Improving low-resource Tibetan end-to-end ASR by multilingual and multilevel unit modeling

Abstract Conventional automatic speech recognition (ASR) and emerging end-to-end (E2E) speech recognition have achieved promising results after being provided with sufficient resources. However, for low-resource language, the current ASR is still challenging. The Lhasa dialect is the most widespread...

Descrizione completa

Dettagli Bibliografici

Autori principali:	Siqing Qin, Longbiao Wang, Sheng Li, Jianwu Dang, Lixin Pan
Natura:	Artigo
Lingua:	Inglês
Pubblicazione:	SpringerOpen 2022-01-01
Serie:	EURASIP Journal on Audio, Speech, and Music Processing
Soggetti:	Transfer learning End-to-end Multilingual speech recognition Low-resource language Lhasa dialect
Accesso online:	https://doi.org/10.1186/s13636-021-00233-4
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!