Autori
Cutugno, Francesco
Giordano Orsini, Luigi Maria
Norman Vitale, Vincenzo

Titolo
Large scale acoustic models: A new perspective
Periodico
Sistemi intelligenti
Anno: 2023 - Fascicolo: 2 - Pagina iniziale: 401 - Pagina finale: 412

Large 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/10.1422/108137
Testo completo alternativo: https://www.rivisteweb.it/doi/10.1422/108137

Esportazione dati in Refworks (solo per utenti abilitati)

Biblioteche ACNP che possiedono il periodico