Papers with Code 아카이브
Speech Separation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Online speaker diarization of meetings guided by speech separation
TDFNet: An Efficient Audio-Visual Speech Separation Model with Top-down Fusion
Boosting Unknown-number Speaker Separation with Transformer Decoder-based Attractor
Resource-constrained stereo singing voice cancellation
Multi-Input Multi-Output Target-Speaker Voice Activity Detection For Unified, Flexible, and Robust Audio-Visual Speaker Diarization
Single-Microphone Speaker Separation and Voice Activity Detection in Noisy and Reverberant Environments
Hyperbolic Distance-Based Speech Separation
Self-Supervised Disentangled Representation Learning for Robust Target Speech Extraction
Improving Label Assignments Learning by Dynamic Sample Dropout Combined with Layer-wise Optimization in Speech Separation
Seeing Through the Conversation: Audio-Visual Speech Separation based on Diffusion Model
Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction
Real-time Speech Enhancement and Separation with a Unified Deep Neural Network for Single/Dual Talker Scenarios
A Single Speech Enhancement Model Unifying Dereverberation, Denoising, Speaker Counting, Separation, and Extraction
On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments
RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation
GASS: Generalizing Audio Source Separation with Large-scale Data
Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization
DDTSE: Discriminative Diffusion Model for Target Speech Extraction
AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data
SPGM: Prioritizing Local Features for enhanced speech separation performance
Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription
TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition
IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation
Target Speech Extraction with Conditional Diffusion Model
Improving Deep Attractor Network by BGRU and GMM for Speech Separation
Monaural Multi-Speaker Speech Separation Using Efficient Transformer Model
Exploring the Integration of Speech Separation and Recognition with Self-Supervised Learning Representation
Audio-visual End-to-end Multi-channel Speech Separation, Dereverberation and Recognition
Enhanced Neural Beamformer with Spatial Information for Target Speech Extraction
Mixture Encoder for Joint Speech Separation and Recognition
Multi-Loss Convolutional Network with Time-Frequency Attention for Speech Enhancement
Audio-Visual Speech Enhancement With Selective Off-Screen Speech Extraction
An Efficient Speech Separation Network Based on Recurrent Fusion Dilated Convolution and Channel Attention
UNSSOR: Unsupervised Neural Speech Separation by Leveraging Over-determined Training Mixtures
Audio-Visual Speech Separation in Noisy Environments with a Lightweight Iterative Model
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.