Speaker separation · MossFormer2 SS 16k

Speaker separation · MossFormer2 SS 16k · TelkNet

Models in this field

1 entries

Includes public test results for models used here and elsewhere. The complete source table is shown by default; conditions and metrics can also be selected for comparison. Scores from different test conditions are not directly comparable.

Only records with verified public inference implementations and matching weights are shown; algorithms requiring no weights are also eligible. Closed services, unreleased weights and unmatched experiment versions are excluded. This is not an all-model leaderboard.

Public weights do not establish a fully open-source license. Expand the data for declared weight licenses and access conditions. Undeclared licenses are marked separately.

BenchmarkRanking category

ClearerVoice-Studio model performance

Choose a dataset to view all metrics for each model. Rows follow the official rank or selected metric. Bold marks each column’s best comparable value, including ties. Different evaluation protocols are ranked separately; missing scores are shown as -.

Deployable entries 1 / source rows 8

Not ranked: 7

A complete public inference package for these experiments has not been verified. Other weights with the same model name do not qualify.

Conv-TasNet · DualPathRNN · DPTNet · SepFormer · TDANet Large · TF-GridNet · SPMamba

The sources use different training or task settings, so compare numbers only within the stated protocol.

Rank by metric

ClearerVoice-Studio model performance
Metric rank	Model	LRS2_2Mix (16 kHz)↑	WSJ0-2Mix (8 kHz)↑	Libri2Mix (8kHz)↑	WHAM! (8 kHz)↑
-	MossFormer2_SS_16KUsed on this site Public weights · Inference code Inference codeWeight license not declared	15.5	22.0	16.7	17.4

Original records (1)

Markers identify models or components used here. Scores and settings come from the cited tests, not a new evaluation of the complete site pipeline.

ClearerVoice-Studio model performance ↗Checked: 2026-10-25

All evaluation sources (1)

Datasets, versions and conditions remain separate, including sources with no eligible ranking rows.

ClearerVoice-Studio model performance ↗
Deployable entries 1 / source rows 8
Not ranked: 7
A complete public inference package for these experiments has not been verified. Other weights with the same model name do not qualify.
Conv-TasNet · DualPathRNN · DPTNet · SepFormer · TDANet Large · TF-GridNet · SPMamba

All original results and sources

Scores apply to the listed dataset, metric and model version; results from different tests are not directly comparable.

The table includes only models with public weights or configurations that can run locally.

ClearerVoice-Studio model performance

Deployable entries 1 / source rows 8

Not ranked: 7

A complete public inference package for these experiments has not been verified. Other weights with the same model name do not qualify.

Conv-TasNet · DualPathRNN · DPTNet · SepFormer · TDANet Large · TF-GridNet · SPMamba

The sources use different training or task settings, so compare numbers only within the stated protocol.

Rank by metric

ClearerVoice-Studio model performance
Metric rank	Model	LRS2_2Mix (16 kHz)↑	WSJ0-2Mix (8 kHz)↑	Libri2Mix (8kHz)↑	WHAM! (8 kHz)↑
-	MossFormer2_SS_16K Public weights · Inference code Inference codeWeight license not declared	15.5	22.0	16.7	17.4

Original records (1)

ClearerVoice-Studio model performance ↗Checked: 2026-10-25

Speaker separation · MossFormer2 SS 16k

Models, parameters, and sources

MossFormer2 SS 16k

Official / repositories

Papers / technical notes

Workflow

Quick feedback

Models in this field

ClearerVoice-Studio model performance

ClearerVoice-Studio model performance