Search papers, labs, and topics across Lattice.
Wang Dai, Archontis Politis and Tuomas Virtanen are with the Audio Research Group, Signal Processing Research Center, Tampere University, Finland. (e-mail: wang.dai@tuni.fi; archontis.politis@tuni.fi; tuomas.virtanen@tuni.fi)
1
0
2
Relative cues like "who spoke first" or "who is louder" dramatically boost text-guided speech extraction, even outperforming systems that rely solely on audio.
