{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:EPH23MW2KN33YC6OAF3BTCKJQJ","short_pith_number":"pith:EPH23MW2","canonical_record":{"source":{"id":"2203.16838","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-31T06:45:39Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"c0b66241d145b250b370bffbdcd12d11d8f544668dc98bb802247bef43512ff4","abstract_canon_sha256":"7abe7ff579220191f88e9b759d3b43fec26b43a1ded034929c502bf4368e7751"},"schema_version":"1.0"},"canonical_sha256":"23cfadb2da5377bc0bce01761989498246c4c760be871061c9da535413ca94cb","source":{"kind":"arxiv","id":"2203.16838","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.16838","created_at":"2026-07-05T04:10:28Z"},{"alias_kind":"arxiv_version","alias_value":"2203.16838v1","created_at":"2026-07-05T04:10:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16838","created_at":"2026-07-05T04:10:28Z"},{"alias_kind":"pith_short_12","alias_value":"EPH23MW2KN33","created_at":"2026-07-05T04:10:28Z"},{"alias_kind":"pith_short_16","alias_value":"EPH23MW2KN33YC6O","created_at":"2026-07-05T04:10:28Z"},{"alias_kind":"pith_short_8","alias_value":"EPH23MW2","created_at":"2026-07-05T04:10:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:EPH23MW2KN33YC6OAF3BTCKJQJ","target":"record","payload":{"canonical_record":{"source":{"id":"2203.16838","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-31T06:45:39Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"c0b66241d145b250b370bffbdcd12d11d8f544668dc98bb802247bef43512ff4","abstract_canon_sha256":"7abe7ff579220191f88e9b759d3b43fec26b43a1ded034929c502bf4368e7751"},"schema_version":"1.0"},"canonical_sha256":"23cfadb2da5377bc0bce01761989498246c4c760be871061c9da535413ca94cb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:28.556254Z","signature_b64":"8nJ0xfteK0mVMbg6rvYi9ObzOTd4r391W6MOowjDwZUIfepDxdqLj2SOzchlt/c9qUc3VpbvLOIuZPDEhpzqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23cfadb2da5377bc0bce01761989498246c4c760be871061c9da535413ca94cb","last_reissued_at":"2026-07-05T04:10:28.555771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:28.555771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.16838","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":"2026-07-05T04:10:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bb4e4AbFfF3GoRCEowmMzX2uaFjjxwBeQt5d6iotkjbSXiajV3SZEgxGYK3SiHvgzO1Ib1nZi8c651hgJRZGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:05:47.314832Z"},"content_sha256":"7f03781540e06a16cecedf9ef34de07a97be27a57e8a946adaf2d8899c02595d","schema_version":"1.0","event_id":"sha256:7f03781540e06a16cecedf9ef34de07a97be27a57e8a946adaf2d8899c02595d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:EPH23MW2KN33YC6OAF3BTCKJQJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NeuFA: Neural Network Based End-to-End Forced Alignment with Bidirectional Attention Mechanism","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Helen Meng, Jingbei Li, Qiao Tian, Yi Meng, Yuping Wang, Yuxuan Wang, Zhiyong Wu","submitted_at":"2022-03-31T06:45:39Z","abstract_excerpt":"Although deep learning and end-to-end models have been widely used and shown superiority in automatic speech recognition (ASR) and text-to-speech (TTS) synthesis, state-of-the-art forced alignment (FA) models are still based on hidden Markov model (HMM). HMM has limited view of contextual information and is developed with long pipelines, leading to error accumulation and unsatisfactory performance. Inspired by the capability of attention mechanism in capturing long term contextual information and learning alignments in ASR and TTS, we propose a neural network based end-to-end forced aligner ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16838","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/2203.16838/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":"2026-07-05T04:10:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O9c+Bi4wduGh07+DTYCidF2623NMH9eEcuXnpmcngK8YM5N4xzgD9wb9pFKPJwpFfpKP0TwhpY04kYVPvXkDBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:05:47.315235Z"},"content_sha256":"7313841408064583a1fe21a26beb20a773af77de1b35c91bc0b8a3e7c2337898","schema_version":"1.0","event_id":"sha256:7313841408064583a1fe21a26beb20a773af77de1b35c91bc0b8a3e7c2337898"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EPH23MW2KN33YC6OAF3BTCKJQJ/bundle.json","state_url":"https://pith.science/pith/EPH23MW2KN33YC6OAF3BTCKJQJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EPH23MW2KN33YC6OAF3BTCKJQJ/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":"2026-07-06T19:05:47Z","links":{"resolver":"https://pith.science/pith/EPH23MW2KN33YC6OAF3BTCKJQJ","bundle":"https://pith.science/pith/EPH23MW2KN33YC6OAF3BTCKJQJ/bundle.json","state":"https://pith.science/pith/EPH23MW2KN33YC6OAF3BTCKJQJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EPH23MW2KN33YC6OAF3BTCKJQJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EPH23MW2KN33YC6OAF3BTCKJQJ","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":"7abe7ff579220191f88e9b759d3b43fec26b43a1ded034929c502bf4368e7751","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-31T06:45:39Z","title_canon_sha256":"c0b66241d145b250b370bffbdcd12d11d8f544668dc98bb802247bef43512ff4"},"schema_version":"1.0","source":{"id":"2203.16838","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.16838","created_at":"2026-07-05T04:10:28Z"},{"alias_kind":"arxiv_version","alias_value":"2203.16838v1","created_at":"2026-07-05T04:10:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16838","created_at":"2026-07-05T04:10:28Z"},{"alias_kind":"pith_short_12","alias_value":"EPH23MW2KN33","created_at":"2026-07-05T04:10:28Z"},{"alias_kind":"pith_short_16","alias_value":"EPH23MW2KN33YC6O","created_at":"2026-07-05T04:10:28Z"},{"alias_kind":"pith_short_8","alias_value":"EPH23MW2","created_at":"2026-07-05T04:10:28Z"}],"graph_snapshots":[{"event_id":"sha256:7313841408064583a1fe21a26beb20a773af77de1b35c91bc0b8a3e7c2337898","target":"graph","created_at":"2026-07-05T04:10:28Z","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/2203.16838/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although deep learning and end-to-end models have been widely used and shown superiority in automatic speech recognition (ASR) and text-to-speech (TTS) synthesis, state-of-the-art forced alignment (FA) models are still based on hidden Markov model (HMM). HMM has limited view of contextual information and is developed with long pipelines, leading to error accumulation and unsatisfactory performance. Inspired by the capability of attention mechanism in capturing long term contextual information and learning alignments in ASR and TTS, we propose a neural network based end-to-end forced aligner ca","authors_text":"Helen Meng, Jingbei Li, Qiao Tian, Yi Meng, Yuping Wang, Yuxuan Wang, Zhiyong Wu","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-31T06:45:39Z","title":"NeuFA: Neural Network Based End-to-End Forced Alignment with Bidirectional Attention Mechanism"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16838","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":"sha256:7f03781540e06a16cecedf9ef34de07a97be27a57e8a946adaf2d8899c02595d","target":"record","created_at":"2026-07-05T04:10:28Z","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":"7abe7ff579220191f88e9b759d3b43fec26b43a1ded034929c502bf4368e7751","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-31T06:45:39Z","title_canon_sha256":"c0b66241d145b250b370bffbdcd12d11d8f544668dc98bb802247bef43512ff4"},"schema_version":"1.0","source":{"id":"2203.16838","kind":"arxiv","version":1}},"canonical_sha256":"23cfadb2da5377bc0bce01761989498246c4c760be871061c9da535413ca94cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23cfadb2da5377bc0bce01761989498246c4c760be871061c9da535413ca94cb","first_computed_at":"2026-07-05T04:10:28.555771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:10:28.555771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8nJ0xfteK0mVMbg6rvYi9ObzOTd4r391W6MOowjDwZUIfepDxdqLj2SOzchlt/c9qUc3VpbvLOIuZPDEhpzqDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:10:28.556254Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.16838","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f03781540e06a16cecedf9ef34de07a97be27a57e8a946adaf2d8899c02595d","sha256:7313841408064583a1fe21a26beb20a773af77de1b35c91bc0b8a3e7c2337898"],"state_sha256":"7816d5c0300be9075e7079ab6837b503644d8526f8a8755228ecd6e2387c03b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ieNqAXvyLsWK6I7GbZdWs5BePclky4fT5fU1uKba61n0845rNS5s/pIkSvB9sNjg/tH31VtP/j+Ek39sLVfCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:05:47.317292Z","bundle_sha256":"7ea71a46cadc317cc835328fb44ddf2f24fa4c407673ed945d2db53c4d98b926"}}