{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NDK3VL7D3HE5ZZ2NEN53O6OTG3","short_pith_number":"pith:NDK3VL7D","canonical_record":{"source":{"id":"2406.02897","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-05T03:36:11Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"703b1813a300a10979947e88d7ce640bf35550bc2665a6094bf80a9e947f847f","abstract_canon_sha256":"b121627e2cbd075647ee4e1143389a57cbfc169a306e2515365ee17865c4b3d4"},"schema_version":"1.0"},"canonical_sha256":"68d5baafe3d9c9dce74d237bb779d336e2c176c6ca6e3ffd08594c908f62964a","source":{"kind":"arxiv","id":"2406.02897","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02897","created_at":"2026-07-05T08:29:28Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02897v2","created_at":"2026-07-05T08:29:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02897","created_at":"2026-07-05T08:29:28Z"},{"alias_kind":"pith_short_12","alias_value":"NDK3VL7D3HE5","created_at":"2026-07-05T08:29:28Z"},{"alias_kind":"pith_short_16","alias_value":"NDK3VL7D3HE5ZZ2N","created_at":"2026-07-05T08:29:28Z"},{"alias_kind":"pith_short_8","alias_value":"NDK3VL7D","created_at":"2026-07-05T08:29:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NDK3VL7D3HE5ZZ2NEN53O6OTG3","target":"record","payload":{"canonical_record":{"source":{"id":"2406.02897","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-05T03:36:11Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"703b1813a300a10979947e88d7ce640bf35550bc2665a6094bf80a9e947f847f","abstract_canon_sha256":"b121627e2cbd075647ee4e1143389a57cbfc169a306e2515365ee17865c4b3d4"},"schema_version":"1.0"},"canonical_sha256":"68d5baafe3d9c9dce74d237bb779d336e2c176c6ca6e3ffd08594c908f62964a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:28.110666Z","signature_b64":"n7igYFXhbzD7Mf/y9yR0usIt7eSIsc1zTN0j9x8+PsHtPQKOEUsdspMOQgzQckbnU/kwZLKRGkrr+W+dem5VBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68d5baafe3d9c9dce74d237bb779d336e2c176c6ca6e3ffd08594c908f62964a","last_reissued_at":"2026-07-05T08:29:28.110186Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:28.110186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.02897","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:29:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cd63Wv+IWXkCe1823zV4l0JbJuYQpKTm+u73PrIsFjEmAjH9LCLR98SYMtbG6sw5hLklzzSMmGDhzXHp+nECBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T22:33:35.752666Z"},"content_sha256":"7e47523b340f3b5c936391560f4411f7a4028f29ec881cfa1f7c565d624f0d2c","schema_version":"1.0","event_id":"sha256:7e47523b340f3b5c936391560f4411f7a4028f29ec881cfa1f7c565d624f0d2c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NDK3VL7D3HE5ZZ2NEN53O6OTG3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"David Aponte, Dung Tran, Kazuhito Koishida, Trung Dang","submitted_at":"2024-06-05T03:36:11Z","abstract_excerpt":"Prior works have demonstrated zero-shot text-to-speech by using a generative language model on audio tokens obtained via a neural audio codec. It is still challenging, however, to adapt them to low-latency scenarios. In this paper, we present LiveSpeech - a fully autoregressive language model-based approach for zero-shot text-to-speech, enabling low-latency streaming of the output audio. To allow multiple token prediction within a single decoding step, we propose (1) using adaptive codebook loss weights that consider codebook contribution in each frame and focus on hard instances, and (2) grou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02897","kind":"arxiv","version":2},"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/2406.02897/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":"2026-07-05T08:29:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FyH/fRVlPjklo5I4DootVdXG8Xh95Drc9xQH77x4GgSrvBzp42hKN2mgDnB7R6EnQXSmJRHJ40uSwzhoOir9BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T22:33:35.753216Z"},"content_sha256":"febd876e4822b968a52587c858f50cf50f0ac84e3fdd7f5e3b684caa7d4ddc31","schema_version":"1.0","event_id":"sha256:febd876e4822b968a52587c858f50cf50f0ac84e3fdd7f5e3b684caa7d4ddc31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NDK3VL7D3HE5ZZ2NEN53O6OTG3/bundle.json","state_url":"https://pith.science/pith/NDK3VL7D3HE5ZZ2NEN53O6OTG3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NDK3VL7D3HE5ZZ2NEN53O6OTG3/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":"2026-08-23T22:33:35Z","links":{"resolver":"https://pith.science/pith/NDK3VL7D3HE5ZZ2NEN53O6OTG3","bundle":"https://pith.science/pith/NDK3VL7D3HE5ZZ2NEN53O6OTG3/bundle.json","state":"https://pith.science/pith/NDK3VL7D3HE5ZZ2NEN53O6OTG3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NDK3VL7D3HE5ZZ2NEN53O6OTG3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NDK3VL7D3HE5ZZ2NEN53O6OTG3","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":"b121627e2cbd075647ee4e1143389a57cbfc169a306e2515365ee17865c4b3d4","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-05T03:36:11Z","title_canon_sha256":"703b1813a300a10979947e88d7ce640bf35550bc2665a6094bf80a9e947f847f"},"schema_version":"1.0","source":{"id":"2406.02897","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02897","created_at":"2026-07-05T08:29:28Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02897v2","created_at":"2026-07-05T08:29:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02897","created_at":"2026-07-05T08:29:28Z"},{"alias_kind":"pith_short_12","alias_value":"NDK3VL7D3HE5","created_at":"2026-07-05T08:29:28Z"},{"alias_kind":"pith_short_16","alias_value":"NDK3VL7D3HE5ZZ2N","created_at":"2026-07-05T08:29:28Z"},{"alias_kind":"pith_short_8","alias_value":"NDK3VL7D","created_at":"2026-07-05T08:29:28Z"}],"graph_snapshots":[{"event_id":"sha256:febd876e4822b968a52587c858f50cf50f0ac84e3fdd7f5e3b684caa7d4ddc31","target":"graph","created_at":"2026-07-05T08:29:28Z","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/2406.02897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prior works have demonstrated zero-shot text-to-speech by using a generative language model on audio tokens obtained via a neural audio codec. It is still challenging, however, to adapt them to low-latency scenarios. In this paper, we present LiveSpeech - a fully autoregressive language model-based approach for zero-shot text-to-speech, enabling low-latency streaming of the output audio. To allow multiple token prediction within a single decoding step, we propose (1) using adaptive codebook loss weights that consider codebook contribution in each frame and focus on hard instances, and (2) grou","authors_text":"David Aponte, Dung Tran, Kazuhito Koishida, Trung Dang","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-05T03:36:11Z","title":"LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02897","kind":"arxiv","version":2},"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":"sha256:7e47523b340f3b5c936391560f4411f7a4028f29ec881cfa1f7c565d624f0d2c","target":"record","created_at":"2026-07-05T08:29:28Z","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":"b121627e2cbd075647ee4e1143389a57cbfc169a306e2515365ee17865c4b3d4","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-05T03:36:11Z","title_canon_sha256":"703b1813a300a10979947e88d7ce640bf35550bc2665a6094bf80a9e947f847f"},"schema_version":"1.0","source":{"id":"2406.02897","kind":"arxiv","version":2}},"canonical_sha256":"68d5baafe3d9c9dce74d237bb779d336e2c176c6ca6e3ffd08594c908f62964a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68d5baafe3d9c9dce74d237bb779d336e2c176c6ca6e3ffd08594c908f62964a","first_computed_at":"2026-07-05T08:29:28.110186Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:28.110186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n7igYFXhbzD7Mf/y9yR0usIt7eSIsc1zTN0j9x8+PsHtPQKOEUsdspMOQgzQckbnU/kwZLKRGkrr+W+dem5VBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:28.110666Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02897","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e47523b340f3b5c936391560f4411f7a4028f29ec881cfa1f7c565d624f0d2c","sha256:febd876e4822b968a52587c858f50cf50f0ac84e3fdd7f5e3b684caa7d4ddc31"],"state_sha256":"112c4c22798b4665882a173a0e434850e0dfc6a06432bb58f9c1151eed7b0264"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4kri96ubIXRkfItLtQO3JJqf00KzcZP2qHKKyTUqIuhUIzCOFFtbXmc3U2zuLcjpCg+keNuc+r9WUMGnjbhkBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T22:33:35.757902Z","bundle_sha256":"fd5363a05ecf74e33a65be96fc501c151588aecd43e5f5e597d3f9916b77734d"}}