RT-03

The 'RT-03' dataset is a benchmark used to evaluate automatic speech recognition (ASR) systems, specifically focusing on speaker variability and adaptation techniques.

Papers using RT-03 (3)

Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid TDNN ASR Systems2022Confidence Score Based Conformer Speaker Adaptation for Speech Recognition2022Unsupervised Model-based speaker adaptation of end-to-end lattice-free MMI model for speech recognition2022