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.
ADL-MVDR: All deep learning MVDR beamformer for target speech separation
Continuous Speech Separation with Conformer
Efficient Integration of Multi-channel Information for Speaker-independent Speech Separation
Speech Separation Based on Multi-Stage Elaborated Dual-Path Deep BiLSTM with Auxiliary Identity Loss
MIRNet: Learning multiple identities representations in overlapped speech
CSLNSpeech: solving extended speech separation problem with the help of Chinese sign language
Sudo rm -rf: Efficient Networks for Universal Audio Source Separation
Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networks
Exploring the time-domain deep attractor network with two-stream architectures in a reverberant environment
Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals
Unsupervised Sound Separation Using Mixture Invariant Training
Multi-talker ASR for an unknown number of sources: Joint training of source counting, separation and ASR
Identify Speakers in Cocktail Parties with End-to-End Attention
GEV Beamforming Supported by DOA-based Masks Generated on Pairs of Microphones
Audio-visual Multi-channel Recognition of Overlapped Speech
Target Speech Extraction Based on Blind Source Separation and X-vector-based Speaker Selection Trained with Data Augmentation
FaceFilter: Audio-visual speech separation using still images
Neural Speech Separation Using Spatially Distributed Microphones
CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings
Simultaneous Denoising and Dereverberation Using Deep Embedding Features
WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-end Speech Enhancement
Deep Attention Fusion Feature for Speech Separation with End-to-End Post-filter Method
Multi-modal Multi-channel Target Speech Separation
Enhancing End-to-End Multi-channel Speech Separation via Spatial Feature Learning
Voice Separation with an Unknown Number of Multiple Speakers
Wavesplit: End-to-End Speech Separation by Speaker Clustering
Spatial and spectral deep attention fusion for multi-channel speech separation using deep embedding features
Continuous speech separation: dataset and analysis
Improving speaker discrimination of target speech extraction with time-domain SpeakerBeam
Audio-visual Recognition of Overlapped speech for the LRS2 dataset
Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation
Utterance-level Permutation Invariant Training with Latency-controlled BLSTM for Single-channel Multi-talker Speech Separation
End-to-end training of time domain audio separation and recognition
A Unified Framework for Speech Separation
Advances in Online Audio-Visual Meeting Transcription
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.