{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:6QQBBJ4PGDJBLLAD6WNNKW7DZN","short_pith_number":"pith:6QQBBJ4P","canonical_record":{"source":{"id":"2006.01463","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-06-02T09:06:41Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"4c22ffaacd26cda15a79bb547050766a8a69fa62f9ca223bd6a924764c7a6517","abstract_canon_sha256":"22b042c3b6eb040e1528468552b2b7706c0d3190ce2c2b54dbbd8cf886966a30"},"schema_version":"1.0"},"canonical_sha256":"f42010a78f30d215ac03f59ad55be3cb7e0afee0e8ef397afc478bf9aa4d43d6","source":{"kind":"arxiv","id":"2006.01463","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.01463","created_at":"2026-07-05T01:07:17Z"},{"alias_kind":"arxiv_version","alias_value":"2006.01463v1","created_at":"2026-07-05T01:07:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.01463","created_at":"2026-07-05T01:07:17Z"},{"alias_kind":"pith_short_12","alias_value":"6QQBBJ4PGDJB","created_at":"2026-07-05T01:07:17Z"},{"alias_kind":"pith_short_16","alias_value":"6QQBBJ4PGDJBLLAD","created_at":"2026-07-05T01:07:17Z"},{"alias_kind":"pith_short_8","alias_value":"6QQBBJ4P","created_at":"2026-07-05T01:07:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:6QQBBJ4PGDJBLLAD6WNNKW7DZN","target":"record","payload":{"canonical_record":{"source":{"id":"2006.01463","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-06-02T09:06:41Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"4c22ffaacd26cda15a79bb547050766a8a69fa62f9ca223bd6a924764c7a6517","abstract_canon_sha256":"22b042c3b6eb040e1528468552b2b7706c0d3190ce2c2b54dbbd8cf886966a30"},"schema_version":"1.0"},"canonical_sha256":"f42010a78f30d215ac03f59ad55be3cb7e0afee0e8ef397afc478bf9aa4d43d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:07:17.757079Z","signature_b64":"e9AVdOhfHipc4AVXFTaAtT6eqwKLyqrZv9CtSrnzHQnalYJLPCEic65s9NHV5uQxswAb4cA3Pk4zO+HdULcEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f42010a78f30d215ac03f59ad55be3cb7e0afee0e8ef397afc478bf9aa4d43d6","last_reissued_at":"2026-07-05T01:07:17.756636Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:07:17.756636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.01463","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":"2026-07-05T01:07:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7vBdpMpkZcz1jJ5aYRd0T2AJKD1+KZaOTqBNiKdlJu4qrG2SpSjHQokLEROkHPnOrrxHdpVKDLCSJ63ipCcDDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:48:56.173238Z"},"content_sha256":"00e6819a5052ddfef29313f66ff4080169a4f16165c6842056f48f1ad7343439","schema_version":"1.0","event_id":"sha256:00e6819a5052ddfef29313f66ff4080169a4f16165c6842056f48f1ad7343439"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:6QQBBJ4PGDJBLLAD6WNNKW7DZN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An ASR Guided Speech Intelligibility Measure for TTS Model Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Arun Baby, Nagaraj Adiga, Pranav Jawale, Saranya Vinnaitherthan, Sharath Adavanne, Srikanth Konjeti, Sumukh Badam","submitted_at":"2020-06-02T09:06:41Z","abstract_excerpt":"The perceptual quality of neural text-to-speech (TTS) is highly dependent on the choice of the model during training. Selecting the model using a training-objective metric such as the least mean squared error does not always correlate with human perception. In this paper, we propose an objective metric based on the phone error rate (PER) to select the TTS model with the best speech intelligibility. The PER is computed between the input text to the TTS model, and the text decoded from the synthesized speech using an automatic speech recognition (ASR) model, which is trained on the same data as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.01463","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/2006.01463/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":"2026-07-05T01:07:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1qQ1hGO9AouFunAur8WOyjTM43LSm6FEVWEjwJaWeTgKQX1Rfo2DubgAPKohGV3lh1yPpndt0mkTQaY9ot0FCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:48:56.173786Z"},"content_sha256":"9ff07e79cd31eb0f210e550e521922bc4048da2c44dc792944da254757f85bd3","schema_version":"1.0","event_id":"sha256:9ff07e79cd31eb0f210e550e521922bc4048da2c44dc792944da254757f85bd3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6QQBBJ4PGDJBLLAD6WNNKW7DZN/bundle.json","state_url":"https://pith.science/pith/6QQBBJ4PGDJBLLAD6WNNKW7DZN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6QQBBJ4PGDJBLLAD6WNNKW7DZN/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":"2026-08-10T14:48:56Z","links":{"resolver":"https://pith.science/pith/6QQBBJ4PGDJBLLAD6WNNKW7DZN","bundle":"https://pith.science/pith/6QQBBJ4PGDJBLLAD6WNNKW7DZN/bundle.json","state":"https://pith.science/pith/6QQBBJ4PGDJBLLAD6WNNKW7DZN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6QQBBJ4PGDJBLLAD6WNNKW7DZN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6QQBBJ4PGDJBLLAD6WNNKW7DZN","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":"22b042c3b6eb040e1528468552b2b7706c0d3190ce2c2b54dbbd8cf886966a30","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-06-02T09:06:41Z","title_canon_sha256":"4c22ffaacd26cda15a79bb547050766a8a69fa62f9ca223bd6a924764c7a6517"},"schema_version":"1.0","source":{"id":"2006.01463","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.01463","created_at":"2026-07-05T01:07:17Z"},{"alias_kind":"arxiv_version","alias_value":"2006.01463v1","created_at":"2026-07-05T01:07:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.01463","created_at":"2026-07-05T01:07:17Z"},{"alias_kind":"pith_short_12","alias_value":"6QQBBJ4PGDJB","created_at":"2026-07-05T01:07:17Z"},{"alias_kind":"pith_short_16","alias_value":"6QQBBJ4PGDJBLLAD","created_at":"2026-07-05T01:07:17Z"},{"alias_kind":"pith_short_8","alias_value":"6QQBBJ4P","created_at":"2026-07-05T01:07:17Z"}],"graph_snapshots":[{"event_id":"sha256:9ff07e79cd31eb0f210e550e521922bc4048da2c44dc792944da254757f85bd3","target":"graph","created_at":"2026-07-05T01:07:17Z","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/2006.01463/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The perceptual quality of neural text-to-speech (TTS) is highly dependent on the choice of the model during training. Selecting the model using a training-objective metric such as the least mean squared error does not always correlate with human perception. In this paper, we propose an objective metric based on the phone error rate (PER) to select the TTS model with the best speech intelligibility. The PER is computed between the input text to the TTS model, and the text decoded from the synthesized speech using an automatic speech recognition (ASR) model, which is trained on the same data as ","authors_text":"Arun Baby, Nagaraj Adiga, Pranav Jawale, Saranya Vinnaitherthan, Sharath Adavanne, Srikanth Konjeti, Sumukh Badam","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-06-02T09:06:41Z","title":"An ASR Guided Speech Intelligibility Measure for TTS Model Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.01463","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":"sha256:00e6819a5052ddfef29313f66ff4080169a4f16165c6842056f48f1ad7343439","target":"record","created_at":"2026-07-05T01:07:17Z","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":"22b042c3b6eb040e1528468552b2b7706c0d3190ce2c2b54dbbd8cf886966a30","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-06-02T09:06:41Z","title_canon_sha256":"4c22ffaacd26cda15a79bb547050766a8a69fa62f9ca223bd6a924764c7a6517"},"schema_version":"1.0","source":{"id":"2006.01463","kind":"arxiv","version":1}},"canonical_sha256":"f42010a78f30d215ac03f59ad55be3cb7e0afee0e8ef397afc478bf9aa4d43d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f42010a78f30d215ac03f59ad55be3cb7e0afee0e8ef397afc478bf9aa4d43d6","first_computed_at":"2026-07-05T01:07:17.756636Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:07:17.756636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e9AVdOhfHipc4AVXFTaAtT6eqwKLyqrZv9CtSrnzHQnalYJLPCEic65s9NHV5uQxswAb4cA3Pk4zO+HdULcEDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:07:17.757079Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.01463","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00e6819a5052ddfef29313f66ff4080169a4f16165c6842056f48f1ad7343439","sha256:9ff07e79cd31eb0f210e550e521922bc4048da2c44dc792944da254757f85bd3"],"state_sha256":"6065894104419014351200a9b50411ddf5904b80077042c16d6e739c25e7befa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tCYa8R90dPUShuVDyah6/EOedjER39lwC/NSqVHnFo1lVCWCyrhlnG3rwZmi8Oq4sp91NWPV5k0BNAa7/vOOAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T14:48:56.179623Z","bundle_sha256":"0aecbaf602e75433168d16252ecd8f4e3b749c350f9e5c3b917ac8414fe9c9e3"}}