Matches in SemOpenAlex for { <https://semopenalex.org/work/W3143186397> ?p ?o ?g. }
- W3143186397 abstract "In the English speech-to-text (STT) machine learning task, acoustic models are conventionally trained on uncased Latin characters, and any necessary orthography (such as capitalization, punctuation, and denormalization of non-standard words) is imputed by separate post-processing models. This adds complexity and limits performance, as many formatting tasks benefit from semantic information present in the acoustic signal but absent in transcription. Here we propose a new STT task: end-to-end neural transcription with fully formatted text for target labels. We present baseline Conformer-based models trained on a corpus of 5,000 hours of professionally transcribed earnings calls, achieving a CER of 1.7. As a contribution to the STT research community, we release the corpus free for non-commercial use at this https URL." @default.
- W3143186397 created "2021-04-13" @default.
- W3143186397 creator A5001291873 @default.
- W3143186397 creator A5005325892 @default.
- W3143186397 creator A5005843015 @default.
- W3143186397 creator A5026088310 @default.
- W3143186397 creator A5027823948 @default.
- W3143186397 creator A5029018277 @default.
- W3143186397 creator A5032957280 @default.
- W3143186397 creator A5033043101 @default.
- W3143186397 creator A5040747392 @default.
- W3143186397 creator A5048403564 @default.
- W3143186397 creator A5051934349 @default.
- W3143186397 creator A5074415592 @default.
- W3143186397 creator A5089791575 @default.
- W3143186397 date "2021-04-05" @default.
- W3143186397 modified "2023-09-26" @default.
- W3143186397 title "SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition" @default.
- W3143186397 cites W1494198834 @default.
- W3143186397 cites W1828163288 @default.
- W3143186397 cites W1995562189 @default.
- W3143186397 cites W2024490156 @default.
- W3143186397 cites W2080134020 @default.
- W3143186397 cites W2101926813 @default.
- W3143186397 cites W2127141656 @default.
- W3143186397 cites W2166637769 @default.
- W3143186397 cites W2189162242 @default.
- W3143186397 cites W2297949011 @default.
- W3143186397 cites W2406343628 @default.
- W3143186397 cites W2546744831 @default.
- W3143186397 cites W2741483887 @default.
- W3143186397 cites W2749051922 @default.
- W3143186397 cites W2880875857 @default.
- W3143186397 cites W2963250244 @default.
- W3143186397 cites W2963403868 @default.
- W3143186397 cites W2974231335 @default.
- W3143186397 cites W3011222885 @default.
- W3143186397 cites W3015752032 @default.
- W3143186397 cites W3023256384 @default.
- W3143186397 cites W3025165719 @default.
- W3143186397 cites W3030437843 @default.
- W3143186397 cites W3127686677 @default.
- W3143186397 cites W3130965709 @default.
- W3143186397 cites W3153592532 @default.
- W3143186397 cites W3198694222 @default.
- W3143186397 cites W97072897 @default.
- W3143186397 hasPublicationYear "2021" @default.
- W3143186397 type Work @default.
- W3143186397 sameAs 3143186397 @default.
- W3143186397 citedByCount "6" @default.
- W3143186397 countsByYear W31431863972021 @default.
- W3143186397 countsByYear W31431863972022 @default.
- W3143186397 crossrefType "posted-content" @default.
- W3143186397 hasAuthorship W3143186397A5001291873 @default.
- W3143186397 hasAuthorship W3143186397A5005325892 @default.
- W3143186397 hasAuthorship W3143186397A5005843015 @default.
- W3143186397 hasAuthorship W3143186397A5026088310 @default.
- W3143186397 hasAuthorship W3143186397A5027823948 @default.
- W3143186397 hasAuthorship W3143186397A5029018277 @default.
- W3143186397 hasAuthorship W3143186397A5032957280 @default.
- W3143186397 hasAuthorship W3143186397A5033043101 @default.
- W3143186397 hasAuthorship W3143186397A5040747392 @default.
- W3143186397 hasAuthorship W3143186397A5048403564 @default.
- W3143186397 hasAuthorship W3143186397A5051934349 @default.
- W3143186397 hasAuthorship W3143186397A5074415592 @default.
- W3143186397 hasAuthorship W3143186397A5089791575 @default.
- W3143186397 hasConcept C111919701 @default.
- W3143186397 hasConcept C127413603 @default.
- W3143186397 hasConcept C138885662 @default.
- W3143186397 hasConcept C150670947 @default.
- W3143186397 hasConcept C154945302 @default.
- W3143186397 hasConcept C179926584 @default.
- W3143186397 hasConcept C201995342 @default.
- W3143186397 hasConcept C204321447 @default.
- W3143186397 hasConcept C2780451532 @default.
- W3143186397 hasConcept C28490314 @default.
- W3143186397 hasConcept C41008148 @default.
- W3143186397 hasConcept C41895202 @default.
- W3143186397 hasConcept C540372491 @default.
- W3143186397 hasConcept C554936623 @default.
- W3143186397 hasConcept C74296488 @default.
- W3143186397 hasConcept C88006597 @default.
- W3143186397 hasConceptScore W3143186397C111919701 @default.
- W3143186397 hasConceptScore W3143186397C127413603 @default.
- W3143186397 hasConceptScore W3143186397C138885662 @default.
- W3143186397 hasConceptScore W3143186397C150670947 @default.
- W3143186397 hasConceptScore W3143186397C154945302 @default.
- W3143186397 hasConceptScore W3143186397C179926584 @default.
- W3143186397 hasConceptScore W3143186397C201995342 @default.
- W3143186397 hasConceptScore W3143186397C204321447 @default.
- W3143186397 hasConceptScore W3143186397C2780451532 @default.
- W3143186397 hasConceptScore W3143186397C28490314 @default.
- W3143186397 hasConceptScore W3143186397C41008148 @default.
- W3143186397 hasConceptScore W3143186397C41895202 @default.
- W3143186397 hasConceptScore W3143186397C540372491 @default.
- W3143186397 hasConceptScore W3143186397C554936623 @default.
- W3143186397 hasConceptScore W3143186397C74296488 @default.
- W3143186397 hasConceptScore W3143186397C88006597 @default.
- W3143186397 hasLocation W31431863971 @default.
- W3143186397 hasOpenAccess W3143186397 @default.