https://github.com/Beilong-Tang/TSELM
공식 코드TSELM: Target Speaker Extraction using Discrete Tokens and Language Models
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/Beilong-Tang/lauraTSE_code
공식 코드LauraTSE: Target Speaker Extraction using Auto-Regressive Decoder-Only Language Models
https://github.com/NVIDIA/NeMo
공식 코드Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration
https://github.com/ahmadikalkhorani/AVCrossNet
공식 코드https://github.com/desh2608/diarizer
공식 코드GPU-accelerated Guided Source Separation for Meeting Transcription
https://github.com/desh2608/gss
공식 코드GPU-accelerated Guided Source Separation for Meeting Transcription
https://github.com/fchest/m3anet
공식 코드M3ANet: Multi-scale and Multi-Modal Alignment Network for Brain-Assisted Target Speaker Extraction
https://github.com/gemengtju/l-spex
공식 코드https://github.com/haoxiangsnr/llm-tse
공식 코드Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction
https://github.com/open-mmlab/amphion
공식 코드Metis: A Foundation Speech Generation Model with Masked Generative Pre-training
https://github.com/spkgyk/RTFS-Net
공식 코드RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation
https://github.com/taoruijie/seanet
공식 코드Audio-Visual Target Speaker Extraction with Reverse Selective Auditory Attention
https://github.com/tatban/Spectron
공식 코드Spectron: Target Speaker Extraction using Conditional Transformer with Adversarial Refinement
https://github.com/wenet-e2e/wesep
공식 코드WeSep: A Scalable and Flexible Toolkit Towards Generalizable Target Speaker Extraction
https://github.com/xuchenglin28/speaker_extraction
공식 코드Target Speaker Verification with Selective Auditory Attention for Single and Multi-talker Speech
https://github.com/zbang/usef-tse
공식 코드USEF-TSE: Universal Speaker Embedding Free Target Speaker Extraction
https://github.com/zexupan/avse_hybrid_loss
공식 코드A Hybrid Continuity Loss to Reduce Over-Suppression for Time-domain Target Speaker Extraction
https://github.com/zexupan/imaginenet
공식 코드ImagineNET: Target Speaker Extraction with Intermittent Visual Cue through Embedding Inpainting
https://github.com/zexupan/reentry
공식 코드https://github.com/lin9x/av-sepformer
Muse: Multi-modal target speaker extraction with visual cues
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.