Papers with Code 아카이브
Target Speaker Extraction
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Extract the dialogue content of the specified target in a multi-person dialogue.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Improving Target Speaker Extraction with Sparse LDA-transformed Speaker Embeddings
GPU-accelerated Guided Source Separation for Meeting Transcription
ExARN: self-attending RNN for target speaker extraction
Adapting self-supervised models to multi-talker speech recognition using speaker embeddings
ImagineNET: Target Speaker Extraction with Intermittent Visual Cue through Embedding Inpainting
Exploiting spatial information with the informed complex-valued spatial autoencoder for target speaker extraction
Semi-supervised Time Domain Target Speaker Extraction with Attention
Speaker-conditioning Single-channel Target Speaker Extraction using Conformer-based Architectures
A Hybrid Continuity Loss to Reduce Over-Suppression for Time-domain Target Speaker Extraction
Coarse-to-Fine Recursive Speech Separation for Unknown Number of Speakers
L-SpEx: Localized Target Speaker Extraction
New Insights on Target Speaker Extraction
Selective Listening by Synchronizing Speech with Lips
Speaker-conditioned Target Speaker Extraction based on Customized LSTM Cells
Target Speaker Verification with Selective Auditory Attention for Single and Multi-talker Speech
Multimodal Attention Fusion for Target Speaker Extraction
Muse: Multi-modal target speaker extraction with visual cues
Multi-Talker MVDR Beamforming Based on Extended Complex Gaussian Mixture Model
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.