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.
SCA: Streaming Cross-attention Alignment for Echo Cancellation
Audio-Visual Speech Enhancement and Separation by Utilizing Multi-Modal Self-Supervised Embeddings
Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation
CasNet: Investigating Channel Robustness for Speech Separation
Provable Subspace Identification Under Post-Nonlinear Mixtures
OCD: Learning to Overfit with Conditional Diffusion Models
An efficient encoder-decoder architecture with top-down attention for speech separation
CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement
VarArray Meets t-SOT: Advancing the State of the Art of Streaming Distant Conversational Speech Recognition
Streaming Target-Speaker ASR with Neural Transducer
Analysis of impact of emotions on target speech extraction and speech separation
Recycling an anechoic pre-trained speech separation deep neural network for binaural dereverberation of a single source
Conv-NILM-Net, a causal and multi-appliance model for energy source separation
ConceptBeam: Concept Driven Target Speech Extraction
ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding
SATTS: Speaker Attractor Text to Speech, Learning to Speak by Learning to Separate
Dual-Path Cross-Modal Attention for better Audio-Visual Speech Extraction
Multi-Modal Multi-Correlation Learning for Audio-Visual Speech Separation
Efficient Transformer-based Speech Enhancement Using Long Frames and STFT Magnitudes
On the Role of Spatial, Spectral, and Temporal Processing for DNN-based Non-linear Multi-channel Speech Enhancement
Resource-Efficient Separation Transformer
Simultaneous Speech Extraction for Multiple Target Speakers under the Meeting Scenarios
Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations
AmbiSep: Ambisonic-to-Ambisonic Reverberant Speech Separation Using Transformer Networks
Conversational Speech Separation: an Evaluation Study for Streaming Applications
An enhanced Conv-TasNet model for speech separation using a speaker distance-based loss function
SepIt: Approaching a Single Channel Speech Separation Bound
MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes
Separator-Transducer-Segmenter: Streaming Recognition and Segmentation of Multi-party Speech
Ultra Fast Speech Separation Model with Teacher Student Learning
Heterogeneous Separation Consistency Training for Adaptation of Unsupervised Speech Separation
RadioSES: mmWave-Based Audioradio Speech Enhancement and Separation System
Listen only to me! How well can target speech extraction handle false alarms?
Leveraging Real Conversational Data for Multi-Channel Continuous Speech Separation
Heterogeneous Target Speech Separation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.