Autori:
Cutugno, Francesco,
Giordano Orsini, Luigi Maria,
Norman Vitale, VincenzoTitolo:
Large scale acoustic models: A new perspectivePeriodico:
Sistemi intelligentiAnno:
2023 - Fascicolo:
2 - Pagina iniziale:
401 - Pagina finale:
412Large Language Models (LLM), such as ChatGPT, generate texts answering to a prompt after being trained through exposition to a huge amount of texts. Similar approaches are applied in Automatic Speech Recognition (ASR) systems which are trained with unprocessed and unlabeled audio data without supervision. The deriving process recalls what a newborn could do to learn speech structure when immersed in the acoustic environment. In parallel with LLM, we refer to this architecture as Large Acoustic Models (LAM). Taking from psycholinguistics literature, we will draw a further parallel between modern ASR and human behaviors introducing the paradigm of artificial language learning. Lastly, a new approach to ASR will be presented, focusing on linguistic theories underlying natural speech.
SICI: 1120-9550(2023)2<401:LSAMAN>2.0.ZU;2-2
Testo completo:
https://www.rivisteweb.it/download/article/10.1422/108137Testo completo alternativo:
https://www.rivisteweb.it/doi/10.1422/108137Esportazione dati in Refworks (solo per utenti abilitati)
Record salvabile in Zotero
Biblioteche ACNP che possiedono il periodico