{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XQR6VCX2SXBA65JSF4S3FAU67G","short_pith_number":"pith:XQR6VCX2","canonical_record":{"source":{"id":"2310.08846","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-10-13T04:13:26Z","cross_cats_sorted":[],"title_canon_sha256":"e0da2bd9896aeb605358bdf13ed2b8534c5eccf6cb6075b7d85bdd2c423ca741","abstract_canon_sha256":"def5c9f7354ebb4159577f6a145b4b2cfe4f4bff935c236476827755bc19abd0"},"schema_version":"1.0"},"canonical_sha256":"bc23ea8afa95c20f75322f25b2829ef9a3e331ce358a9087ac9ca9935aeabbd2","source":{"kind":"arxiv","id":"2310.08846","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08846","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08846v1","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08846","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"pith_short_12","alias_value":"XQR6VCX2SXBA","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"pith_short_16","alias_value":"XQR6VCX2SXBA65JS","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"pith_short_8","alias_value":"XQR6VCX2","created_at":"2026-07-05T07:00:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XQR6VCX2SXBA65JSF4S3FAU67G","target":"record","payload":{"canonical_record":{"source":{"id":"2310.08846","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-10-13T04:13:26Z","cross_cats_sorted":[],"title_canon_sha256":"e0da2bd9896aeb605358bdf13ed2b8534c5eccf6cb6075b7d85bdd2c423ca741","abstract_canon_sha256":"def5c9f7354ebb4159577f6a145b4b2cfe4f4bff935c236476827755bc19abd0"},"schema_version":"1.0"},"canonical_sha256":"bc23ea8afa95c20f75322f25b2829ef9a3e331ce358a9087ac9ca9935aeabbd2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:35.786514Z","signature_b64":"2Kh3Mbhxir94iHQCTO1o5ltuAXwHHM04o/v8zIcCt16iAc6lU+6uSe5ustgpXKLJM8YkPXTAnnCmHb4NLU2OBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc23ea8afa95c20f75322f25b2829ef9a3e331ce358a9087ac9ca9935aeabbd2","last_reissued_at":"2026-07-05T07:00:35.786064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:35.786064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.08846","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":"2026-07-05T07:00:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bbs9HdZErgkstiNkLKuQrzHrb7VKuXWQtRceQcupk7lyJ5bGCwGDmFlM/vaQ0OhJ06bXWW/JJitWkWY91Dz9AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:28:41.138395Z"},"content_sha256":"629d5d823693fe36ecb51d4f79b5d0b57bf55f2ce1aa18cb599ed208879926b0","schema_version":"1.0","event_id":"sha256:629d5d823693fe36ecb51d4f79b5d0b57bf55f2ce1aa18cb599ed208879926b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XQR6VCX2SXBA65JSF4S3FAU67G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speaking rate attention-based duration prediction for speed control TTS","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Abhayjeet Singh, Anjali Jayakumar, Deekshitha G, Jesuraj Bandekar, Pooja VH, Prasanta Kumar Ghosh, Sandhya Badiger, Sathvik Udupa, Saurabh Kumar","submitted_at":"2023-10-13T04:13:26Z","abstract_excerpt":"With the advent of high-quality speech synthesis, there is a lot of interest in controlling various prosodic attributes of speech. Speaking rate is an essential attribute towards modelling the expressivity of speech. In this work, we propose a novel approach to control the speaking rate for non-autoregressive TTS. We achieve this by conditioning the speaking rate inside the duration predictor, allowing implicit speaking rate control. We show the benefits of this approach by synthesising audio at various speaking rate factors and measuring the quality of speaking rate-controlled synthesised spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08846","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/2310.08846/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":"2026-07-05T07:00:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kReFVuRl1kNI0L3urmKWws5wh0OWoD2hmzdJYTdauqHHqqmx/U3cNCRzrCKJcVFgfux0BfB6rSIkvTOChgMfAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:28:41.138916Z"},"content_sha256":"246304398c907f4310a4643013b96b6a6d730beddd912382d2be361be51317fc","schema_version":"1.0","event_id":"sha256:246304398c907f4310a4643013b96b6a6d730beddd912382d2be361be51317fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XQR6VCX2SXBA65JSF4S3FAU67G/bundle.json","state_url":"https://pith.science/pith/XQR6VCX2SXBA65JSF4S3FAU67G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XQR6VCX2SXBA65JSF4S3FAU67G/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":"2026-08-08T09:28:41Z","links":{"resolver":"https://pith.science/pith/XQR6VCX2SXBA65JSF4S3FAU67G","bundle":"https://pith.science/pith/XQR6VCX2SXBA65JSF4S3FAU67G/bundle.json","state":"https://pith.science/pith/XQR6VCX2SXBA65JSF4S3FAU67G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XQR6VCX2SXBA65JSF4S3FAU67G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XQR6VCX2SXBA65JSF4S3FAU67G","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":"def5c9f7354ebb4159577f6a145b4b2cfe4f4bff935c236476827755bc19abd0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-10-13T04:13:26Z","title_canon_sha256":"e0da2bd9896aeb605358bdf13ed2b8534c5eccf6cb6075b7d85bdd2c423ca741"},"schema_version":"1.0","source":{"id":"2310.08846","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08846","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08846v1","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08846","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"pith_short_12","alias_value":"XQR6VCX2SXBA","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"pith_short_16","alias_value":"XQR6VCX2SXBA65JS","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"pith_short_8","alias_value":"XQR6VCX2","created_at":"2026-07-05T07:00:35Z"}],"graph_snapshots":[{"event_id":"sha256:246304398c907f4310a4643013b96b6a6d730beddd912382d2be361be51317fc","target":"graph","created_at":"2026-07-05T07:00:35Z","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/2310.08846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the advent of high-quality speech synthesis, there is a lot of interest in controlling various prosodic attributes of speech. Speaking rate is an essential attribute towards modelling the expressivity of speech. In this work, we propose a novel approach to control the speaking rate for non-autoregressive TTS. We achieve this by conditioning the speaking rate inside the duration predictor, allowing implicit speaking rate control. We show the benefits of this approach by synthesising audio at various speaking rate factors and measuring the quality of speaking rate-controlled synthesised spe","authors_text":"Abhayjeet Singh, Anjali Jayakumar, Deekshitha G, Jesuraj Bandekar, Pooja VH, Prasanta Kumar Ghosh, Sandhya Badiger, Sathvik Udupa, Saurabh Kumar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-10-13T04:13:26Z","title":"Speaking rate attention-based duration prediction for speed control TTS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08846","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":"sha256:629d5d823693fe36ecb51d4f79b5d0b57bf55f2ce1aa18cb599ed208879926b0","target":"record","created_at":"2026-07-05T07:00:35Z","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":"def5c9f7354ebb4159577f6a145b4b2cfe4f4bff935c236476827755bc19abd0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-10-13T04:13:26Z","title_canon_sha256":"e0da2bd9896aeb605358bdf13ed2b8534c5eccf6cb6075b7d85bdd2c423ca741"},"schema_version":"1.0","source":{"id":"2310.08846","kind":"arxiv","version":1}},"canonical_sha256":"bc23ea8afa95c20f75322f25b2829ef9a3e331ce358a9087ac9ca9935aeabbd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc23ea8afa95c20f75322f25b2829ef9a3e331ce358a9087ac9ca9935aeabbd2","first_computed_at":"2026-07-05T07:00:35.786064Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:35.786064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2Kh3Mbhxir94iHQCTO1o5ltuAXwHHM04o/v8zIcCt16iAc6lU+6uSe5ustgpXKLJM8YkPXTAnnCmHb4NLU2OBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:35.786514Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.08846","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:629d5d823693fe36ecb51d4f79b5d0b57bf55f2ce1aa18cb599ed208879926b0","sha256:246304398c907f4310a4643013b96b6a6d730beddd912382d2be361be51317fc"],"state_sha256":"a7f8ca8392562cc1e56642d72ff65b880bde79ee1b6054cc6ce3aa098dee91f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NPaRkxxV49NFodg8iWhC9kZQ5wGPHGcNqApvx7GOvAwhLYOWE2W/n2zISvB4vtskqg0+3ItgojvRTQRtuV0dBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:28:41.145661Z","bundle_sha256":"6ddac67edd5bd4512324587d5f729fa0f8970aa0c134368ce43f018dad16c3ae"}}