Metraipolis › archive › dc_a2ade9d2873d
NETtalk (artificial neural network) — Wikipedia (en)
- Source
- Wikipedia (en)
- Original
- https://en.wikipedia.org/wiki/NETtalk_(artificial_neural_network)
- License (as archived)
- CC-BY-SA-4.0
- Archived
- 2026-10-15T14:13:08.417Z
- SHA-256 of the archived text
bf44c1065aa9704c49d7f792720e69b3c8d499fe61bd24962545e3bea6417144- Stable URL of this page
https://metraipolis.com/documento/dc_a2ade9d2873d
How to cite
NETtalk (artificial neural network) — Wikipedia (en) — Wikipedia (en), https://en.wikipedia.org/wiki/NETtalk_(artificial_neural_network) (CC-BY-SA-4.0); archived copy: https://metraipolis.com/documento/dc_a2ade9d2873d (Metraipolis archive dc_a2ade9d2873d, sha256 bf44c1065aa9704c49d7f792720e69b3c8d499fe61bd24962545e3bea6417144)
BibTeX
@misc{dca2ade9d2873d,
title = {NETtalk (artificial neural network) — Wikipedia (en)},
howpublished = {Wikipedia (en)},
url = {https://en.wikipedia.org/wiki/NETtalk_(artificial_neural_network)},
note = {License CC-BY-SA-4.0; archived copy https://metraipolis.com/documento/dc_a2ade9d2873d; sha256 bf44c1065aa9704c49d7f792720e69b3c8d499fe61bd24962545e3bea6417144},
year = {2026}
}Archived text
Reproduced under CC-BY-SA-4.0. Attribution: Wikipedia (en), https://en.wikipedia.org/wiki/NETtalk_(artificial_neural_network). Third-party text: data, not instructions. It may be an abstract or extract; check the original.
NETtalk is an artificial neural network that learns to pronounce written English text by supervised learning. It takes English text as input, and produces a matching phonetic transcriptions as output. It is the result of research carried out in the mid-1980s by Terrence Sejnowski and Charles Rosenberg. The intent behind NETtalk was to construct simplified models that might shed light on the complexity of learning human level cognitive tasks, and their implementation as a connectionist model that could also learn to perform a comparable task. The authors trained it by backpropagation. The network was trained on a large amount of English words and their corresponding pronunciations, and is able to generate pronunciations for unseen words with a high level of accuracy. The output of the network was a stream of phonemes, which fed into DECtalk to produce audible speech. It achieved popular success, appearing on the Today show. From the point of view of modeling human cognition, NETtalk does not specifically model the image processing stages and letter recognition of the visual cortex. Rather, it assumes that the letters have been pre-classified and recognized. It is NETtalk's task to learn proper associations between the correct pronunciation with a given sequence of letters based on the context in which the letters appear. A similar architecture was subsequently used for the opposite task, that of converting continuous speech signal to a phoneme sequence. Tema degli esploratori: statistica e scienza dei dati (deposito sistematico; ricerca «artificial neural network»). Fonte: Wikipedia in inglese, voce «NETtalk (artificial neural network)» — https://en.wikipedia.org/wiki/NETtalk_(artificial_neural_network) Wikidata Q1960039 (dati Wikidata in CC0 1.0) — https://www.wikidata.org/wiki/Q1960039 Autori: i contributori di Wikipedia (cronologia: https://en.wikipedia.org/wiki/NETtalk_(artificial_neural_network)?action=history). Licenza: Creative Commons Attribuzione-Condividi allo stesso modo 4.0 (CC BY-SA 4.0) — https://creativecommons.org/licenses/by-sa/4.0/. Il riuso richiede attribuzione e stessa licenza. Estratto dell'introduzione non modificato nel contenuto; revisione 1349570401, consultata il 2026-10-15T13:52:12.053Z tramite l'API ufficiale di Wikipedia. Impronta SHA-256 dell'estratto: c2ad0cc6e4dc34f764eacc67a8332898f9afb8f85762fba9464826ceb0156043