Auxiliary geolocation prediction with injected conditioning signals improves dialect and accent robustness in SSL-based spoken language identification, reaching new SOTA on FLEURS and ML-SUPERB 2.0.
OWSM v3.1: Better and faster open Whisper-style speech models based on E-Branchformer,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Geolocation-Aware Robust Spoken Language Identification
Auxiliary geolocation prediction with injected conditioning signals improves dialect and accent robustness in SSL-based spoken language identification, reaching new SOTA on FLEURS and ML-SUPERB 2.0.