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.
A Neural State-Space Model Approach to Efficient Speech Separation
Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data
Speech Separation based on Contrastive Learning and Deep Modularization
Locate and Beamform: Two-dimensional Locating All-neural Beamformer for Multi-channel Speech Separation
Diffusion-based Signal Refiner for Speech Separation
AudioSlots: A slot-centric generative model for audio separation
Deep Learning for Joint Acoustic Echo and Acoustic Howling Suppression in Hybrid Meetings
Multi-channel Speech Separation Using Spatially Selective Deep Non-linear Filters
On Data Sampling Strategies for Training Neural Network Speech Separation Models
End-to-End Integration of Speech Separation and Voice Activity Detection for Low-Latency Diarization of Telephone Conversations
Towards Real-Time Single-Channel Speech Separation in Noisy and Reverberant Environments
Learning-based Robust Speaker Counting and Separation with the Aid of Spatial Coherence
Online Binaural Speech Separation of Moving Speakers With a Wavesplit Network
X-SepFormer: End-to-end Speaker Extraction Network with Explicit Optimization on Speaker Confusion
A Multi-Stage Triple-Path Method for Speech Separation in Noisy and Reverberant Environments
Multi-Dimensional and Multi-Scale Modeling for Speech Separation Optimized by Discriminative Learning
Scaling strategies for on-device low-complexity source separation with Conv-Tasnet
MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions
Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separation
Deep AHS: A Deep Learning Approach to Acoustic Howling Suppression
Short-Term Memory Convolutions
Neural Target Speech Extraction: An Overview
Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation
Improving Target Speaker Extraction with Sparse LDA-transformed Speaker Embeddings
Multi-resolution location-based training for multi-channel continuous speech separation
An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits
Quotations, Coreference Resolution, and Sentiment Annotations in Croatian News Articles: An Exploratory Study
MIMO-DBnet: Multi-channel Input and Multiple Outputs DOA-aware Beamforming Network for Speech Separation
Deep neural network techniques for monaural speech enhancement: state of the art analysis
Deep Neural Mel-Subband Beamformer for In-car Speech Separation
Self-Remixing: Unsupervised Speech Separation via Separation and Remixing
Reverberation as Supervision for Speech Separation
An Adapter based Multi-label Pre-training for Speech Separation and Enhancement
Handling Trade-Offs in Speech Separation with Sparsely-Gated Mixture of Experts
Speech separation with large-scale self-supervised learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.