f64456be381e24d0097b601291"},"schema_version":"1.0","source":{"id":"1811.08111","kind":"arxiv","version":1}},"canonical_sha256":"de108c373aa134f7cf39deb3b3a23cdf6f66d0184bdf5dbf5bbe6ce5227a061c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de108c373aa134f7cf39deb3b3a23cdf6f66d0184bdf5dbf5bbe6ce5227a061c","first_computed_at":"2026-07-05T00:32:47.982692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:32:47.982692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V782f2+Fclb8EAEpb9IMD/4mbwxFWN1mE7ejWT7j7/dmiDFZ2+VzLBX21t8GAX0Mkw59NS2CuIp0wfTiuvb7CA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:32:47.983199Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.08111","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76e886c7cf028b2cf6479e84b42029c40b30b4418d0477ebd943700d3b1e2494","sha256:29e6df4148ffda5d94c109e7ee6fb6d38979fb415cdc8e7db371259dc1eae8d4"],"state_sha256":"c64dd5ad187f5946b7abb6f632b491c1922261b8c78e05ceb022419ad7b341ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"clz0j3Qrx6bXEaG1b4LD2FK1K9uRJHkmiiWF4yptqQMRDO2cyREnjTfQLQdakXOi6ztahxuAIJrXkeHpzoc1Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:55:31.558081Z","bundle_sha256":"28a53b79e16b8430798c3db215dcfbf2ff96b17d811d201b3fd9f55104364ffe"}}