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.
Low-Latency Speech Separation Guided Diarization for Telephone Conversations
Target Confusion in End-to-end Speaker Extraction: Analysis and Approaches
Speaker Extraction with Co-Speech Gestures Cue
EEND-SS: Joint End-to-End Neural Speaker Diarization and Speech Separation for Flexible Number of Speakers
Disentangling the Impacts of Language and Channel Variability on Speech Separation Networks
Coarse-to-Fine Recursive Speech Separation for Unknown Number of Speakers
Remix-cycle-consistent Learning on Adversarially Learned Separator for Accurate and Stable Unsupervised Speech Separation
Embedding Recurrent Layers with Dual-Path Strategy in a Variant of Convolutional Network for Speaker-Independent Speech Separation
Investigating self-supervised learning for speech enhancement and separation
VoViT: Low Latency Graph-based Audio-Visual Voice Separation Transformer
Harmonicity Plays a Critical Role in DNN Based Versus in Biologically-Inspired Monaural Speech Segregation Systems
Audio-visual speech separation based on joint feature representation with cross-modal attention
Deep Learning-Based Joint Control of Acoustic Echo Cancellation, Beamforming and Postfiltering
Royalflush Speaker Diarization System for ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge
MixCycle: Unsupervised Speech Separation via Cyclic Mixture Permutation Invariant Training
Exploring Self-Attention Mechanisms for Speech Separation
The RoyalFlush System of Speech Recognition for M2MeT Challenge
SkiM: Skipping Memory LSTM for Low-Latency Real-Time Continuous Speech Separation
Endpoint Detection for Streaming End-to-End Multi-talker ASR
DPCCN: Densely-Connected Pyramid Complex Convolutional Network for Robust Speech Separation And Extraction
Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problem
Learning-based personal speech enhancement for teleconferencing by exploiting spatial-spectral features
Directed Speech Separation for Automatic Speech Recognition of Long Form Conversational Speech
A Time-domain Real-valued Generalized Wiener Filter for Multi-channel Neural Separation Systems
Multi-Channel Multi-Speaker ASR Using 3D Spatial Feature
A Conformer-based ASR Frontend for Joint Acoustic Echo Cancellation, Speech Enhancement and Speech Separation
Single-channel speech separation using Soft-minimum Permutation Invariant Training
Inter-channel Conv-TasNet for multichannel speech enhancement
LiMuSE: Lightweight Multi-modal Speaker Extraction
Target Speech Extraction: Independent Vector Extraction Guided by Supervised Speaker Identification
Continuous Speech Separation with Recurrent Selective Attention Network
Separating Long-Form Speech with Group-Wise Permutation Invariant Training
Progressive Learning for Stabilizing Label Selection in Speech Separation with Mapping-based Method
REAL-M: Towards Speech Separation on Real Mixtures
All-neural beamformer for continuous speech separation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.