SOTAVerified

Speech Separation

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.

Source: A Unified Framework for Speech Separation

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 359 papers

TitleStatusHype
Dynamic Slimmable Networks for Efficient Speech Separation—0
Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios—0
SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative PipelineCode3
Attractor-Based Speech Separation of Multiple Utterances by Unknown Number of Speakers—0
Single-Channel Target Speech Extraction Utilizing Distance and Room Clues—0
Time-Frequency-Based Attention Cache Memory Model for Real-Time Speech Separation—0
SepPrune: Structured Pruning for Efficient Deep Speech SeparationCode1
A Survey of Deep Learning for Complex Speech Spectrograms—0
ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion PriorCode1
SwinLip: An Efficient Visual Speech Encoder for Lip Reading Using Swin Transformer—0
Show:102550
← PrevPage 1 of 36Next →
All datasetsWSJ0-2mixWHAMR!Libri2MixWSJ0-3mixLRS2WHAM!WSJ0-5mixLRS3VoxCeleb2WSJ0-4mixLibri5MixLibri10Mix

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SepTDASI-SDRi21—Unverified
2Hungarian PITSI-SDRi13.22—Unverified
3Conditional TasNetSI-SDRi11.7—Unverified
4TasTasSI-SDRi11.14—Unverified
5Gated DualPathRNNSI-SDRi10.56—Unverified
6Multi-Decoder DPRNNSI-SDRi5.9—Unverified