TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Speech/Speech Separation

Speech Separation

39 benchmarks359 papers

The task of extracting all overlapping speech sources in a given mixed speech signal refers to the Speech Separation. Speech Separation is a special scenario of source separation problem, where the focus is only on the overlapping speech signal sources and other interferences such as music or noise signals are not the main concern of the study. A recent representative Github project can be referred to ClearerVoice-Studio.

<span class="description-source">Source: A Unified Framework for Speech Separation </span>

Image credit: Speech Separation of A Target Speaker Based on Deep Neural Networks

Benchmarks

Speech Separation on WSJ0-2mix

SI-SDRiSDRiNumber of parameters (M)MACs (G)

Speech Separation on WHAMR!

SI-SDRiNumber of parameters (M)SDRiMACs (G)

Speech Separation on Libri2Mix

SI-SDRiSDRiNumber of parameters (M)SDR

Speech Separation on WSJ0-3mix

SI-SDRi

Speech Separation on LRS2

SI-SNRiSDRiPESQSTOI

Speech Separation on WHAM!

SI-SDRi

Speech Separation on WSJ0-5mix

SI-SDRi

Speech Separation on LRS3

SI-SNRiSDRi

Speech Separation on VoxCeleb2

SI-SNRiSDRi

Speech Separation on WSJ0-4mix

SI-SDRi

Speech Separation on Libri5Mix

SI-SDRi

Speech Separation on Libri10Mix

SI-SDRi

Speech Separation on GRID corpus (mixed-speech)

SDR

Speech Separation on Libri20Mix

SI-SDRi

Speech Separation on LibriCSS

0S0L10%20%30%40%

Speech Separation on Libri15Mix

SI-SDRi

Speech Separation on TCD-TIMIT corpus (mixed-speech)

SDR

Speech Separation on WSJ0-2mix-16k

SI-SDRi

Speech Separation on WSJ0-2mix-extr

SI-SDR

Speech Separation on iKala

NSDR