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.
Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domain
North America Bixby Speaker Diarization System for the VoxCeleb Speaker Recognition Challenge 2021
Continuous Streaming Multi-Talker ASR with Dual-path Transducers
Complementing Handcrafted Features with Raw Waveform Using a Light-weight Auxiliary Model
Graph-PIT: Generalized permutation invariant training for continuous separation of arbitrary numbers of speakers
Improving Reverberant Speech Separation with Multi-stage Training and Curriculum Learning
Multi-Task Audio Source Separation
Separation Guided Speaker Diarization in Realistic Mismatched Conditions
A Comparative Study of Modular and Joint Approaches for Speaker-Attributed ASR on Monaural Long-Form Audio
Investigation of Practical Aspects of Single Channel Speech Separation for ASR
Sparsely Overlapped Speech Training in the Time Domain: Joint Learning of Target Speech Separation and Personal VAD Benefits
Deep neural network Based Low-latency Speech Separation with Asymmetric analysis-Synthesis Window Pair
Teacher-Student MixIT for Unsupervised and Semi-supervised Speech Separation
Dual-Path Filter Network: Speaker-Aware Modeling for Speech Separation
Improving Channel Decorrelation for Multi-Channel Target Speech Extraction
Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition
A cappella: Audio-visual Singing Voice Separation
Many-Speakers Single Channel Speech Separation with Optimal Permutation Training
MIMO Self-attentive RNN Beamformer for Multi-speaker Speech Separation
Streaming Multi-talker Speech Recognition with Joint Speaker Identification
Configurable Privacy-Preserving Automatic Speech Recognition
Guided Training: A Simple Method for Single-channel Speaker Separation
Looking into Your Speech: Learning Cross-modal Affinity for Audio-visual Speech Separation
Blind Speech Separation and Dereverberation using Neural Beamforming
USTC-NELSLIP System Description for DIHARD-III Challenge
Continuous Speech Separation with Ad Hoc Microphone Arrays
Compute and memory efficient universal sound source separation
Tune-In: Training Under Negative Environments with Interference for Attention Networks Simulating Cocktail Party Effect
Audio-Visual Speech Separation Using Cross-Modal Correspondence Loss
Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation
Integration of deep learning with expectation maximization for spatial cue based speech separation in reverberant conditions
End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend
Dual-Path Modeling for Long Recording Speech Separation in Meetings
Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism
Beam-Guided TasNet: An Iterative Speech Separation Framework with Multi-Channel Output
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.