Arabic-English CS benchmarks

The 'Arabic-English CS benchmarks' consists of datasets used to evaluate the performance of speech recognition models on Arabic-English code-switched speech.

Papers using Arabic-English CS benchmarks (2)

SAGE: Spliced-Audio Generated Data for Enhancing Foundational Models in Low-Resource Arabic-English Code-Switched Speech Recognition2025Adapting the adapters for code-switching in multilingual ASR2023 · 2 cites