Startseite Neuigkeiten Neueste Forschungsarbeiten Tutorials Datensätze Wiki SOTA LLM-Modelle GPU-Rangliste Veranstaltungen

Deutsch

Speech Separation On Libri2Mix

Metriken

SI-SDRi

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	SI-SDRi	Paper Title	Repository
TDANet	16.9	An efficient encoder-decoder architecture with top-down attention for speech separation
MossFormer2 (w/o DM)	21.7	MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation
MossFormer2 (w speed perturb)	22.2	MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation
Conv-Tasnet (Libri1Mix speech enhancement pre-trained)	14.1	Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training
TF-Locoformer (M)	22.1	TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
WHYV	17.5	An alternative Approach in Voice Extraction	-
TDANet Large	17.4	An efficient encoder-decoder architecture with top-down attention for speech separation
Conv-Tasnet (Libri1Mix speech enhancement multi-task)	13.7	Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training
Conv-Tasnet	13.2	Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training
Separate And Diffuse	21.5	Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation	-

0 of 10 row(s) selected.