{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SS5P5CRX36ZTLKLI3JKOB2UIO4","short_pith_number":"pith:SS5P5CRX","schema_version":"1.0","canonical_sha256":"94bafe8a37dfb335a968da54e0ea88771af2d9aa89c9d6840b8882af8c178009","source":{"kind":"arxiv","id":"1912.11613","version":1},"attestation_state":"computed","paper":{"title":"Utterance-level Permutation Invariant Training with Latency-controlled BLSTM for Single-channel Multi-talker Speech Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gaofeng Cheng, Jiasong Sun, Lu Huang, Pengyuan Zhang, Shumin Xu, Yi Yang","submitted_at":"2019-12-25T07:40:02Z","abstract_excerpt":"Utterance-level permutation invariant training (uPIT) has achieved promising progress on single-channel multi-talker speech separation task. Long short-term memory (LSTM) and bidirectional LSTM (BLSTM) are widely used as the separation networks of uPIT, i.e. uPIT-LSTM and uPIT-BLSTM. uPIT-LSTM has lower latency but worse performance, while uPIT-BLSTM has better performance but higher latency. In this paper, we propose using latency-controlled BLSTM (LC-BLSTM) during inference to fulfill low-latency and good-performance speech separation. To find a better training strategy for BLSTM-based separ"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1912.11613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-12-25T07:40:02Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"a2ba0a2b1bd23c55ffd9b7162583b94d9b3f9931329f97edd56233cfee03c714","abstract_canon_sha256":"6085830b59a5f519df326bd3d6cd29474b296d5f86fc477ce7e1a941a7ef8e4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:28:27.872927Z","signature_b64":"3OrMqSLtc87uDQAS3DJB5B15s1f8JYEckemC5vZGra0SKMi1Jv3x9D5D6yH151apeV1qPyInU2eGavxuHaVRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94bafe8a37dfb335a968da54e0ea88771af2d9aa89c9d6840b8882af8c178009","last_reissued_at":"2026-07-05T00:28:27.872525Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:28:27.872525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Utterance-level Permutation Invariant Training with Latency-controlled BLSTM for Single-channel Multi-talker Speech Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gaofeng Cheng, Jiasong Sun, Lu Huang, Pengyuan Zhang, Shumin Xu, Yi Yang","submitted_at":"2019-12-25T07:40:02Z","abstract_excerpt":"Utterance-level permutation invariant training (uPIT) has achieved promising progress on single-channel multi-talker speech separation task. Long short-term memory (LSTM) and bidirectional LSTM (BLSTM) are widely used as the separation networks of uPIT, i.e. uPIT-LSTM and uPIT-BLSTM. uPIT-LSTM has lower latency but worse performance, while uPIT-BLSTM has better performance but higher latency. In this paper, we propose using latency-controlled BLSTM (LC-BLSTM) during inference to fulfill low-latency and good-performance speech separation. To find a better training strategy for BLSTM-based separ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.11613","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/1912.11613/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1912.11613","created_at":"2026-07-05T00:28:27.872590+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.11613v1","created_at":"2026-07-05T00:28:27.872590+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.11613","created_at":"2026-07-05T00:28:27.872590+00:00"},{"alias_kind":"pith_short_12","alias_value":"SS5P5CRX36ZT","created_at":"2026-07-05T00:28:27.872590+00:00"},{"alias_kind":"pith_short_16","alias_value":"SS5P5CRX36ZTLKLI","created_at":"2026-07-05T00:28:27.872590+00:00"},{"alias_kind":"pith_short_8","alias_value":"SS5P5CRX","created_at":"2026-07-05T00:28:27.872590+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SS5P5CRX36ZTLKLI3JKOB2UIO4","json":"https://pith.science/pith/SS5P5CRX36ZTLKLI3JKOB2UIO4.json","graph_json":"https://pith.science/api/pith-number/SS5P5CRX36ZTLKLI3JKOB2UIO4/graph.json","events_json":"https://pith.science/api/pith-number/SS5P5CRX36ZTLKLI3JKOB2UIO4/events.json","paper":"https://pith.science/paper/SS5P5CRX"},"agent_actions":{"view_html":"https://pith.science/pith/SS5P5CRX36ZTLKLI3JKOB2UIO4","download_json":"https://pith.science/pith/SS5P5CRX36ZTLKLI3JKOB2UIO4.json","view_paper":"https://pith.science/paper/SS5P5CRX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.11613&json=true","fetch_graph":"https://pith.science/api/pith-number/SS5P5CRX36ZTLKLI3JKOB2UIO4/graph.json","fetch_events":"https://pith.science/api/pith-number/SS5P5CRX36ZTLKLI3JKOB2UIO4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SS5P5CRX36ZTLKLI3JKOB2UIO4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SS5P5CRX36ZTLKLI3JKOB2UIO4/action/storage_attestation","attest_author":"https://pith.science/pith/SS5P5CRX36ZTLKLI3JKOB2UIO4/action/author_attestation","sign_citation":"https://pith.science/pith/SS5P5CRX36ZTLKLI3JKOB2UIO4/action/citation_signature","submit_replication":"https://pith.science/pith/SS5P5CRX36ZTLKLI3JKOB2UIO4/action/replication_record"}},"created_at":"2026-07-05T00:28:27.872590+00:00","updated_at":"2026-07-05T00:28:27.872590+00:00"}