← all datasets

WSJ-0-2mix-extr

Emerging
4papers using it
2022first seen

The 'WSJ0-2mix-extr' dataset/benchmark contains mixed audio recordings of two speakers and is used to evaluate target-speaker automatic speech recognition (TS-ASR) performance.

Papers using WSJ-0-2mix-extr (4)

WSJ-0-2mix-extr β€” datasets β€” speech-audio