Accent-robust speech recognition for English in low-resource settings using Manifold Mixup

Abstract We adapt Manifold Mixup theory for accent-robust end-to-end (E2E) Automatic speech recognition (ASR). Accent-variation between a source and target constitutes a domain-mismatch scenario. Manifold Mixup allows cross-domain robustness where a model trained on a source accent generalizes to ta...

Descripción completa

Detalles Bibliográficos

Autores principales:	Tirthankar Banerjee, V. Ramasubramanian
Formato:	Artigo
Lenguaje:	Inglês
Publicado:	SpringerOpen 2025-11-01
Colección:	EURASIP Journal on Audio, Speech, and Music Processing
Materias:	Automated speech recognition Accented speech recognition Manifold mixup Cross accent Indic TIMIT Svarah
Acceso en línea:	https://doi.org/10.1186/s13636-025-00435-0
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!