RT-03-CTS

The 'RT03-CTS' dataset is used to evaluate speaker diarization systems and their effectiveness in reducing speaker errors in automatic speech recognition (ASR) pipelines.

Papers using RT-03-CTS (7)

Speakers Unembedded: Embedding-free Approach To Long-form Neural Diarization2024 · 2 citesSEAL: Speaker Error Correction Using Acoustic-conditioned Large Language Models2025SEAL: Speaker Error Correction using Acoustic-conditioned Large Language Models2025Lexical Speaker Error Correction: Leveraging Language Models For Speaker Diarization Error Correction2023 · 7 citesLexical Speaker Error Correction: Leveraging Language Models for Speaker Diarization Error Correction2023AG-LSEC: Audio Grounded Lexical Speaker Error Correction2024Speakers Unembedded: Embedding-free Approach to Long-form Neural Diarization2024