Papers with Code 아카이브

Speech Separation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 1
평가표: 19
보존된 평가 기록: 128

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

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/etzinis/unsupervised_spatial_dc

공식 코드

Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures using Spatial Information

https://github.com/facebookresearch/svoice

공식 코드

Voice Separation with an Unknown Number of Multiple Speakers

https://github.com/fgnt/graph_pit

공식 코드

Graph-PIT: Generalized permutation invariant training for continuous separation of arbitrary numbers of speakers

https://github.com/francoisgrondin/steernet

공식 코드

GEV Beamforming Supported by DOA-based Masks Generated on Pairs of Microphones

https://github.com/gnafiy/tpdt-ss-kws

공식 코드

Text-aware Speech Separation for Multi-talker Keyword Spotting

https://github.com/griko/vanpy

공식 코드

VANPY: Voice Analysis Framework

https://github.com/hangtingchen/Beam-Guided-TasNet

공식 코드

Beam-Guided TasNet: An Iterative Speech Separation Framework with Multi-Channel Output

https://github.com/hmartelb/avlit

공식 코드

Audio-Visual Speech Separation in Noisy Environments with a Lightweight Iterative Model

https://github.com/itsnotacie/sepprune

공식 코드

SepPrune: Structured Pruning for Efficient Deep Speech Separation

https://github.com/iveveive/slnspeech

공식 코드

CSLNSpeech: solving extended speech separation problem with the help of Chinese sign language

https://github.com/joonaskalda/pixit

공식 코드

PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker Recordings

https://github.com/jusperlee/ctcnet

공식 코드

An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits

https://github.com/jusperlee/lrs3-for-speech-separation

공식 코드

An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits

https://github.com/jusperlee/sonicsim

공식 코드

SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios

https://github.com/jusperlee/spmamba

공식 코드

SPMamba: State-space model is all you need in speech separation

https://github.com/jwr1995/dtcn

공식 코드

Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation

https://github.com/jwr1995/pubsep

공식 코드

On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments

https://github.com/jyhan03/icassp22-dataset

공식 코드

DPCCN: Densely-Connected Pyramid Complex Convolutional Network for Robust Speech Separation And Extraction

https://github.com/karnwatcharasupat/directional-sparse-filtering-tf

공식 코드

Directional Sparse Filtering using Weighted Lehmer Mean for Blind Separation of Unbalanced Speech Mixtures

https://github.com/lixilinx/IVA4Cocktail

공식 코드

Independent Vector Analysis with Deep Neural Network Source Priors

https://github.com/merlresearch/reverberation-as-supervision

공식 코드

Enhanced Reverberation as Supervision for Unsupervised Speech Separation

https://github.com/merlresearch/tf-locoformer

공식 코드

TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement

https://github.com/mingyue66/textrolmix

공식 코드

Beyond Speaker Identity: Text Guided Target Speech Extraction

https://github.com/modelscope/ClearerVoice-Studio

공식 코드

MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions

https://github.com/mpariente/AsSteroid

공식 코드

Filterbank design for end-to-end speech separation

https://github.com/naplab/Conv-TasNet

공식 코드

Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation

https://github.com/nfurnon/disco

공식 코드

Distributed speech separation in spatially unconstrained microphone arrays

https://github.com/r06944010/Speech-Separation-TF2

공식 코드

Interrupted and cascaded permutation invariant training for speech separation

https://github.com/rrbluke/BSSD

공식 코드

Blind Speech Separation and Dereverberation using Neural Beamforming

https://github.com/ruizhecao96/cmgan

공식 코드

CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement

https://github.com/shaharlutatipersonal/ocd

공식 코드

OCD: Learning to Overfit with Conditional Diffusion Models

https://github.com/shakeddovrat/librimix

공식 코드

Many-Speakers Single Channel Speech Separation with Optimal Permutation Training

https://github.com/sinica-slam/casnet

공식 코드

CasNet: Investigating Channel Robustness for Speech Separation

https://github.com/sinica-slam/cospro-mix

공식 코드

Disentangling the Impacts of Language and Channel Variability on Speech Separation Networks

https://github.com/snuhcs/papez

공식 코드

Papez: Resource-Efficient Speech Separation with Auditory Working Memory

https://github.com/sp-uhh/mp-gtf

공식 코드

A Multi-Phase Gammatone Filterbank for Speech Separation via TasNet

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.