Multiple choice learning matches permutation invariant training for speech separation on WSJ0-mix and LibriMix with up to 20 speakers, at lower loss-computation cost.
All-neural online source separation, counting, and diarization for meeting analysis,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multiple Choice Learning for Efficient Speech Separation with Many Speakers
Multiple choice learning matches permutation invariant training for speech separation on WSJ0-mix and LibriMix with up to 20 speakers, at lower loss-computation cost.