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.
Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios
Incorporating Linguistic Constraints from External Knowledge Source for Audio-Visual Target Speech Extraction
Inter-Speaker Relative Cues for Text-Guided Target Speech Extraction
SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline
Attractor-Based Speech Separation of Multiple Utterances by Unknown Number of Speakers
Single-Channel Target Speech Extraction Utilizing Distance and Room Clues
Time-Frequency-Based Attention Cache Memory Model for Real-Time Speech Separation
SepPrune: Structured Pruning for Efficient Deep Speech Separation
A Survey of Deep Learning for Complex Speech Spectrograms
ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Prior
SwinLip: An Efficient Visual Speech Encoder for Lip Reading Using Swin Transformer
SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation
SonicSieve: Bringing Directional Speech Extraction to Smartphones Using Acoustic Microstructures
Passive Underwater Acoustic Signal Separation based on Feature Decoupling Dual-path Network
Causal Self-supervised Pretrained Frontend with Predictive Code for Speech Separation
Contextual Speech Extraction: Leveraging Textual History as an Implicit Cue for Target Speech Extraction
VANPY: Voice Analysis Framework
EDSep: An Effective Diffusion-Based Method for Speech Source Separation
Enhancing Intelligibility for Generative Target Speech Extraction via Joint Optimization with Target Speaker ASR
Leveraging Spatial Cues from Cochlear Implant Microphones to Efficiently Enhance Speech Separation in Real-World Listening Scenes
Beyond Speaker Identity: Text Guided Target Speech Extraction
Reading to Listen at the Cocktail Party: Multi-Modal Speech Separation
Distance Based Single-Channel Target Speech Extraction
U-Mamba-Net: A highly efficient Mamba-based U-net style network for noisy and reverberant speech separation
Speech Separation using Neural Audio Codecs with Embedding Loss
Multiple Choice Learning for Efficient Speech Separation with Many Speakers
Study of the Performance of CEEMDAN in Underdetermined Speech Separation
DCF-DS: Deep Cascade Fusion of Diarization and Separation for Speech Recognition under Realistic Single-Channel Conditions
Speech Separation with Pretrained Frontend to Minimize Domain Mismatch
Task-Aware Unified Source Separation
SepMamba: State-space models for speaker separation using Mamba
Mask-Weighted Spatial Likelihood Coding for Speaker-Independent Joint Localization and Mask Estimation
STCON System for the CHiME-8 Challenge
Investigation of Speaker Representation for Target-Speaker Speech Processing
TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.