{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MMZIQG3DBJJVRZFC55KFVSS6BR","short_pith_number":"pith:MMZIQG3D","schema_version":"1.0","canonical_sha256":"6332881b630a5358e4a2ef545aca5e0c755b27b1116bdb4b6956a9abdfab735a","source":{"kind":"arxiv","id":"2407.09732","version":1},"attestation_state":"computed","paper":{"title":"Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Adrian Nicolas Florea, Cong Han, Nima Mesgarani, Xilin Jiang, Yinghao Aaron Li","submitted_at":"2024-07-13T00:35:21Z","abstract_excerpt":"It is too early to conclude that Mamba is a better alternative to transformers for speech before comparing Mamba with transformers in terms of both performance and efficiency in multiple speech-related tasks. To reach this conclusion, we propose and evaluate three models for three tasks: Mamba-TasNet for speech separation, ConMamba for speech recognition, and VALL-M for speech synthesis. We compare them with transformers of similar sizes in performance, memory, and speed. Our Mamba or Mamba-transformer hybrid models show comparable or higher performance than their transformer counterparts: Sep"},"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":"2407.09732","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-13T00:35:21Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"cdf9722478dcaa0dcb73c81adfafe91b73b9ebdecf24a5ec65e6ab70620b145d","abstract_canon_sha256":"0ec3d2d9e1e707fc62337c917a5d0d3fbf69093081610447a3369b248a981fb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:34.173417Z","signature_b64":"QuGsdQ30DJh/Fh2HennG6sUa7L1qBNRw1hLb2kQgL1iDyYnoNJTRK+bnK5IAhtARPL7H763IS9FC+PQw2rwkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6332881b630a5358e4a2ef545aca5e0c755b27b1116bdb4b6956a9abdfab735a","last_reissued_at":"2026-07-05T08:43:34.173066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:34.173066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Adrian Nicolas Florea, Cong Han, Nima Mesgarani, Xilin Jiang, Yinghao Aaron Li","submitted_at":"2024-07-13T00:35:21Z","abstract_excerpt":"It is too early to conclude that Mamba is a better alternative to transformers for speech before comparing Mamba with transformers in terms of both performance and efficiency in multiple speech-related tasks. To reach this conclusion, we propose and evaluate three models for three tasks: Mamba-TasNet for speech separation, ConMamba for speech recognition, and VALL-M for speech synthesis. We compare them with transformers of similar sizes in performance, memory, and speed. Our Mamba or Mamba-transformer hybrid models show comparable or higher performance than their transformer counterparts: Sep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09732","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/2407.09732/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":"2407.09732","created_at":"2026-07-05T08:43:34.173124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.09732v1","created_at":"2026-07-05T08:43:34.173124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09732","created_at":"2026-07-05T08:43:34.173124+00:00"},{"alias_kind":"pith_short_12","alias_value":"MMZIQG3DBJJV","created_at":"2026-07-05T08:43:34.173124+00:00"},{"alias_kind":"pith_short_16","alias_value":"MMZIQG3DBJJVRZFC","created_at":"2026-07-05T08:43:34.173124+00:00"},{"alias_kind":"pith_short_8","alias_value":"MMZIQG3D","created_at":"2026-07-05T08:43:34.173124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16911","citing_title":"Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberation","ref_index":92,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MMZIQG3DBJJVRZFC55KFVSS6BR","json":"https://pith.science/pith/MMZIQG3DBJJVRZFC55KFVSS6BR.json","graph_json":"https://pith.science/api/pith-number/MMZIQG3DBJJVRZFC55KFVSS6BR/graph.json","events_json":"https://pith.science/api/pith-number/MMZIQG3DBJJVRZFC55KFVSS6BR/events.json","paper":"https://pith.science/paper/MMZIQG3D"},"agent_actions":{"view_html":"https://pith.science/pith/MMZIQG3DBJJVRZFC55KFVSS6BR","download_json":"https://pith.science/pith/MMZIQG3DBJJVRZFC55KFVSS6BR.json","view_paper":"https://pith.science/paper/MMZIQG3D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.09732&json=true","fetch_graph":"https://pith.science/api/pith-number/MMZIQG3DBJJVRZFC55KFVSS6BR/graph.json","fetch_events":"https://pith.science/api/pith-number/MMZIQG3DBJJVRZFC55KFVSS6BR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MMZIQG3DBJJVRZFC55KFVSS6BR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MMZIQG3DBJJVRZFC55KFVSS6BR/action/storage_attestation","attest_author":"https://pith.science/pith/MMZIQG3DBJJVRZFC55KFVSS6BR/action/author_attestation","sign_citation":"https://pith.science/pith/MMZIQG3DBJJVRZFC55KFVSS6BR/action/citation_signature","submit_replication":"https://pith.science/pith/MMZIQG3DBJJVRZFC55KFVSS6BR/action/replication_record"}},"created_at":"2026-07-05T08:43:34.173124+00:00","updated_at":"2026-07-05T08:43:34.173124+00:00"}