Pith. sign in

TF- GridNet: Integrating full- and sub-band modeling for speech separation,

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

eess.AS 1

years

2024 1

verdicts

CONDITIONAL 1

representative citing papers

Speech Separation using Neural Audio Codecs with Embedding Loss

eess.AS · 2024-11-27 · conditional · novelty 5.0

Codecformer-EL replaces the waveform loss in codec-based speech separation with an MSE loss on frozen codec embeddings, cutting training cost by about half and improving perceptual metrics on WSJ0-2mix.

citing papers explorer

Showing 1 of 1 citing paper.

  • Speech Separation using Neural Audio Codecs with Embedding Loss eess.AS · 2024-11-27 · conditional · none · ref 7

    Codecformer-EL replaces the waveform loss in codec-based speech separation with an MSE loss on frozen codec embeddings, cutting training cost by about half and improving perceptual metrics on WSJ0-2mix.