{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:3EVKIYRQGHUDQAHZNAQDO2JCJW","short_pith_number":"pith:3EVKIYRQ","schema_version":"1.0","canonical_sha256":"d92aa4623031e83800f968203769224da81e9f8f49cc9f08a6ef8faa72af1ff0","source":{"kind":"arxiv","id":"1409.8558","version":1},"attestation_state":"computed","paper":{"title":"A Deep Learning Approach to Data-driven Parameterizations for Statistical Parametric Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Alan W. Black, Prasanna Kumar Muthukumar","submitted_at":"2014-09-30T14:20:29Z","abstract_excerpt":"Nearly all Statistical Parametric Speech Synthesizers today use Mel Cepstral coefficients as the vocal tract parameterization of the speech signal. Mel Cepstral coefficients were never intended to work in a parametric speech synthesis framework, but as yet, there has been little success in creating a better parameterization that is more suited to synthesis. In this paper, we use deep learning algorithms to investigate a data-driven parameterization technique that is designed for the specific requirements of synthesis. We create an invertible, low-dimensional, noise-robust encoding of the Mel L"},"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":"1409.8558","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-09-30T14:20:29Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"e2fb20023c8a6905a357d65ee24785993b3e8c987ea50122922b722252654546","abstract_canon_sha256":"11700c6e591049ecf4841b1f7e4b76ff5a2baa65def8cf9b73c59ecb08d2423e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:41:24.211267Z","signature_b64":"4g0XZQVhlDD0AUV/WXcp2urNa7KQfpUavA/UzJgBlqsy0zFwa6JKFAAuVWDvhnQFoQBgl1JFgYFF+wFqlrtZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d92aa4623031e83800f968203769224da81e9f8f49cc9f08a6ef8faa72af1ff0","last_reissued_at":"2026-05-18T02:41:24.210797Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:41:24.210797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Deep Learning Approach to Data-driven Parameterizations for Statistical Parametric Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Alan W. Black, Prasanna Kumar Muthukumar","submitted_at":"2014-09-30T14:20:29Z","abstract_excerpt":"Nearly all Statistical Parametric Speech Synthesizers today use Mel Cepstral coefficients as the vocal tract parameterization of the speech signal. Mel Cepstral coefficients were never intended to work in a parametric speech synthesis framework, but as yet, there has been little success in creating a better parameterization that is more suited to synthesis. In this paper, we use deep learning algorithms to investigate a data-driven parameterization technique that is designed for the specific requirements of synthesis. We create an invertible, low-dimensional, noise-robust encoding of the Mel L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.8558","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":""},"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":"1409.8558","created_at":"2026-05-18T02:41:24.210879+00:00"},{"alias_kind":"arxiv_version","alias_value":"1409.8558v1","created_at":"2026-05-18T02:41:24.210879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.8558","created_at":"2026-05-18T02:41:24.210879+00:00"},{"alias_kind":"pith_short_12","alias_value":"3EVKIYRQGHUD","created_at":"2026-05-18T12:28:11.866339+00:00"},{"alias_kind":"pith_short_16","alias_value":"3EVKIYRQGHUDQAHZ","created_at":"2026-05-18T12:28:11.866339+00:00"},{"alias_kind":"pith_short_8","alias_value":"3EVKIYRQ","created_at":"2026-05-18T12:28:11.866339+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1609.03499","citing_title":"WaveNet: A Generative Model for Raw Audio","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3EVKIYRQGHUDQAHZNAQDO2JCJW","json":"https://pith.science/pith/3EVKIYRQGHUDQAHZNAQDO2JCJW.json","graph_json":"https://pith.science/api/pith-number/3EVKIYRQGHUDQAHZNAQDO2JCJW/graph.json","events_json":"https://pith.science/api/pith-number/3EVKIYRQGHUDQAHZNAQDO2JCJW/events.json","paper":"https://pith.science/paper/3EVKIYRQ"},"agent_actions":{"view_html":"https://pith.science/pith/3EVKIYRQGHUDQAHZNAQDO2JCJW","download_json":"https://pith.science/pith/3EVKIYRQGHUDQAHZNAQDO2JCJW.json","view_paper":"https://pith.science/paper/3EVKIYRQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1409.8558&json=true","fetch_graph":"https://pith.science/api/pith-number/3EVKIYRQGHUDQAHZNAQDO2JCJW/graph.json","fetch_events":"https://pith.science/api/pith-number/3EVKIYRQGHUDQAHZNAQDO2JCJW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3EVKIYRQGHUDQAHZNAQDO2JCJW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3EVKIYRQGHUDQAHZNAQDO2JCJW/action/storage_attestation","attest_author":"https://pith.science/pith/3EVKIYRQGHUDQAHZNAQDO2JCJW/action/author_attestation","sign_citation":"https://pith.science/pith/3EVKIYRQGHUDQAHZNAQDO2JCJW/action/citation_signature","submit_replication":"https://pith.science/pith/3EVKIYRQGHUDQAHZNAQDO2JCJW/action/replication_record"}},"created_at":"2026-05-18T02:41:24.210879+00:00","updated_at":"2026-05-18T02:41:24.210879+00:00"}