{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MBBVN2PRU5P6Z2N2FYE57TKGFE","short_pith_number":"pith:MBBVN2PR","schema_version":"1.0","canonical_sha256":"604356e9f1a75fece9ba2e09dfcd462933a0ccc71a9d685b888706edea217a1f","source":{"kind":"arxiv","id":"2107.01922","version":1},"attestation_state":"computed","paper":{"title":"Investigation of Practical Aspects of Single Channel Speech Separation for ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jian Wu, Jinyu Li, Naoyuki Kanda, Sanyuan Chen, Shujie Liu, Takuya Yoshioka, Yu Wu, Zhuo Chen","submitted_at":"2021-07-05T10:35:35Z","abstract_excerpt":"Speech separation has been successfully applied as a frontend processing module of conversation transcription systems thanks to its ability to handle overlapped speech and its flexibility to combine with downstream tasks such as automatic speech recognition (ASR). However, a speech separation model often introduces target speech distortion, resulting in a sub-optimum word error rate (WER). In this paper, we describe our efforts to improve the performance of a single channel speech separation system. Specifically, we investigate a two-stage training scheme that firstly applies a feature level o"},"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":"2107.01922","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-07-05T10:35:35Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"ecf4b985e9bebc32c9363857da49ef1bf406560917219558198461e167e19b43","abstract_canon_sha256":"a9f2986894724aaa5384469afd96a67a6326c7430dbef27a182725bd0a39c0dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:55:01.872840Z","signature_b64":"2NDsaUiRRKJFUPtcxGkHvzUNkKW4RWSKD3VRJgJ7K8QeN2PrKKPp9W/GH7xofdql/TqdD23SY3oquUSTq6H7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"604356e9f1a75fece9ba2e09dfcd462933a0ccc71a9d685b888706edea217a1f","last_reissued_at":"2026-07-05T02:55:01.872510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:55:01.872510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Investigation of Practical Aspects of Single Channel Speech Separation for ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jian Wu, Jinyu Li, Naoyuki Kanda, Sanyuan Chen, Shujie Liu, Takuya Yoshioka, Yu Wu, Zhuo Chen","submitted_at":"2021-07-05T10:35:35Z","abstract_excerpt":"Speech separation has been successfully applied as a frontend processing module of conversation transcription systems thanks to its ability to handle overlapped speech and its flexibility to combine with downstream tasks such as automatic speech recognition (ASR). However, a speech separation model often introduces target speech distortion, resulting in a sub-optimum word error rate (WER). In this paper, we describe our efforts to improve the performance of a single channel speech separation system. Specifically, we investigate a two-stage training scheme that firstly applies a feature level o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01922","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/2107.01922/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":"2107.01922","created_at":"2026-07-05T02:55:01.872563+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.01922v1","created_at":"2026-07-05T02:55:01.872563+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01922","created_at":"2026-07-05T02:55:01.872563+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBBVN2PRU5P6","created_at":"2026-07-05T02:55:01.872563+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBBVN2PRU5P6Z2N2","created_at":"2026-07-05T02:55:01.872563+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBBVN2PR","created_at":"2026-07-05T02:55:01.872563+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/MBBVN2PRU5P6Z2N2FYE57TKGFE","json":"https://pith.science/pith/MBBVN2PRU5P6Z2N2FYE57TKGFE.json","graph_json":"https://pith.science/api/pith-number/MBBVN2PRU5P6Z2N2FYE57TKGFE/graph.json","events_json":"https://pith.science/api/pith-number/MBBVN2PRU5P6Z2N2FYE57TKGFE/events.json","paper":"https://pith.science/paper/MBBVN2PR"},"agent_actions":{"view_html":"https://pith.science/pith/MBBVN2PRU5P6Z2N2FYE57TKGFE","download_json":"https://pith.science/pith/MBBVN2PRU5P6Z2N2FYE57TKGFE.json","view_paper":"https://pith.science/paper/MBBVN2PR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.01922&json=true","fetch_graph":"https://pith.science/api/pith-number/MBBVN2PRU5P6Z2N2FYE57TKGFE/graph.json","fetch_events":"https://pith.science/api/pith-number/MBBVN2PRU5P6Z2N2FYE57TKGFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBBVN2PRU5P6Z2N2FYE57TKGFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBBVN2PRU5P6Z2N2FYE57TKGFE/action/storage_attestation","attest_author":"https://pith.science/pith/MBBVN2PRU5P6Z2N2FYE57TKGFE/action/author_attestation","sign_citation":"https://pith.science/pith/MBBVN2PRU5P6Z2N2FYE57TKGFE/action/citation_signature","submit_replication":"https://pith.science/pith/MBBVN2PRU5P6Z2N2FYE57TKGFE/action/replication_record"}},"created_at":"2026-07-05T02:55:01.872563+00:00","updated_at":"2026-07-05T02:55:01.872563+00:00"}